CN118263863B - Intelligent control method for power load balance - Google Patents
Intelligent control method for power load balance Download PDFInfo
- Publication number
- CN118263863B CN118263863B CN202410515674.9A CN202410515674A CN118263863B CN 118263863 B CN118263863 B CN 118263863B CN 202410515674 A CN202410515674 A CN 202410515674A CN 118263863 B CN118263863 B CN 118263863B
- Authority
- CN
- China
- Prior art keywords
- power load
- power
- load balance
- module
- data stream
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 39
- 238000012544 monitoring process Methods 0.000 claims abstract description 112
- 238000001514 detection method Methods 0.000 claims abstract description 92
- 230000005284 excitation Effects 0.000 claims abstract description 33
- 230000002159 abnormal effect Effects 0.000 claims abstract description 14
- 238000004458 analytical method Methods 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 12
- 230000003213 activating effect Effects 0.000 claims abstract description 11
- 230000001105 regulatory effect Effects 0.000 claims description 28
- 238000004364 calculation method Methods 0.000 claims description 22
- 238000010276 construction Methods 0.000 claims description 22
- 238000013528 artificial neural network Methods 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 11
- 238000012423 maintenance Methods 0.000 claims description 10
- 230000003750 conditioning effect Effects 0.000 claims description 7
- 238000007781 pre-processing Methods 0.000 claims description 7
- 238000005065 mining Methods 0.000 claims description 6
- 230000004927 fusion Effects 0.000 claims description 3
- 230000000694 effects Effects 0.000 abstract description 7
- 230000008569 process Effects 0.000 description 8
- 230000008859 change Effects 0.000 description 7
- 230000007774 longterm Effects 0.000 description 5
- 238000012417 linear regression Methods 0.000 description 4
- 238000012986 modification Methods 0.000 description 4
- 230000004048 modification Effects 0.000 description 4
- 238000012216 screening Methods 0.000 description 3
- 230000005856 abnormality Effects 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000012731 temporal analysis Methods 0.000 description 1
- 238000000700 time series analysis Methods 0.000 description 1
- 238000002759 z-score normalization Methods 0.000 description 1
Classifications
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for AC mains or AC distribution networks
- H02J3/003—Load forecast, e.g. methods or systems for forecasting future load demand
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J13/00—Circuit arrangements for providing remote indication of network conditions, e.g. an instantaneous record of the open or closed condition of each circuitbreaker in the network; Circuit arrangements for providing remote control of switching means in a power distribution network, e.g. switching in and out of current consumers by using a pulse code signal carried by the network
- H02J13/00032—Systems characterised by the controlled or operated power network elements or equipment, the power network elements or equipment not otherwise provided for
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for AC mains or AC distribution networks
- H02J3/001—Methods to deal with contingencies, e.g. abnormalities, faults or failures
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for AC mains or AC distribution networks
- H02J3/04—Circuit arrangements for AC mains or AC distribution networks for connecting networks of the same frequency but supplied from different sources
- H02J3/06—Controlling transfer of power between connected networks; Controlling sharing of load between connected networks
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J3/00—Circuit arrangements for AC mains or AC distribution networks
- H02J3/12—Circuit arrangements for AC mains or AC distribution networks for adjusting voltage in AC networks by changing a characteristic of the network load
- H02J3/14—Circuit arrangements for AC mains or AC distribution networks for adjusting voltage in AC networks by changing a characteristic of the network load by switching loads on to, or off from, network, e.g. progressively balanced loading
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
- H02J2203/10—Power transmission or distribution systems management focussing at grid-level, e.g. load flow analysis, node profile computation, meshed network optimisation, active network management or spinning reserve management
Landscapes
- Engineering & Computer Science (AREA)
- Power Engineering (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Marketing (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Public Health (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses an intelligent control method for power load balance, and relates to the technical field of power. The method comprises the following steps: monitoring the power system in real time to generate a power monitoring data stream; performing standardization processing to generate a power monitoring standard data stream; constructing a power load balance detection module; extracting a power load monitoring data stream, inputting the power load monitoring data stream into a power load balance identification sub-module, and generating a power load balance identification coefficient; inputting a load balance detection output excitation submodule and calculating a power load balance detection coefficient; judging whether the power load balance detection coefficient meets the power load balance detection constraint; if not, generating a power load balance abnormal signal; and activating a power load balance adjustment module, performing load balance adjustment analysis, and generating an electric power system adjustment decision. The technical problem that the power load balance is difficult to monitor and regulate in real time in the prior art is solved, the intelligent regulation and control of the power load balance is realized, and the technical effect of improving the stability of a power system is achieved.
