EP4427478A1

EP4427478A1 - Sustainable network engineering for energy savings in mobile networks

Info

Publication number: EP4427478A1
Application number: EP21810429.7A
Authority: EP
Inventors: Eugene Gomes; Premnath Kandhasamy NARAYANAN; Armagan USKUDAR; Mahmood Osorio; Amy DE BUITLÉIR; Diego MARTOS; James O'meara; Peter Moonen; Xin Li
Original assignee: Telefonaktiebolaget LM Ericsson AB
Current assignee: Telefonaktiebolaget LM Ericsson AB
Priority date: 2021-11-05
Filing date: 2021-11-05
Publication date: 2024-09-11
Also published as: WO2023079348A1

Abstract

Embodiments of the application offer efficient ways to conserve energy in mobile networks. In one embodiment, a computerized method for saving energy includes determining which of one or more nodes in a plurality of nodes of a mobile network in which to activate the at least one energy savings function to provide energy, where the determination comprises identifying a plurality of key impact areas of energy savings for the mobile network. Based on the determination of the nodes in the plurality of nodes, the method continues with configuring at least one node that is not the determined node and at least one node of the determined nodes to prepare for activating the at least one energy savings function. The method further includes providing energy savings for the mobile network by activating the at least one energy savings function in the determined nodes.

Description

SPECIFICATION

SUSTAINABLE NETWORK ENGINEERING FOR ENERGY SAVINGS IN MOBILE NETWORKS

TECHNICAL FIELD

[0001] Embodiments of the invention relate to the field of energy conservation in mobile networks.

BACKGROUND ART

[0002] Energy consumption of telecommunication networks is increasing as the technologies evolve (e.g., the 4^th Generation (4G)/Long Term Evolution (LTE), 5G/New Radio (NR) and beyond 5G networks). Existing methods and techniques are focused on energy savings with specific network configurations and to yield best results. Specific autonomous network functions (e.g., self-organizing network (SON)) provide needed energy savings functions (also referred to as energy functions, energy saving functions, energy saving features, energy savings features, network functions for energy saving, and these terms are used interchangeably in this disclosure unless noted otherwise). To get the best potential for energy savings, different network function selection strategy (e.g., enabling selected energy savings functions at the correct sites) and specific network configurations are needed in mobile networks (also referred to as mobile telecommunications networks, wireless networks, cellular networks, or simply networks, and these terms are used interchangeably in this disclosure unless noted otherwise). [0003] Common energy saving methods for wireless telecommunication equipment deployed in mobile networks are (1) building energy efficient hardware, (2) activating energy savings functions such as radio access network (RAN) energy savings functions, core energy savings functions, data center energy savings functions; and (3) plugging in more sustainable energies produced through renewable energy sources for running the networks. Among them, method (2) is presently a widely used approach where autonomous network functions are activated on all the nodes in a mobile network.

[0004] Although methods (1) and (3) above are efficient, all of them need more capital expenditure. Further, method (3) requires additional technological advancement to meet energy demands. Additionally, energy savings autonomous network functions used in method (2) do not yield higher power savings on all the nodes where they are activated. In fact, in certain nodes they cause issues related to customer experience and contradict service level agreements (SLAs) with subscribers, and operators are forced to activate these functions selectively on the network. Currently such selective process is manual. Also, centralized controller functions such as the network function orchestrator used in method (2) identify such energy savings functions as a key reason for degradation in network performance and the centralized controller functions disable the features autonomously as the needed intent or goal is not met. As mobile networks continue to grow and expand due to new technology and standards, additional resources and hardware are used to accommodate the traffic growth. More resources in the network introduced over time leads to higher power consumption. Thus, better ways to achieve energy savings in a mobile network are needed.

SUMMARY

[0005] Embodiments of the application offer efficient ways to conserve energy in mobile telecommunications networks. In one embodiment, a computerized method for saving energy in a mobile telecommunications network includes determining which of one or more nodes in a plurality of nodes of the mobile telecommunications network in which to activate the at least one energy savings function to provide energy savings to the mobile telecommunications network, where the determination comprises identifying a plurality of key impact areas of energy savings for the mobile telecommunications network. Based on the determination of the nodes in the plurality of nodes, the method continues with configuring at least one node that is not the determined node and at least one node of the determined nodes to prepare for activating the at least one energy savings function. The method further includes providing energy savings for the mobile telecommunications network by activating the at least one energy savings function in the determined nodes.

[0006] In one embodiment, a computer system is disclosed to perform operations for saving energy in a mobile telecommunications network. The computer system comprises a processor and memory coupled to the processor, where the memory stores instructions, which when executed by the processor, are capable to perform the method including determining which of one or more nodes in a plurality of nodes of the mobile telecommunications network in which to activate the at least one energy savings function to provide energy savings to the mobile telecommunications network, where the determination comprises identifying a plurality of key impact areas of energy savings for the mobile telecommunications network. Based on the determination of the nodes in the plurality of nodes, the computer system continues with configuring at least one node that is not the determined node and at least one node of the determined nodes to prepare for activating the at least one energy savings function. The computer system further provides energy savings for the mobile telecommunications network by activating the at least one energy savings function in the determined nodes.

[0007] In one embodiment, non-transitory computer readable medium storing instructions is disclosed. When the instructions are executed by a processor, these instructions are capable to perform a method, including determining which of one or more nodes in a plurality of nodes of the mobile telecommunications network in which to activate the at least one energy savings function to provide energy savings to the mobile telecommunications network, where the determination comprises identifying a plurality of key impact areas of energy savings for the mobile telecommunications network. Based on the determination of the nodes in the plurality of nodes, the method continues with configuring at least one node that is not the determined node and at least one node of the determined nodes to prepare for activating the at least one energy savings function. The method further includes providing energy savings for the mobile telecommunications network by activating the at least one energy savings function in the determined nodes.

[0008] Through embodiments disclosed herein, sites and energy savings functions for nodes in a mobile telecommunications network are identified to achieve maximum yield without compromising customer experience.

BRIEF DESCRIPTION OF THE DRAWINGS

[0009] The invention may best be understood by referring to the following description and accompanying drawings that are used to illustrate embodiments of the invention. In the drawings:

[0010] Figure 1A is a block diagram showing various portions of a system for sustainable network engineering in mobile networks per some embodiments.

[0011] Figure IB is a block diagram showing an expanded view of a sustainable network engineering apparatus of Figure 1A per some embodiments.

[0012] Figure 1C is a block diagram showing an expanded view of time aware modeling per some embodiments. [0013] Figure 2A is a table showing the identification of KPI features and key impact areas for sector/cell selection for energy savings per some embodiments.

[0014] Figure 2B is a diagram showing the multiple impact areas for energy savings per some embodiments.

[0015] Figure 3 shows the determination of the correlation scores per some embodiments. [0016] Figures 4 provides a graph showing analysis of relative importance of KPI features per some embodiments.

[0017] Figure 5 is a block diagram showing thresholds derived through tree classifier rules per some embodiments.

[0018] Figure 6 summarizes example energy savings functions that may be used by a sustainable network engineering system per some embodiments.

[0019] Figure 7 is a block diagram showing an example of the use of sustainable network engineering system associated with a particular energy savings function per some embodiments. [0020] Figure 8 is a flow diagram showing operations of activating one or more energy savings functions per some embodiments.

[0021] Figure 9 is a block diagram showing a sustainable network engineering system in a cloud native environment per some embodiments.

[0022] Figure 10 shows an example computer system to perform operations discussed here per some embodiments.