Description
Technical Field
The invention relates to the technical field of power, in particular to an intelligent control method for power load balance.
Background
With rapid progress and technological changes in modern society, electric power is an important foundation for supporting industrial production, commercial operation and resident life, and stable and efficient operation is of great importance. However, with the increasing demand for power and the increasing complexity of power network structures, the problem of power load balancing is increasingly prominent, and becomes an important factor affecting the stability of the power system. The traditional power load balance control method is limited by technical means and management modes, and accurate and efficient adjustment is often difficult to achieve. On the one hand, the traditional power monitoring means have limitations in data acquisition and processing, and cannot reflect the running state and load change of the power system comprehensively in real time. On the other hand, due to the lack of an intelligent control algorithm, the traditional control method cannot be subjected to self-adaptive adjustment according to the actual condition of the power system, so that the load balance adjustment effect is poor.
Disclosure of Invention
The embodiment of the application provides an intelligent control method for power load balance, which solves the technical problem that the power load balance is difficult to monitor and regulate in real time in the prior art.
In view of the above problems, the embodiment of the application provides an intelligent control method for power load balancing.
The embodiment of the application provides an intelligent control method for power load balance, which comprises the following steps:
monitoring the power system in real time according to the power sensing monitoring component to generate a power monitoring data stream;
Carrying out standardized processing on the power monitoring data stream according to a data preprocessing component to generate a power monitoring standard data stream;
Building a power load balance detection module, wherein the power load balance detection module comprises a power load balance identification sub-module and a load balance detection output excitation sub-module;
Extracting a power load monitoring data stream according to the power monitoring standard data stream, inputting the power load monitoring data stream into the power load balance identification submodule, and generating D power load balance identification coefficients, wherein D is a positive integer greater than 1;
inputting the D power load balance identification coefficients into the load balance detection output excitation submodule, and calculating a power load balance detection coefficient;
Judging whether the power load balance detection coefficient meets power load balance detection constraint;
if the power load balance detection coefficient does not meet the power load balance detection constraint, generating a power load balance abnormal signal;
And activating a power load balance adjustment module according to the power load balance abnormal signal, and performing load balance adjustment analysis according to the power load balance adjustment module to generate an electric power system adjustment decision.
One or more technical schemes provided by the application have at least the following technical effects or advantages:
And monitoring the power system in real time through the power sensing monitoring component to generate a power monitoring data stream. And carrying out standardized processing on the power monitoring data stream according to the data preprocessing component to generate a power monitoring standard data stream. Then, a power load balance detection module is established, including a power load balance identification sub-module and a load balance detection output excitation sub-module. And extracting a power load monitoring data stream from the power monitoring standard data stream, inputting the power load monitoring data stream into a power load balance identification submodule to generate D power load balance identification coefficients, wherein D is a positive integer greater than 1. D power load balance identification coefficients are input into a load balance detection output excitation submodule, and power load balance detection coefficients are calculated. And judging whether the power load balance detection coefficient meets the power load balance detection constraint, and if the power load balance detection coefficient does not meet the power load balance detection constraint, generating a power load balance abnormal signal. And activating a power load balance adjusting module according to the power load balance abnormal signal, performing load balance adjustment analysis, and generating an electric power system adjustment decision. The technical problem that the power load balance is difficult to monitor and regulate in real time in the prior art is solved, the intelligent regulation and control of the power load balance is realized, and the technical effect of improving the stability of a power system is achieved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following description will briefly explain the drawings needed in the description of the embodiments, which are merely examples of the present invention, and other drawings can be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of an intelligent control method for power load balancing according to an embodiment of the present application;
fig. 2 is a schematic flow chart of load balance regulation analysis in the intelligent control method of power load balance according to the embodiment of the application.
Detailed Description
The embodiment of the application solves the technical problem that the power load balance is difficult to monitor and regulate in real time in the prior art by providing the intelligent control method for the power load balance.
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
It should be noted that the terms "comprises" and "comprising," along with any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or server that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed or inherent to such process, method, article, or apparatus, but may include other steps or modules not expressly listed or inherent to such process, method, article, or apparatus.
Example 1
As shown in fig. 1, an embodiment of the present application provides an intelligent control method for power load balancing, where the method includes:
monitoring the power system in real time according to the power sensing monitoring component to generate a power monitoring data stream;
The power sensing monitoring component comprises a current sensor, a voltage sensor, an electric energy quality sensor and the like, and can acquire the running state and load change of the power system through monitoring the power system in real time so as to generate power monitoring data flow. The power monitoring data flow reflects the real-time state of the power system, revealing the potential cause of the load balancing problem.
Carrying out standardized processing on the power monitoring data stream according to a data preprocessing component to generate a power monitoring standard data stream;
The data preprocessing component is used for carrying out standardized processing on the power monitoring data stream so as to eliminate noise, abnormal values and influences of different dimensions in the data, thereby generating the power monitoring standard data stream. Specifically, the data preprocessing component cleans the data in the power monitoring data stream to remove duplicate, missing or erroneous data; secondly, smoothing the data to reduce the influence of random noise; the data is then transformed to the same scale by, for example, Z-score normalization or min-max normalization. After standardized processing, the power monitoring data stream is converted into a power monitoring standard data stream, and the power monitoring standard data stream has higher quality and usability and can more accurately reflect the running state and load change of the power system.
Building a power load balance detection module, wherein the power load balance detection module comprises a power load balance identification sub-module and a load balance detection output excitation sub-module;
And constructing a power load balance detection module, wherein the power load balance detection module comprises a power load balance identification sub-module and a load balance detection output excitation sub-module, and the power load balance identification sub-module and the load balance detection output excitation sub-module are comprehensively utilized to realize real-time monitoring and evaluation of the load balance of the power system. The power load balance identification submodule receives the power monitoring standard data stream as input and identifies and analyzes the load state of the power system. The load balance detection output excitation submodule further detects and judges according to the output of the power load balance identification submodule.
Further, build the power load balance detection module, include:
invoking an identification sub-module to construct a data set, wherein the identification sub-module to construct the data set comprises a power load monitoring record set and a power load balance identification record set;
taking the power load monitoring record set as input data, taking the power load balance identification record set as output data, respectively performing supervised learning on D base learners to generate D power load balance identifiers meeting the constraint of load balance identification precision, wherein the D base learners are different from each other;
combining the D power load balance identifiers as parallel independent nodes to generate the power load balance identification sub-module;
D load balance recognition precision parameters corresponding to the D power load balance recognizers are obtained, duty ratio calculation is carried out on the D load balance recognition precision parameters, and the load balance detection output excitation submodule is generated, wherein the load balance detection output excitation submodule comprises D load balance recognition output excitation coefficients;
and connecting the power load balance identification sub-module with the load balance detection output excitation sub-module to obtain the power load balance detection module.
The identification sub-module constructs a data set comprising a power load monitoring record set and a power load balance identification record set, wherein the power load monitoring record set comprises load data of the power system in different time periods and different running states, and the power load balance identification record set is a result of carrying out balance state identification on the load data, namely a label marking whether each load data is in a balance state or not. And taking the power load monitoring record set as input data, taking the power load balance identification record set as output data, and performing supervised learning on the D base learners, wherein the D base learners are different from each other. The base learner may be generated from training data by a BP neural network, a residual neural network, a vector machine, or the like. Supervised learning is a method of training a model with existing data so that the model can predict or classify new data. In this process, each base learner learns how to identify the balance state of the power load based on the input and output data. After all the D base learners complete the supervised learning, D power load balance identifiers meeting the load balance recognition precision constraint are generated. And combining the D power load balance identifiers as parallel independent nodes to generate a power load balance identification sub-module, namely the D identifiers work in parallel and process input power load data at the same time, so that the processing speed and the processing efficiency of the whole detection module are improved. The load balance recognition precision parameters reflect the accuracy degree of each recognizer in recognizing the power load balance state, D load balance recognition precision parameters corresponding to the D power load balance recognizers are obtained, the duty ratio calculation is carried out on the D load balance recognition precision parameters, D load balance recognition output excitation coefficients are obtained, and then the load balance detection output excitation sub-module is generated. The load balance detection output excitation submodule comprises D load balance identification output excitation coefficients. And connecting the power load balance identification sub-module with the load balance detection output excitation sub-module to obtain the complete power load balance detection module. The power load balance detection module receives power load data in real time, processes and outputs recognition results in parallel through a plurality of recognizers, integrates and optimizes the results according to excitation coefficients, and finally gives accurate power load balance state assessment.