DETAILED DESCRIPTION

[0023] Certain aspects of the present disclosure and their embodiments may provide solutions to challenges facing the common energy saving methods for wireless telecommunication equipment described herein. A novel site selection, feature selection, and parameter configuration method is provided. A sustainable network engineering (SNE) apparatus applies methods that could identify sites and energy savings functions for nodes in the network by applying needed network configurations and prerequisite optimization functions before activating energy savings functions. A SNE apparatus and method activates energy savings functions on the nodes where there will be maximum yield and without compromising customer experience. Selecting the nodes for activation and de-activation of energy savings functions based on identified thresholds helps save energy and allows autonomous network functions to yield higher power savings on all the nodes where they are activated. [0024] An advantage of this approach is that nodes do not contradict the service level agreements of the subscribers. Further, the selection process can be automated. Also, centralized controller functions such as the ones of the Self-Organizing Network (SON) coordinator will no longer identify such energy savings functions as a key reason for degradation in network performance and they do not disable the features autonomously.

[0025] Further, the focus is on nodes and energy savings functions that will yield the most energy gain, and the existing network footprint is not changed (e.g., coverage, capacity, and service/traffic pattern). By ensuring quality of service (QoS), the customer experience does not degrade. Moreover, this approach allows other autonomous network functions to co-exist and continue their objective (e.g., self-organizing networks coverage, load balancing, and other outage compensation network functions). The solution is allowed to evolve in response to changes in the network and traffic patterns. In addition, this approach prioritizes cellular network quality key performance indicators (KPIs) along with traffic KPIs including resource usage, traffic, and throughput.

[0026] Some of the embodiments contemplated herein will now be described more fully with reference to the accompanying drawings. Other embodiments, however, are contained within the scope of the subject matter disclosed herein, the disclosed subject matter should not be construed as limited to only the embodiments set forth herein; rather, these embodiments are provided by way of example to convey the scope of the subject matter to those skilled in the art. [0027] Certain embodiments of the present disclosure may include some, all, or none of the above advantages. Other advantages will be apparent to those of ordinary skill in the art.

Sustainable Network Engineering System

[0028] Figure 1A is a block diagram showing various portions of a system for sustainable network engineering in mobile networks per some embodiments. Through a sustainable network engineering system (SNES) 100, the key impact areas of energy savings in a network are identified and the nodes to activate one or more energy savings functions are determined. The system 100 may include a radio network 1 (shown and referred to as reference 112 herein), a network management system 2 (reference 114), a data preparation sub-system 3 (reference 116), a sustainable network engineering apparatus 4 (reference 102), a network configuration apparatus 5 (reference 118), and an autonomous network functions model 6 (reference 120). According to the teachings of the disclosure, sustainable network engineering (SNE) apparatus 102 identifies (1) sites, (2) energy savings functions for nodes, and (3) parameter configuration in order to save energy for radio network 112, as described in more detail below. Note some of the entities shown may be outside of the sustainable network engineering system (SNES) 100 and/or they may be a part of existing entities (thus not changing the network footprint). In some embodiments, the sustainable network engineering system 100 includes hardware/software implementing the sustainable network engineering apparatus 102, all or a subset of other entities shown in Figure 1 A use existing hardware/software in the mobile networks.

[0029] Radio network 112 (e.g., LTE, 5G) provides services to the connected users (e.g., mobile phones) and devices (e.g., Internet of things (loT) devices). Radio network 112 additionally logs all the network events, performance counters, faulty alarms as they occur. Radio network 112 may comprise and/or interface with any type of communication, telecommunication, data, cellular, and/or radio network or other similar type of system. In some embodiments, the mobile network may be configured to operate according to specific standards or other types of predefined rules or procedures. Thus, particular embodiments of the radio network 112 may implement communication standards, such as Global System for Mobile Communications (GSM), Universal Mobile Telecommunications System (UMTS), LTE, and/or other suitable 2G, 3G, 4G, or 5G standards; wireless local area network (WLAN) standards, such as the IEEE 802.11 standards; and/or any other appropriate wireless communication standard, such as the Worldwide Interoperability for Microwave Access (WiMax), Bluetooth, Z- Wave, and/or ZigBee standards.

[0030] Network management system 114 (NMS) processes the needed network data and provides processed data in a structured format with their respective interfaces (e.g., structured query language (SQL), representational state transfer (REST)). Data preparation subsystem 116 processes the network data to fit as per the needs of the sustainable network engineering apparatus 102. When data is collected from the network management system 114, the data may be grouped at sector and/or cell levels. For example, data preparation subsystem 116 aggregates data of key performance indicators (KPIs) to a sector level (e.g., from current cell level) when the energy consumption telemetry data is available at the sector level. Additionally, the data may be categorized based on their characteristics when they are collected from the network management system 114. For example, the data may be sliced into different regions (e.g., urban or rural) and/or different bands, and they are prepared differently in the data preparation subsystem 116. [0031] Sustainable network engineering (SNE) apparatus 102 applies the data from data preparation subsystem 116 and produces output to network configuration apparatus 118. One output relates to key impact areas of energy saving and their relevance, such as which aspect of wireless telecommunication is consuming more energy (referred to as key impact areas, such as radio utilization measurements, uplink/downlink quality measurements, traffic measurements, configuration measurements, and the like), as described in greater detail below in conjunction with Figures 2A-2B. Additionally or alternatively, the output relates to derived KPI feature values (such as correlation scores, relative importance scores, and threshold valued explained in Figure 2A) from SNE apparatus 102. The output is produced using methods such as correlation, surrogative modeling (also referred to as surrogative algorithm), and causation analysis using, in one embodiment, a decision tree classifier.

[0032] Another output from SNE apparatus 102 includes a proposal for activation of nodes with energy savings functions (e.g., where high energy saving yield is possible). The nodes may be derived from selecting site (e.g., from an urban/rural region), sector, or cell to activate the energy saving functions. The selection may also use methods such as correlation, surrogative modeling, and causation analysis as discussed herein. Examples of the node selection are described in greater details in conjunction with Figure 5. These selected nodes may be prepared by changing configurations for activating the energy savings functions as shown at reference 132. Examples of activating energy savings functions are described in greater detail below in conjunction with Figure 7.

[0033] For nodes that are not part of energy activation, the SNE apparatus 102 proposes an optimization function with the intended goal, before activating the energy savings functions. The optimization function may cause the nodes that are not part of energy activation to mitigate the impact of activating the energy savings functions at the selected nodes. These outputs are provided to network configuration apparatus 118.

[0034] Note that SNE apparatus 102 maintains an energy saving score for each of the nodes in the radio network 112 and reinforces an SNE strategy based on energy saving intended goals in some embodiments. Energy score is a metric that indicates energy efficiency of the network.

For example, in one embodiment, the energy score may indicate a ratio between overall capacity utilization (e.g. : physical resource block (PRB) utilization of a cell) divided by overall energy consumption of the cell. Alternatively, the energy score may indicate a derived energy value based on a relative importance score of a cell (representing a KPI feature impact weightage) multiplied by the respective KPI value. That way only the high impact KPI features get higher dominance with energy efficiency calculation. The energy score can be at network level, node level, sector level or cell level. According to the energy evaluation, the KPI features are aggregated at respective levels. In some embodiments, the nodes with a higher energy score are prioritized when the SNE apparatus 102 selects to activate energy savings functions. In some embodiments, the SNE apparatus 102 examines the nodes with lower energy scores and perform configuration changes 132 to improve their energy saving scores as a pre-requisite to activate the energy savings function.