Extracting a power load monitoring data stream according to the power monitoring standard data stream, inputting the power load monitoring data stream into the power load balance identification submodule, and generating D power load balance identification coefficients, wherein D is a positive integer greater than 1;
The power load monitoring data flow is a key index and parameter reflecting the load change of the power system, and comprises information such as voltage, current, power, load distribution and the like. And extracting a power load monitoring data stream from the power monitoring standard data stream, inputting the power load monitoring data stream into a power load balance identification sub-module, and generating D power load balance identification coefficients. The power load balance identification coefficient is the result of the power load balance identifier to quantitatively evaluate the power load balance state, reflects the load balance conditions of the power system in different time and different areas, and is an important basis for judging whether the power system needs to carry out load adjustment.
Inputting the D power load balance identification coefficients into the load balance detection output excitation submodule, and calculating a power load balance detection coefficient;
d power load balance identification coefficients are input into a load balance detection output excitation submodule, and the D power load balance identification coefficients are weighted according to the D power load balance identification output excitation coefficients, so that the power load balance detection coefficients are obtained.
Judging whether the power load balance detection coefficient meets power load balance detection constraint;
if the power load balance detection coefficient does not meet the power load balance detection constraint, generating a power load balance abnormal signal;
The power load balance detection constraint is set based on the actual operation requirement and the safety standard of the power system, and includes but is not limited to a load deviation threshold, load distribution uniformity, a power factor range and the like, and reflects the basic condition that the power system should achieve in terms of load balance. Comparing the power load balance detection coefficient with the power load balance detection constraint, and checking whether the power load balance detection coefficient exceeds a set threshold range or meets a specific balance index requirement. When the power load balance detection coefficient does not satisfy the power load balance detection constraint, it means that an abnormality occurs in the load balance state of the power system or that the load balance state deviates from the expected range. In this case, the power load balance detection module may generate a power load balance abnormality signal.
And activating a power load balance adjustment module according to the power load balance abnormal signal, and performing load balance adjustment analysis according to the power load balance adjustment module to generate an electric power system adjustment decision.
The power load balance abnormal signal is used for activating a power load balance adjustment module, load balance adjustment analysis is carried out after the power load balance adjustment module is activated, and an electric power system adjustment decision is generated according to the result of the adjustment analysis so as to restore the load balance state of the electric power system.
Further, as shown in fig. 2, performing a load balance regulation analysis according to the power load balance regulation module to generate a power system regulation decision, including:
loading a conditioning module first build data set, wherein the conditioning module first build data set comprises a plurality of sample electrical load monitoring data streams;
Performing load balance regulation and control decision confidence sample mining according to each sample power load monitoring data flow in the first construction data set of the regulating module to generate a second construction data set of the regulating module;
Taking the first construction data set of the regulating module as input information, taking the second construction data set of the regulating module as output information, performing supervision training on a preset neural network architecture, and generating the power load balance regulating module when the continuous preset times of regulating decision error coefficients are smaller than or equal to a regulating decision error threshold value;
and inputting the power load monitoring data stream into the power load balance adjustment module to obtain the power system regulation and control decision.
The conditioning module first build data set includes a plurality of sample electrical load monitoring data streams, each reflecting an operating state of the electrical power system at a different time under different load conditions. And loading a first construction data set of the acquisition adjustment module, and carrying out load balance adjustment and control decision confidence sample mining on each sample power load monitoring data stream in the first construction data set of the adjustment module, namely screening samples which have important influence on the load balance adjustment decision from the original data set. By confidence sample mining, a second set of build data for the conditioning module is obtained that contains the key samples. Taking the first construction data set of the regulating module as input information, and taking the second construction data set of the regulating module as output information, and performing supervision training on a preset neural network architecture. The BP neural network is selected as a neural network architecture, and through supervised training, the BP neural network can learn the mapping relation from input to output, and continuously optimize internal parameters and weights, so that the accuracy and reliability of adjustment decisions are improved. And the adjustment decision error coefficient is used for measuring the difference between the decision generated by the BP neural network and the actual expected decision, and in the continuous iterative training process, when the continuous preset times of the adjustment decision error coefficient are smaller than or equal to the adjustment decision error threshold value, the BP neural network is indicated to reach the expected performance, so that the power load balance adjustment module is obtained. The power load balance adjustment module obtained through a large amount of data and training can quickly and accurately generate a load balance adjustment decision according to the actually input power load monitoring data flow.
Further, performing load balance regulation and control decision confidence sample mining according to each sample power load monitoring data flow in the first construction data set of the regulation module to generate a second construction data set of the regulation module, including:
Extracting a first sample power load monitoring data stream according to the first construction data set of the regulating module, wherein the first sample power load monitoring data stream is any one of the first construction data set of the regulating module;
Performing load balance regulation record retrieval according to the first sample power load monitoring data flow to obtain a first sample load balance regulation scheme set;
performing support calculation of each sample scheme according to the first sample load balance regulation scheme set, and generating a first scheme support calculation result;
Carrying out confidence coefficient calculation of each sample scheme according to the first scheme support coefficient calculation result to generate a first scheme confidence coefficient calculation result;
selecting the first sample load balance regulation scheme set according to a sample scheme confidence coefficient threshold value and the first scheme confidence coefficient calculation result to obtain a first confidence sample load balance regulation scheme set which is larger than or equal to the sample scheme confidence coefficient threshold value;
The first set of confidence sample load balancing regulatory schemes is added to the regulatory module second set of build data.
And randomly selecting one sample power load monitoring data stream from the first construction data set of the regulating module as a first sample power load monitoring data stream, wherein the first sample power load monitoring data stream represents the load state of the power system in a specific time period and contains rich load change information. According to the first sample power load monitoring data stream, searching in the historical regulation record of the power system to find a historical load balance regulation scheme related to the first sample power load monitoring data stream, namely a first sample load balance regulation scheme set. And carrying out support degree calculation of each sample scheme on the first sample load balance regulation scheme set, wherein the support degree represents the frequency of occurrence of the scheme in historical data, and obtaining a first scheme support degree calculation result after statistics. And carrying out confidence coefficient calculation of each sample scheme on the first scheme support coefficient calculation result, wherein the confidence coefficient is the ratio of the support coefficient to the total times, and obtaining the first scheme confidence coefficient calculation result after calculation. And screening the first sample load balance regulation scheme set according to a preset sample scheme confidence threshold. All schemes with confidence greater than or equal to the threshold will be retained, forming a first set of confidence sample load balancing regulatory schemes. And adding the first confidence sample load balance regulation scheme set obtained by screening into a second construction data set of the regulation module. The conditioning module second build data set will be used for neural network training to learn how to generate a high confidence load balancing regulation scheme from the input power load monitoring data stream.
Further, generating a power system regulation decision further comprises:
Obtaining a power load prediction window;
generating a power load prediction result according to the power load prediction window and the power load monitoring data flow and by combining a power load prediction module;
Comparing and analyzing the power load prediction result with the power load monitoring data stream to determine power load prediction variation characteristic data and a power load prediction variation characteristic index;
judging whether the power load prediction variation characteristic index is larger than or equal to a power load variation threshold value or not;
When the power load prediction variation characteristic index is larger than or equal to the power load variation threshold, carrying out power load balance decision according to the power load prediction variation characteristic data to generate a variation load balance scheme;
And optimizing the power system regulation and control decision according to the variant load balancing scheme to generate a first optimized power regulation and control decision.