[0035] Network configuration apparatus 118 may prepare the needed configuration changes and perform the needed changes to radio network 112 based on the KPI feature values (as described in greater detail below in conjunction with Figure 2A). Autonomous network functions (e.g., energy savings functions) 120 may perform the needed actions on the network to save energy. In case network configuration apparatus 118 has provided pre-requisite optimization and activation of other network functions for energy savings, radio network 112 may then perform pre-requisite actions as needed before activating the energy savings functions. [0036] Figure IB is a block diagram showing an expanded view of a sustainable network engineering apparatus of Figure 1A per some embodiments. SNE apparatus 102 uses one or more of the followings methods as indicated in Figure 1 A for (a) identifying sites and sectors/cells (b) identifying energy savings functions to be activated or de-activated and (c) proposing additional network optimization strategies for harnessing most energy gains before the energy savings functions are activated for certain cases based on following deep dive methods. Based on the proposal, a further decision either to activate/de-activate or perform other optimizations as a pre-requisite is performed.

[0037] The deep dive methods include machine learning methods such as correlation, surrogative modeling, and causation analysis, as described more fully below, according to some embodiments. For the correlation method, SNE apparatus 102 finds a correlation between the network data and an “energy consumption” telemetry KPI (also referred to as an energy KPI or an energy KPI measurement). Network data includes values of network KPI features in impact areas such as coverage, capacity, network utilization, signal levels. The network KPI features indicate a variety of aspects of network performance and configuration, and the network KPI features correlate with the “energy consumption” telemetry KPIs; and to differentiate the two terms, the latter is referred to as energy KPIs or energy KPI features, and a “KPI feature” refers to a network KPI feature unless noted otherwise. Additional details are described in the Pearson Correlation method as known in the art. For the surrogative modeling method, KPI features influence “telemetry energy counters” prediction both globally and locally. Additional details are described in the rank correlation method as known in the art. For the causation method, the exact thresholds and the hierarchical rules are derived based on the given data.

[0038] Figure IB shows a variety of graphical models depicting the results of various actions performed by SNE apparatus 102. Some portions of the figure are described in greater detail below in conjunction with Figures 1C, 3, 4, and 5. These include results of the correlation analysis described above in the lower left corner of SNE apparatus 102 and the results of a causation analysis, also in the lower left corner of SNE apparatus 102. Also in the lower left comer is a predictive power score plot, a partial dependence plot, and a feature impact plot. In the upper left comer, K-shape cluster results are shown. In the upper middle of the SNE apparatus 102, a power consumption heatmap is shown. A time aware modeling 156 is shown in the upper right comer, and explainable artificial intelligence (Al) models are shown in the lower right-hand comer of the SNE apparatus 102. These illustrations and results depict the operations performed by SNE apparatus 102.

[0039] The functions performed by SNE apparatus 102 are to achieve a target energy saving objective, which, in this example, is the energy consumption at a sector level and the targeted energy saving is indicated by a performance monitoring (Perf M) counter that measures a radio unit consumed energy at the sector level, referred to as Perf M Consumed Energy at reference 150). The SNE apparatus 102 may perform different operations or same operations with different parameter values on each band (high/low band, each band being evaluated in a group of nodes sharing one common characteristics), or nodes in different regions (e.g., urban, rural, or suburb). For example, SNE apparatus 102 may use Al models in a rural area different from the ones in an urban area. Note a band is a targeted wireless channel group, associated with one or multiple nodes allowed to operate in that channel group or band.

[0040] Figure 1C is a block diagram showing an expanded view of time aware modeling per some embodiments. Figure 1C shows an embodiment of the time aware modeling 156 and it includes the operations data that goes through the modeling process to arrive at a prediction. Time aware modeling defines and visualizes how models change over time and allows different versions or states of a model to be created to represent how the model will change with the passage of time. Through time aware modeling 156, SNE apparatus 102 may predict power consumption of nodes. The time aware modeling 156 is used to capture the seasonal trends of energy at node, sector, cell, or network level (based on the aggregation of network data) and makes the power consumption predict at the different level accurate throughout seasons.

Identify Key Impact Areas and KPI Features for Energy Savings

[0041] Figure 2A is a table showing the identification of KPI features and key impact areas for sector/cell selection for energy savings per some embodiments. SNE apparatus 102 generates values in the KPI feature/key impact area identification table 200 shown in Figure 2A using correlation, surrogative modeling, and causation analysis for correlation scores, relative importance scores, and threshold values. For example, SNE apparatus 102 may determine the relationship of a KPI feature in the table with energy savings. The relationship may be reflected by (1) a correlation score indicating how relevant the KPI feature is to energy saving (e.g., the score being in the range of -1 to 1, the higher the more positively correlated the KPI feature is to energy saving), (2) a relative importance score of the KPI feature to energy saving (e.g., the score being in the range of 0 to 1, the higher the more important the KPI feature is to energy saving), and (3) the threshold value, crossing of which by the KPI feature value indicating the need of activating one or more energy savings functions.

[0042] The KPI features in the table 200 may be grouped into multiple impact areas, including utilization KPIs including radio utilization measurements 1 to 3 (reference 202), uplink quality KPIs including uplink quality measurements 1 to 2(reference 204), traffic KPIs including measurements 1 to 4 on number of calls (reference 206), a configuration KPI such as distance between sites (reference 208), a cluster radio utilization KPI such as (reference 210), and mobility KPIs including mobility measurements 1 to 2 (reference 212). While the table 200 shows only the KPI features of the identified key impact areas, values of more KPI features that do not belong to the key impact areas are calculated in some embodiments. The influence of the impact areas is different in different networks. Based on the influence of the KPI features, some corresponding impact areas are identified as key impact areas. The key impact areas may include additional and/or different KPI features in different networks. For example, in some networks downlink (instead of uplink) quality KPIs may be used.

[0043] Table 200 shows KPI feature values of different KPI features in these impact areas. For example, the first row in the table is an utilization KPI, which has the correlation score of 0.75, which means this KPI feature is highly related to energy saving; the relative importance score is 1, which means this KPI feature is among the most important to energy saving; the threshold value is 24, which means if the value of the utilization KPI (radio utilization measurement 1) is less than 24, one or more energy savings functions may be activated at a particular node (sector/cell). Note that the generated values may correspond to a particular energy saving objective (e.g., the energy consumption at a sector level reaching a targeted energy saving as indicated by an energy KPI such as Perf M Consumed Energy described herein) and/or general objective of saving energy in a mobile network.

[0044] These values (correlation scores, relative importance scores, threshold values) in the table 200 may be derived based on machine learning methods described herein. Note that values in this example are for aggregation at the sector level (more than one cell), so some threshold values, when it represents a percentage value, the percentage may be over 100%.

[0045] Figure 2B is a diagram showing the key impact areas for energy savings per some embodiments. Six key impact areas are shown by the order of influence on energy saving for the particular network (or a portion of the network), and the key impact areas are utilization 202, uplink quality 204, traffic 206, configuration 208, cluster radio utilization 210, mobility 212 in this example. Their relative influence of the key impact areas is indicated by their respective sizes in the diagram. Based on the relative influence of the key impact areas, SNE apparatus 102 may identify the nodes to activating energy savings functions.