The choice of the power prediction window depends on the specific needs of the power system, the power prediction window being a specific period of time for making predictions of the power load. And combining the power load prediction module, predicting the future power load by using a power load prediction window and the current power load monitoring data flow, and obtaining a power load prediction result. And comparing the generated power load prediction result with a real-time power load monitoring data stream for analysis. And determining the power load prediction variation characteristic data and the power load prediction variation characteristic index through comparison analysis. The variation characteristic data comprise the offset of the load peak value, the shape change of the load curve and the like; the mutation feature index is an index for quantitatively representing the features. And comparing the power load prediction variation characteristic index with a preset power load variation threshold value. The power load variation threshold is generally set according to historical data and operation experience of the power system, and is used for judging whether the variation degree of the prediction result reaches the level of taking countermeasures. If the power load prediction variation characteristic index is larger than or equal to the power load variation threshold value, the difference between the prediction result and the actual load is larger, and corresponding balance adjustment measures are needed to be adopted. And according to the power load prediction variation characteristic data, making a specific power load balance decision to generate a variation load balance scheme. And optimizing the original power system regulation and control decision according to the variant load balancing scheme to obtain a first optimized power regulation and control decision, wherein the first optimized power regulation and control decision is used as a new guiding strategy to be applied to the actual operation of the power system.
Further, generating a power load prediction result according to the power load prediction window and the power load monitoring data flow in combination with a power load prediction module, including:
the power load prediction module comprises a primary power load prediction model and a secondary power load prediction model, wherein the primary power load prediction model is used for predicting a power load smaller than or equal to a first preset window, and the secondary power load prediction model is used for predicting a power load larger than or equal to a second preset window, and the first preset window is smaller than the second preset window;
And if the power load prediction window is smaller than or equal to the first preset window, activating the primary power load prediction model to predict the power load of the power load monitoring data stream, so as to obtain the power load prediction result.
The power load prediction module includes a primary power load prediction model and a secondary power load prediction model. Optionally, a linear regression is selected to construct a primary power load prediction model, recent power load data is collected, characteristics closely related to short-term load change are selected according to historical data and experience, a linear regression equation is constructed, a load value is used as a dependent variable, the selected characteristics are used as independent variables, model parameters, namely regression coefficients, are estimated by using a least square method and other methods, a specific form of the linear regression model is obtained through training a data fitting model, and the established linear regression model is utilized to predict new power load data. Optionally, an autoregressive integral moving average model in the time series analysis model is selected to construct a secondary power load prediction model, long-term historical power load data is collected, the data is preprocessed, and characteristics related to long-term load prediction are extracted. And training the model by using the processed data and the selected characteristics, and obtaining a secondary power load prediction model by adjusting model parameters and structures. The primary power load prediction model is mainly used to predict a power load in a short time (less than or equal to a first predetermined window). The secondary power load prediction model is then used to predict the power load for a longer period of time (greater than or equal to the second predetermined window). Based on the size of the power load prediction window, the system intelligently chooses to activate the corresponding prediction model. And when the prediction window is smaller than or equal to the first preset window, the system activates a primary power load prediction model to perform short-term load prediction on the power load monitoring data stream, so as to obtain a power load prediction result.
Further, if the power load prediction window is greater than or equal to the second predetermined window, activating the secondary power load prediction model to perform power load prediction on the power load monitoring data stream, and obtaining the power load prediction result.
When the power load prediction window is larger than or equal to the second preset window, the system activates a secondary power load prediction model, and long-term load prediction is carried out on the power load monitoring data flow, so that a power load prediction result is obtained.
Further, the method comprises the steps of:
If the power load prediction window is larger than the first preset window and the power load prediction window is smaller than the second preset window, based on the power load monitoring data flow, calling the primary power load prediction model and the secondary power load prediction model to respectively conduct power load prediction, and generating a first power load prediction result and a second power load prediction result;
and carrying out data fusion on the first power load prediction result and the second power load prediction result to obtain the power load prediction result.