[0046] The first value of a KPI feature regarding energy saving is its correlation score as shown in table 200. Figure 3 shows the determination of the correlation scores per some embodiments. A heatmap may be used to indicate. The heatmap shows correlations between different KPI features in grayscale, and the correlation between a KPI feature and an energy KPI, Perf_M_consumed_Energy_sum, which measures the sum of performance counter values, each measuring a radio unit consumed energy at a sector level is shown in the grayscale square corresponding to the KPI feature listed vertically. The correlation score legend 300 shows the grayscale mapping to the various correlation scores. Corresponding to Table 200, one KPI feature with the highest correlation score is the sum of Utilization KPI 2 at the value of 1, while one KPI feature with the lowest correlation score is the sum of traffic KPI 4 at the value of 0.7. [0047] The correlation scores may be generated through SNE apparatus 102. For example, SNE apparatus 102 calculates correlation (shown in Figure 2A) with energy KPIs/counters for a variety of network KPI features (in key impact areas such as mobility, uplink quality, and number of calls). Correlation provides the relation between the network KPI features and energy KPIs or counters. A higher relation (either positive or negative) indicates the more influencing factor. SNE apparatus 102 may also use Pearson’s, Kendall’s, Spearman’s correlation along with dynamic time warping (DTW) based on the linearity and type of KPI data.

[0048] The second value of a KPI feature regarding energy saving is its relative importance score as shown in table 200. Figures 4 provides a graph showing analysis of relative importance of KPI features per some embodiments. In some embodiments, the analysis is through application of surrogative models by the sustainable network engineering (SNE) apparatus 102, such as those described by SHAP (SHapley Additive exPlanations), LIME (local interpretable model-agnostic explanations), Layer-wise relevance propagation (LRP), ELI5, and Skate, to identify global and local prediction of KPIs with energy counters or KPIs.

[0049] SHAP is a method to explain individual predictions and it is based on the game theoretically optimal Shapley Values (which shows how important each player’s contribution was to a game). The method of LIME locally generates data around a single predication and fits a linear model that shows the relative importance of features in that local neighborhood. LRP backpropagates a class-specific signal through a neural network while multiplying it with each convolutional layer’s activations and results in a fine-grained heatmap the most important features for classification. The method of ELI5 helps to debug machine learning classifiers and explain their predictions in an easy to understand an intuitive way, and Skate enables model interpretation for all forms of models to help one build an Interpretable machine learning system often needed for real world use-cases using a model-agnostic approach.

[0050] Through the surrogative modeling, SNE 102 may calculate feature impact analysis using one or more of the surrogative models to identify the key KPI features that are influencing the prediction of energy counters or KPIs in order of their importance. For example, Figure 4 shows that SNE 102 determines that the utilization KPI 1 (Utilization KPI I surn) has 100% importance (corresponding to relative importance score of 1.00 in Figure 2A), and the other KPI features have lower levels of importance, shown in a descending order in Figure 4.

[0051] The sustainable network engineering (SNE) apparatus 102 analyzes feature impact using one or more of the surrogative models to identify the key KPI features that are influencing the prediction of energy counters or KPIs (e.g., Perf M Consumed Energysum at sector level). Based on the impact factor of each KPI the relative importance score is calculated.

[0052] The third value of a KPI feature regarding energy saving is its threshold value as shown in table 200. Figure 5 is a block diagram showing thresholds derived through tree classifier rules per some embodiments. Threshold values are calculated using tree classifier algorithms such as C4.5 that provides clear conditions about which KPI values the network is running with high or low energy. The threshold value rules as shown in Figure 5 are applied on the network for activating or de-activating the energy saving network functions on the network. The SNE apparatus 102 may use C4.5 tree classifier model to identify the conditions that influences a node to consume high or low power.

Identify Nodes to Activate Energy Savings Functions

[0053] The key impact areas and corresponding KPI features may be identified for energy saving as discussed relating to the derivation of correlation scores, relative importance scores, and threshold values as discussed herein. The SNE apparatus 102 also selects nodes to activate the energy savings functions. The selection may be performed through a tree classifier such as the one shown in Figure 5. For example, the KPI feature values in key impact areas may be provided to the tree classifier, and the path on the tree classifier then determines whether or not an energy savings function is activated on the node.

[0054] For example, the KPI feature values in key impact areas for one node is shown in the following table:

KPI Feature Values

[0055] Based on the KPI feature values for the nodes, the path will turn left first since the utilization KPI 1 sum is 31, less than the threshold value 34 as indicated in Figure 5. Since the utilization KPI 1 sum is 105, less than the corresponding threshold of 112, the path will go to the left again. Then since the uplink KPI 1 sum is 5.8, higher than the corresponding threshold of 5.743, the path will go to the right. At the leaf level, the path ends to the right, since the traffic KPI 1 sum is 66.9, higher than the threshold 66.841. As indicated in the corresponding box, the node is selected to activate one or more energy savings functions to achieve lower power. By providing the SNE apparatus 102 the KPI feature values of nodes, the tree classifier may identify the nodes to activate the energy savings functions. The nodes may be at the sector level or cell level, and the tree clarifiers may have different thresholds at the sector level and cell level. Additionally, the threshold values may be different to achieve different energy saving objectives, e.g., the threshold values may be selected specifically to deliver a targeted energy saving as indicated by Perf M Consumed Energy at sector level.

[0056] Figure 6 summarizes example energy savings functions that may be used by a sustainable network engineering system per some embodiments. As indicated, example energy savings functions include Microsleep Tx (transmit) (MSTx) (also referred to as micro TX sleep), Low Energy Scheduler Solution (LESS), MIMO Sleep Mode (MSM), and Cell Sleep Mode (CSM). Other energy savings functions may also be used.

[0057] Microsleep Tx automatically switches off the radio power amplifiers on a symbol-time basis when no signalling or user data needs to be transmitted on downlink. This provides the benefit of enabling discontinuous transmission on downlink to save energy during lower traffic. Low Energy Scheduler Solution reschedules downlink transmissions for non-critical data. Timesensitive transfers, such as voice, are excluded, making sure the quality for service is never compromised. This improves MSTx efficiency as even more timeslots are emptied and can trigger micro sleep. MIMO Sleep Mode deactivates power for a subset of the antenna branches. The feature automatically reconfigures from MIMO to single input multiple output (SIMO) mode and back based on traffic load. This provides the benefit of automatically reducing power consumption in the radio during low traffic hours. Cell Sleep Mode turns off the power amplifier for a capacity cell when the total traffic is below a set threshold. This provides the benefit of automatically reducing power consumption in the radio during low-traffic hours.

An example of Activating Energy Savings Functions

[0058] Figure 7 is a block diagram showing an example of the use of sustainable network engineering system associated with a particular energy savings function per some embodiments. In this example, the Cell Sleep energy savings function is activated to save energy at a particular node. While Figure 7 is used to show the application of the sustainable network engineering system, the system is also broadly associated with identifying which features among many may be more advantageous to select for application.

[0059] In operation, data is provided to SNE apparatus 102 by data preparation subsystem 116 as indicated by reference 720. The data may be collected from the radio network 112 and would have been first processed by network management systems 114 (not explicitly shown in Figure 7) and provided in a structured format with their respective interfaces (e.g., SQL, REST) to data preparation sub-system 3 before being prepared by data preparation subsystem 116.

[0060] SNE apparatus 102 generates for a particular cluster a table for certain key performance indicators a correlation score associated with respective derived causation rules having respective feature priorities, as indicated by reference 730. The table is used to identify the KPI features and key impact areas as described above with reference to Figure 2A. The nodes (sectors/cells) for which activate the at least one energy savings function is to be activated are also identified. The information is then provided to network configuration apparatus 118 as indicated by reference 750.

[0061] The network configuration apparatus 118 prepares the needed configuration changes associated with the Micro Sleep energy savings function (or any other energy savings function(s) determined to be activated in other scenarios) and performs the needed changes to the network 112 (e.g., the configuration changes described at reference 132) based on the table as shown in Figure 2A. For example, for the nodes determined not to the ones for which the Micro Sleep energy savings function is to be activated, they are prepared to take on additional workload when the determined nodes go to the lower power mode with the Micro Sleep energy savings function being activated. The nodes may be neighboring nodes and the beam directions of these nodes may be rearranged to accommodate the upcoming activation of the Micro Sleep energy savings function on the determined nodes. The configuration changes may be performed on the nodes for which energy savings function is to be activated. For example, if the KPI feature values show that performance degradation of a node (e.g., a cell/sector), mitigation may be performed prior to activating the energy savings function(s): If signal issues are indicated (e.g.: low values as measured by traffic KPIs 1 to 4 indicating interference or low coverage), optimization of the node to mitigate signal issues may be performed (e.g.: Interference control, coverage optimization with antenna electrical or digital tilt); if mobility issues are indicated (e.g., low values as measured by mobility KPIs 1 to 2 indicating too many handover failures), mobility optimization may be performed (e.g., adjusting handover signal level threshold). Additionally, for the nodes determined to be the ones for which the Micro Sleep energy savings function is to be activated, the operational state of the nodes may be saved to prevent information loss due to the activation of the Micro Sleep energy savings function on the node. [0062] Then autonomous network function 120 performs the needed actions on the network to activate the Micro Sleep energy savings function based on topology and/or band (e.g., dense urban, sub-urban region, or high/low band). In the illustrated Figure 7, “Correlation,” “Feature Impact,” “Partial Dependence Plot,” “Causation Analysis,” and “Interpretable Al” graphical depictions are provided to indicate various functional blocks that SNE apparatus 102 may perform in generating table 200 as described herein.

Operations of Embodiments

[0063] Figure 8 is a flow diagram showing operations of activating one or more energy savings functions per some embodiments. The operations may be performed in a mobile telecommunications network by a computer system such as the sustainable network engineering (SNE) apparatus 102 discussed herein.

[0064] At reference 802, the computer system may determine for a portion of the mobile telecommunications network, energy savings that would occur in response to application of at least one energy savings function to the portion of the mobile telecommunications network. The compute system may determine how much energy savings are to be achieved and how the energy savings are to be measured for the portion of the network. The targeted energy saving indicated by Perf M Consumed Energy at the sector level is used in some examples herein. The computer system may determine different energy saving objectives for different portions of the network. This determination is operational, and some networks have default energy saving objectives and the computer system may perform energy saving without performing the operation.

[0065] At reference 804, the computer system determines which of one or more nodes in a plurality of nodes of the mobile telecommunications network in which to activate the at least one energy savings function to provide energy savings to the mobile telecommunications network, where the determination comprises identifying a plurality of key impact areas of energy savings for the mobile telecommunications network. The operations of identifying the plurality of key impact areas of energy savings are discussed herein above relating to the KPI feature/key impact area identification table 200.

[0066] In some embodiments, the plurality of key impact areas is identified using at least one of operations of correlation, surrogative modelling, and causation analysis, and wherein the operations derive corresponding values to determine the nodes. In some embodiments, the corresponding values are used to identify relative correlation of the plurality of key impact areas to the energy savings, relative importance of the plurality of key impact areas to the energy savings, or threshold values for key performance indicator features of the plurality of key impact areas to the energy savings.

[0067] In some embodiments, using the correlation to identify the plurality of key impact areas comprises deriving a correlation score between a key performance indicator feature and the energy savings, as discussed herein above relating to at least Figures 1 A-1B, 2A, and 3.

[0068] In some embodiments, using the surrogative modelling to identify the key impact areas comprises deriving a score to indicate importance of a key performance indicator feature toward the energy savings, as discussed herein above relating to at least Figures 1 A-1B, 2A, and 4.

[0069] In some embodiments, using the causation analysis comprises application of a decision tree classifier to determine a threshold value of a key performance indicator feature to activate the at least one energy savings function, as discussed herein above relating to at least Figure 1 A- 1B, 2A, and 5.

[0070] In some embodiments, determining a node in the plurality of nodes to activate the at least one energy savings function comprises comparing values of key performance indicator features of the node to thresholds of corresponding key performance indicator features, wherein the comparison is performed hierarchically through a tree structure formed by the thresholds of corresponding key performance indicator features, as discussed herein above relating to at least Figure 5.

[0071] In some embodiments, the at least one energy savings function comprises at least one of Microsleep transmit (MSTx), Low Energy Scheduler Solution, multiple-input and multipleoutput (MIMO) Sleep Mode, and Cell Sleep Mode (CSM), as discussed herein above relating at least Figure 6.

[0072] In some embodiments, determining which nodes in the plurality of nodes of the mobile telecommunications network in which to activate the at least one energy savings function comprises aggregating values of a plurality of key performance indicators from the plurality of nodes, where at least one value of a key performance indicator is converted from a cell level to a sector level, as discussed herein above relating to at least Figures 1 A-1B.

[0073] In some embodiments, the key impact areas of energy savings for the mobile telecommunications network comprises one or more of the following: mobility, number of calls, radio utilization, and inter site distance cluster radio utilization, as discussed herein above relating at least Figures 2A-2B. [0074] At reference 806, the computer system, based on the determination of the nodes in the plurality of nodes, configures at least one node that is not the determined node and at least one node of the determined nodes to prepare for activating the at least one energy savings function, as discussed herein above relating to at least Figures 1 A-1B and 7.

[0075] At reference 808, the computer system provides energy savings for the mobile telecommunications network by activating the at least one energy savings function in the determined nodes, as discussed herein above relating to at least Figures 1 A-1B and 7.

Environment and Computer Systems to Implement Embodiments

[0076] Figure 9 is a block diagram showing a sustainable network engineering system in a cloud native environment per some embodiments. As shown, the cloud native environment is shown as a hierarchical architecture, where the infrastructure 930 may be provided by cloud service provider. A client may deploy one or more hosts 922 to 926 to implement their applications. The cloud native environment may be managed by cloud native container orchestrator and/or service mesh as shown at reference 912, which in turn supports applications, such as applications 902 to 910, one or more of which may include full or a portion of a sustainable network engineering system such as system 100 in Figure 1.

[0077] Figure 10 shows an example computer system to perform operations discussed here per some embodiments. Computer system 1000 may represent any of network management systems 2 (reference 114), data preparation sub-system 3 (reference 116), sustainable network engineering apparatus 4 (reference 102), network configuration apparatus 5 (reference 118), autonomous network functions model 6 (reference 120), or any other functional block described herein, and perform one or more of the methods described with respect to Figures 1-9. Software may be provided on a non-transitory computer readable medium illustrated as memory 1004 or storage 1006. Software running on one or more computer systems 1000 may perform one or more steps of one or more methods described or illustrated herein or provides functionality described or illustrated herein such as an application including full or a portion of a sustainable network engineering system (e.g., system 100 in Figure 1) as the application 910 shown in the memory 1004 or storage 1006. Particular embodiments include one or more portions of one or more computer systems 1000. Herein, reference to a computer system may encompass a computing device, and vice versa, where appropriate.

[0078] This disclosure contemplates any suitable number of computer systems 1000. This disclosure contemplates a computer system 1000 taking any suitable physical form. As example and not by way of limitation, computer system 1000 may be an embedded computer system, a system-on-chip (SOC), a single-board computer system (SBC) (such as, for example, a computer-on-module (COM) or system-on-module (SOM)), a desktop computer system, a laptop or notebook computer system, an interactive kiosk, a mainframe, a mesh of computer systems, a mobile telephone, a personal digital assistant (PDA), a server, a tablet computer system, an augmented/virtual reality device, or a combination of two or more of these. Where appropriate, computer system 1000 may include one or more computer systems 1000; be unitary or distributed; span multiple locations; span multiple machines; span multiple data centers; or reside in a cloud, which may include one or more cloud components in one or more networks. Where appropriate, one or more computer systems 1000 may perform without substantial spatial or temporal limitation one or more steps of one or more methods described or illustrated herein. As an example, and not by way of limitation, one or more computer systems 1000 may perform in real time or in batch mode one or more steps of one or more methods described or illustrated herein. One or more computer systems 1000 may perform at different times or at different locations one or more steps of one or more methods described or illustrated herein, where appropriate.

[0079] Computer system 1000 includes a processor 1002, memory 1004, storage 1006, an input/output (I/O) interface 1008, a communication interface 1010, and a bus 1012. Although this disclosure describes and illustrates a particular computer system having a particular number of particular components in a particular arrangement, this disclosure contemplates any suitable computer system having any suitable number of any suitable components in any suitable arrangement.

[0080] Processor 1002 includes hardware for executing instructions, such as those making up a computer program. As an example and not by way of limitation, to execute instructions, processor 1002 may retrieve (or fetch) the instructions from an internal register, an internal cache, memory 1004, or storage 1006; decode and execute them; and then write one or more results to an internal register, an internal cache, memory 1004, or storage 1006. Processor 1002 may include one or more internal caches for data, instructions, or addresses. This disclosure contemplates processor 1002 including any suitable number of any suitable internal caches, where appropriate. As an example, and not by way of limitation, processor 1002 may include one or more instruction caches, one or more data caches, and one or more translation lookaside buffers (TLBs). Instructions in the instruction caches may be copies of instructions in memory 1004 or storage 1006, and the instruction caches may speed up retrieval of those instructions by processor 1002. Data in the data caches may be copies of data in memory 1004 or storage 1006 for instructions executing at processor 1002 to operate on; the results of previous instructions executed at processor 1002 for access by subsequent instructions executing at processor 1002 or for writing to memory 1004 or storage 1006; or other suitable data. The data caches may speed up read or write operations by processor 1002. The TLBs may speed up virtual-address translation for processor 1002. Processor 1002 may include one or more internal registers for data, instructions, or addresses. This disclosure contemplates processor 1002 including any suitable number of any suitable internal registers, where appropriate. Where appropriate, processor 1002 may include one or more arithmetic logic units (ALUs); be a multi-core processor; or include one or more processors 1002. Although this disclosure describes and illustrates a particular processor, this disclosure contemplates any suitable processor.

[0081] Memory 1004 includes main memory for storing instructions or logic for processor 1002 to execute or data for processor 1002 to operate on. As an example, and not by way of limitation, computer system 1000 may load instructions or logic from storage 1006 or another source (such as, for example, another computer system 1000) to memory 1004. Processor 602 may then load the instructions or logic from memory 1004 to an internal register or internal cache. To execute the instructions or logic, processor 1002 may retrieve the instructions or logic from the internal register or internal cache and decode them. During or after execution of the instructions or logic, processor 1002 may write one or more results (which may be intermediate or final results) to the internal register or internal cache. Processor 1002 may then write one or more of those results to memory 1004. Processor 1002 executes only instructions or logic in one or more internal registers or internal caches or in memory 1004 (as opposed to storage 1006 or elsewhere) and operates only on data in one or more internal registers or internal caches or in memory 1004 (as opposed to storage 1006 or elsewhere). One or more memory buses (which may each include an address bus and a data bus) may couple processor 1002 to memory 1004. Bus 1012 may include one or more memory buses, as described below. One or more memory management units (MMUs) reside between processor 1002 and memory 1004 and facilitate accesses to memory 1004 requested by processor 1002. Memory 1004 includes random access memory (RAM). This RAM may be volatile memory, where appropriate. Where appropriate, this RAM may be dynamic RAM (DRAM) or static RAM (SRAM). Moreover, where appropriate, this RAM may be single-ported or multi-ported RAM. This disclosure contemplates any suitable RAM. Memory 1004 may include one or more memories 1004, where appropriate. Although this disclosure describes and illustrates particular memory, this disclosure contemplates any suitable memory.

[0082] Storage 1006 includes mass storage for data or instructions or logic. As an example and not by way of limitation, storage 1006 may include a hard disk drive (HDD), a floppy disk drive, flash memory, an optical disc, a magneto-optical disc, magnetic tape, or a USB drive or a combination of two or more of these. Storage 1006 may include removable or non-removable (or fixed) media, where appropriate. Storage 1006 may be internal or external to computer system 1000, where appropriate. Storage 1006 is non-volatile, solid-state memory. Storage 606 includes read-only memory (ROM). Where appropriate, this ROM may be mask-programmed ROM, programmable ROM (PROM), erasable PROM (EPROM), electrically erasable PROM (EEPROM), electrically alterable ROM (EPROM), or flash memory or a combination of two or more of these. This disclosure contemplates mass storage 1006 taking any suitable physical form. Storage 1006 may include one or more storage control units facilitating communication between processor 1002 and storage 1006, where appropriate. Where appropriate, storage 1006 may include one or more storages 1006. Although this disclosure describes and illustrates particular storage, this disclosure contemplates any suitable storage.

[0083] VO interface 1008 includes hardware, software, or both, providing one or more interfaces for communication between computer system 1000 and one or more VO devices. Computer system 1000 may include one or more of these VO devices, where appropriate. One or more of these VO devices may enable communication between a person and computer system 1000. As an example and not by way of limitation, an VO device may include a keyboard, keypad, microphone, monitor, mouse, printer, scanner, speaker, still camera, stylus, tablet, touch screen, trackball, video camera, another suitable VO device or a combination of two or more of these. An VO device may include one or more sensors. This disclosure contemplates any suitable VO devices and any suitable VO interfaces 608 for them. Where appropriate, VO interface 1008 may include one or more device or software drivers enabling processor 1002 to drive one or more of these VO devices. VO interface 1008 may include one or more VO interfaces 1008, where appropriate. Although this disclosure describes and illustrates a particular VO interface, this disclosure contemplates any suitable VO interface.

[0084] Communication interface 1010 includes hardware, software, or both providing one or more interfaces for communication (such as, for example, packet-based communication) between computer system 1000 and one or more other computer systems 1000 or one or more networks 112. As an example and not by way of limitation, communication interface 1010 may include a network interface controller (NIC) or network adapter for communicating with an Ethernet or other wire-based network or a wireless NIC (WNIC) or wireless adapter for communicating with a mobile network, such as a WI-FI network. This disclosure contemplates any suitable network and any suitable communication interface 1010 for it. As an example and not by way of limitation, computer system 1000 may communicate with an ad hoc network, a personal area network (PAN), a local area network (LAN), a wide area network (WAN), a metropolitan area network (MAN), or one or more portions of the Internet or a combination of two or more of these. One or more portions of one or more of these networks may be wired or wireless. As an example, computer system 1000 may communicate with a wireless PAN (WPAN) (such as, for example, a BLUETOOTH WPAN), a WI-FI network, a WI-MAX network, a cellular telephone network (such as, for example, a Global System for Mobile Communications (GSM) network), or other suitable mobile network or a combination of two or more of these. Computer system 1000 may include any suitable communication interface 1010 for any of these networks, where appropriate. Communication interface 1010 may include one or more communication interfaces 1010, where appropriate. Although this disclosure describes and illustrates a particular communication interface, this disclosure contemplates any suitable communication interface.

[0085] Bus 1012 includes hardware, software, or both coupling components of computer system 1000 to each other. As an example and not by way of limitation, bus 1012 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Enhanced Industry Standard Architecture (EISA) bus, a front-side bus (FSB), a HYPERTRANSPORT (HT) interconnect, an Industry Standard Architecture (ISA) bus, an INFINIBAND interconnect, a low-pin-count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCIe) bus, a serial advanced technology attachment (SATA) bus, a Video Electronics Standards Association local (VLB) bus, or another suitable bus or a combination of two or more of these. Bus 1012 may include one or more buses 1012, where appropriate. Although this disclosure describes and illustrates a particular bus, this disclosure contemplates any suitable bus or interconnect.

[0086] Herein, a computer-readable non-transitory storage medium or media may include one or more semiconductor-based or other integrated circuits (ICs) (such, as for example, field- programmable gate arrays (FPGAs) or application-specific ICs (ASICs)), hard disk drives (HDDs), hybrid hard drives (HHDs), optical discs, optical disc drives (ODDs), magneto-optical discs, magneto-optical drives, floppy diskettes, floppy disk drives (FDDs), magnetic tapes, solid-state drives (SSDs), RAM-drives, SECURE DIGITAL cards or drives, any other suitable computer-readable non-transitory storage media, or any suitable combination of two or more of these, where appropriate. For example, computer system 1000 may be a decoder chip and/or encoder chip. A computer-readable non-transitory storage medium may be volatile, non-volatile, or a combination of volatile and non-volatile, where appropriate.

[0087] In the disclosure, numerous specific details such as logic implementations, opcodes, means to specify operands, resource partitioning/sharing/duplication implementations, types and interrelationships of system components, and logic partitioning/integration choices are set forth in order to provide a more thorough understanding of the present invention. It will be appreciated, however, by one skilled in the art that the invention may be practiced without such specific details. In other instances, control structures, gate level circuits and full software instruction sequences have not been shown in detail in order not to obscure the invention. Those of ordinary skill in the art, with the included descriptions, will be able to implement appropriate functionality without undue experimentation.

[0088] References in the disclosure to “one embodiment,” “an embodiment,” “an example embodiment,” etc., indicate that the embodiment described may include a particular feature, structure, or characteristic, but every embodiment may not necessarily include the particular feature, structure, or characteristic. Moreover, such phrases are not necessarily referring to the same embodiment. Further, when a particular feature, structure, or characteristic is described in connection with an embodiment, it is submitted that it is within the knowledge of one skilled in the art to affect such feature, structure, or characteristic in connection with other embodiments whether or not explicitly described.

[0089] In the description and claims, the terms “coupled” and “connected,” along with their derivatives, may be used. It should be understood that these terms are not intended as synonyms for each other. “Coupled” is used to indicate that two or more elements, which may or may not be in direct physical or electrical contact with each other, co-operate or interact with each other. “Connected” is used to indicate the establishment of communication between two or more elements that are coupled with each other. A “set,” as used herein refers to any positive whole number of items including one item. [0090] Generally, all terms used herein are to be interpreted according to their ordinary meaning in the relevant technical field, unless a different meaning is clearly given and/or is implied from the context in which it is used. All references to a/an/the element, apparatus, component, means, step, etc. are to be interpreted openly as referring to at least one instance of the element, apparatus, component, means, step, etc., unless explicitly stated otherwise. The steps of any methods disclosed herein do not have to be performed in the exact order disclosed, unless a step is explicitly described as following or preceding another step and/or where it is implicit that a step must follow or precede another step. Any feature of any of the embodiments disclosed herein may be applied to any other embodiment, wherever appropriate. Likewise, any advantage of any of the embodiments may apply to any other embodiments, and vice versa. Other objectives, features, and advantages of the enclosed embodiments will be apparent from the following description.

EMBODIMENTS

[0091] According to one embodiment, a system for saving energy in a mobile telecommunications network includes a sustainable network engineering apparatus operable to determine, for each of a plurality of portions of the mobile telecommunications network, the energy savings that would occur in response to application of at least one energy savings functions to the portion of the mobile telecommunications network. Based on the energy savings determined to occur, the sustainable network engineering apparatus determines which nodes in a plurality of nodes of the mobile telecommunications network in which to activate the at least one energy savings functions to provide energy savings to the mobile telecommunications network. The system also includes a network configuration activation apparatus operable to provide energy savings for the mobile telecommunications network by activating the determined at least one energy savings functions in the determined nodes.

[0092] According to another embodiment, a computerized method for saving energy in a mobile telecommunications network includes determining, by a computer, for each of a plurality of portions of the mobile telecommunications network, the energy savings that would occur in response to application of at least one energy savings functions to the portion of the mobile telecommunications network. The method further includes, based on the energy savings determined to occur, determining which nodes in a plurality of nodes of the mobile telecommunications network in which to activate the at least one energy savings functions to provide energy savings to the mobile telecommunications network. The method also includes providing energy savings for the mobile telecommunications network by activating the determined at least one energy savings functions in the determined nodes.

[0093] A number of enumerated embodiments are listed herein below.

1. A computerized method for saving energy in a mobile telecommunications network, the method comprising: determining by a computer, for each of a plurality of portions of the mobile telecommunications network, the energy savings that would occur in response to application of at least one energy savings features to the portion of the mobile telecommunications network; based on the energy savings determined to occur, determining which nodes in a plurality of nodes of the mobile telecommunications network in which to activate the at least one energy savings features to provide energy savings to the mobile telecommunications network; and providing energy savings for the mobile telecommunications network by activating the determined at least one energy savings features in the determined nodes.

2. The method of embodiment 1, wherein determining by a computer, for each of a plurality of portions of the communications network, the energy savings that would occur in response to application of a respective energy savings feature to a respective one of the plurality of portions of the communications network further comprises determining key impact areas of energy savings for the mobile telecommunications network.

3. The method of embodiment 2, wherein determining key impact areas further comprises using one or more of the following: correlation, a surrogative model, and causation analysis.

4. The method of embodiment 2, wherein determining key impact areas further comprises using causation analysis including application of a decision tree classifier.

5. The method of embodiment 1, wherein the at least one energy savings feature includes at least one of Microsleep Tx (MSTx), Low Energy Scheduler Solution, MIMO Sleep Mode, and Cell Sleep Mode (CSM). 6. The method of embodiment 1, wherein providing energy savings for the mobile telecommunications network by activating the determined at least one energy savings features in the determined nodes includes not activating any energy savings feature in at least one of the plurality of nodes in the mobile telecommunications network and further comprising optimizing at least one of the nodes of the plurality of nodes in which no energy savings functions are activated.

7. The method of embodiment 1, and further comprising generating and storing an energy savings score for each of the determined nodes of the plurality of nodes.

8. A system for saving energy in a mobile telecommunications network, the system comprising: one or more computer-readable non-transitory storage media embodying logic; and one or more processors operable to execute the logic, the logic when executed operable to: determine, for each of a plurality of portions of the mobile telecommunications network, the energy savings that would occur in response to application of at least one energy savings features to the portion of the mobile telecommunications network; based on the energy savings determined to occur, determine which nodes in a plurality of nodes of the mobile telecommunications network in which to activate the at least one energy savings features to provide energy savings to the mobile telecommunications network; and provide energy savings for the mobile telecommunications network by activating the determined at least one energy savings features in the determined nodes.

9. The system of embodiment 8, wherein the logic is further operable to determine by a computer, for each of a plurality of portions of the communications network, the energy savings that would occur in response to application of a respective energy savings feature to a respective one of the plurality of portions of the communications network by determining key impact areas of energy savings for the mobile telecommunications network. 10. The system of embodiment 9, wherein the logic is operable to determine key impact areas by using one or more of the following: correlation, a surrogative model, and causation analysis.

11. The system of embodiment 9, wherein the logic is operable to determine key impact areas using causation analysis including application of a decision tree classifier.

12. The system of embodiment 8, wherein the at least one energy savings feature includes at least one of Microsleep Tx (MSTx), Low Energy Scheduler Solution, MIMO Sleep Mode, and Cell Sleep Mode (CSM).

13. The system of embodiment 8, wherein the logic is operable to provide energy savings for the mobile telecommunications network by activating the determined at least one energy savings features in the determined nodes by not activating any energy savings feature in at least one of the plurality of nodes in the mobile telecommunications network and the logic is further operable to initiate optimization at least one of the nodes of the plurality of nodes in which no energy savings functions are activated.

14. The system of embodiment 8, and wherein the logic is further operable to generate and initiate storage of an energy savings score for each of the determined nodes of the plurality of nodes.

15. A system for saving energy in a mobile telecommunications network, the system comprising: a sustainable network engineering apparatus operable to: determine, for each of a plurality of portions of the mobile telecommunications network, the energy savings that would occur in response to application of at least one energy savings features to the portion of the mobile telecommunications network; based on the energy savings determined to occur, determine which nodes in a plurality of nodes of the mobile telecommunications network in which to activate the at least one energy savings features to provide energy savings to the mobile telecommunications network; and a network configuration activation apparatus operable to: provide energy savings for the mobile telecommunications network by activating the determined at least one energy savings features in the determined nodes.

16. The system of embodiment 15, wherein the sustainable network engineering apparatus is further operable to determine for each of a plurality of portions of the communications network, the energy savings that would occur in response to application of a respective energy savings feature to a respective one of the plurality of portions of the communications network by determining key impact areas of energy savings for the mobile telecommunications network.

17. The system of embodiment 16, wherein determining key impact areas further comprises using one or more of the following: correlation, a surrogative model, and causation analysis.

18. The system of embodiment 16, wherein determining key impact areas further comprises using causation analysis including application of a decision tree classifier.

19. The system of embodiment 16, wherein the at least one energy savings feature includes at least one of Microsleep Tx (MSTx), Low Energy Scheduler Solution, MIMO Sleep Mode, and Cell Sleep Mode (CSM).

20. The system of embodiment 16, wherein providing energy savings for the mobile telecommunications network by activating the determined at least one energy savings features in the determined nodes includes not activating any energy savings feature in at least one of the plurality of nodes in the mobile telecommunications network and further comprising optimizing at least one of the nodes of the plurality of nodes in which no energy savings functions are activated.

Claims

29 CLAIMS What is claimed is:

1. A computerized method for saving energy in a mobile telecommunications network, the method comprising: determining (804) which of one or more nodes in a plurality of nodes of the mobile telecommunications network in which to activate the at least one energy savings function to provide energy savings to the mobile telecommunications network, wherein the determination comprises identifying a plurality of key impact areas of energy savings for the mobile telecommunications network; based on the determination of the nodes in the plurality of nodes, configuring (806) at least one node that is not the determined node and at least one node of the determined nodes to prepare for activating the at least one energy savings function; and providing (808) energy savings for the mobile telecommunications network by activating the at least one energy savings function in the determined nodes.

2. The method of claim 1, wherein the plurality of key impact areas is identified using at least one of operations of correlation, surrogative modelling, and causation analysis, and wherein the operations derive corresponding values to determine the nodes.

3. The method of claim 1 or 2, wherein the corresponding values are used to identify relative correlation of the plurality of key impact areas to the energy savings, relative importance of the plurality of key impact areas to the energy savings, or threshold values for key performance indicator features of the plurality of key impact areas to the energy savings.

4. The method of claim 1 or 2, wherein using the correlation to identify the plurality of key impact areas comprises deriving a correlation score between a key performance indicator feature and the energy savings.

5. The method of claim 1 or 2, wherein using the surrogative modelling to identify the plurality of key impact areas comprises deriving a score to indicate importance of a key performance indicator feature toward the energy savings. 30

6. The method of claim 1 or 2, wherein using the causation analysis comprises application of a decision tree classifier to determine a threshold value of a key performance indicator feature to activate the at least one energy savings function.

7. The method of claim 6, wherein determining a node in the plurality of nodes to activate the at least one energy savings function comprises comparing values of key performance indicator features of the node to thresholds of corresponding key performance indicator features, wherein the comparison is performed hierarchically through a tree structure formed by the thresholds of corresponding key performance indicator features.

8. The method of claim 1 or 2, wherein the at least one energy savings function comprises at least one of Microsleep transmit (MSTx), Low Energy Scheduler Solution, multiple-input and multiple-output (MIMO) Sleep Mode, and Cell Sleep Mode (CSM).

9. The method of claim 1 or 2, wherein determining which nodes in the plurality of nodes of the mobile telecommunications network in which to activate the at least one energy savings function comprises aggregating values of a plurality of key performance indicators from the plurality of nodes, wherein at least one value of a key performance indicator is converted from a cell level to a sector level.

10. The method of claim 1 or 2, wherein the key impact areas of energy savings for the mobile telecommunications network comprises one or more of the following: mobility, number of calls, radio utilization, and inter site distance cluster radio utilization.

11. The method of claim 1 or 2, further comprising: determining (802) for a portion of the mobile telecommunications network, energy savings that would occur in response to application of at least one energy savings function to the portion of the mobile telecommunications network.

12. The method of claim 1 or 2, and further comprising generating and storing an energy savings score for each of the determined nodes of the plurality of nodes.

13. A computer system (1000) to perform operations for saving energy in a mobile telecommunications network, the computer system comprising: a processor (1002) and memory (1004) coupled to the processor, wherein the memory stores instructions, which when executed by the processor, are capable to perform: determining (804) which of one or more nodes in a plurality of nodes of the mobile telecommunications network in which to activate the at least one energy savings function to provide energy savings to the mobile telecommunications network, wherein the determination comprises identifying a plurality of key impact areas of energy savings for the mobile telecommunications network; based on the determination of the nodes in the plurality of nodes, configuring (806) at least one node that is not the determined node and at least one node of the determined nodes to prepare for activating the at least one energy savings function; and providing (808) energy savings for the mobile telecommunications network by activating the at least one energy savings function in the determined nodes.

14. The computer system of claim 13, wherein the plurality of key impact areas is identified using at least one of operations of correlation, surrogative modelling, and causation analysis, and wherein the operations derive corresponding values to determine the nodes.

15. The computer system of claim 13 or 14, wherein the corresponding values are used to identify relative correlation of the plurality of key impact areas to the energy savings, relative importance of the plurality of key impact areas to the energy savings, or threshold values for key performance indicator features of the plurality of key impact areas to the energy savings.

16. The computer system of claim 13 or 14, wherein using the correlation to identify the plurality of key impact areas comprises deriving a correlation score between a key performance indicator feature and the energy savings.

17. The computer system of claim 13 or 14, wherein using the surrogative modelling to identify the plurality of key impact areas comprises deriving a score to indicate importance of a key performance indicator feature toward the energy savings.

18. The computer system of claim 13 or 14, wherein using the causation analysis comprises application of a decision tree classifier to determine a threshold value of a key performance indicator feature to activate the at least one energy savings function.

19. The computer system of claim 18, wherein determining a node in the plurality of nodes to activate the at least one energy savings function comprises comparing values of key performance indicator features of the node to thresholds of corresponding key performance indicator features, wherein the comparison is performed hierarchically through a tree structure formed by the thresholds of corresponding key performance indicator features.

20. A non-transitory computer readable medium storing instructions, which when executed by a processor, are capable to perform methods 1 to 12.