When the power load prediction window is greater than the first predetermined window but less than the second predetermined window, it means that the predicted time range is between short and long term. In this case, neither the primary power load prediction model nor the secondary power load prediction model alone may achieve the optimal prediction effect. Therefore, the two models are used in combination, specifically, a primary power load prediction model is called to perform short-term load prediction, and a first power load prediction result is generated; and then, calling a secondary power load prediction model to perform long-term load prediction, and generating a second power load prediction result. And carrying out data fusion on the first power load prediction result and the second power load prediction result through weighted average to obtain the power load prediction result. The power load prediction result obtained in this way is more comprehensive, accurate and reliable, and the prediction requirements of the power system under different time scales can be better met.
Further, generating a power system regulation decision further comprises:
performing fault detection according to the power monitoring standard data stream to obtain a power fault detection result and a power fault risk coefficient;
When the power failure risk coefficient is larger than/equal to a power failure risk threshold, performing a failure operation and maintenance decision according to the power failure detection result to generate a power failure operation and maintenance decision;
And optimizing the power system regulation and control decision according to the power failure operation and maintenance decision, and generating a second optimized power regulation and control decision.
And performing fault detection on the power monitoring standard data stream, namely identifying possible faults of the power system by analyzing the data, obtaining a power fault detection result comprising a fault type, a fault position and the like, and obtaining a power fault risk coefficient to represent the possibility of the faults of the current system. The power failure risk threshold is set according to the characteristics and operation and maintenance experience of the power system, and when the power failure risk coefficient is greater than or equal to the power failure risk threshold, a failure operation and maintenance decision is made according to the power failure detection result, namely, a maintenance or treatment scheme aiming at the current failure condition is formulated. And optimizing the regulation and control decision of the power system according to the operation and maintenance decision of the power failure, and obtaining a second optimized power regulation and control decision so as to reduce the influence of the failure on the operation of the power system to the maximum extent.
In summary, the embodiment of the application has at least the following technical effects:
And monitoring the power system in real time through the power sensing monitoring component to generate a power monitoring data stream. And carrying out standardized processing on the power monitoring data stream according to the data preprocessing component to generate a power monitoring standard data stream. Then, a power load balance detection module is established, including a power load balance identification sub-module and a load balance detection output excitation sub-module. And extracting a power load monitoring data stream from the power monitoring standard data stream, inputting the power load monitoring data stream into a power load balance identification submodule to generate D power load balance identification coefficients, wherein D is a positive integer greater than 1. D power load balance identification coefficients are input into a load balance detection output excitation submodule, and power load balance detection coefficients are calculated. And judging whether the power load balance detection coefficient meets the power load balance detection constraint, and if the power load balance detection coefficient does not meet the power load balance detection constraint, generating a power load balance abnormal signal. And activating a power load balance adjusting module according to the power load balance abnormal signal, performing load balance adjustment analysis, and generating an electric power system adjustment decision. The technical problem that the power load balance is difficult to monitor and regulate in real time in the prior art is solved, the intelligent regulation and control of the power load balance is realized, and the technical effect of improving the stability of a power system is achieved.
It should be noted that the sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. And the foregoing description has been directed to specific embodiments of this specification. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
The foregoing description of the preferred embodiments of the application is not intended to limit the application to the precise form disclosed, and any such modifications, equivalents, and alternatives falling within the spirit and scope of the application are intended to be included within the scope of the application.
The specification and figures are merely exemplary illustrations of the present application and are considered to cover any and all modifications, variations, combinations, or equivalents that fall within the scope of the application. It will be apparent to those skilled in the art that various modifications and variations can be made to the present application without departing from the scope of the application. Thus, the present application is intended to include such modifications and alterations insofar as they come within the scope of the application or the equivalents thereof.
Claims (6)
1. An intelligent control method for power load balancing, the method comprising:
monitoring the power system in real time according to the power sensing monitoring component to generate a power monitoring data stream;
The power monitoring data stream is subjected to standardized processing according to the data preprocessing component so as to eliminate noise, abnormal values and influences of different dimensions in the data and generate a power monitoring standard data stream;
Building a power load balance detection module, wherein the power load balance detection module comprises a power load balance identification sub-module and a load balance detection output excitation sub-module;
Extracting a power load monitoring data stream according to the power monitoring standard data stream, inputting the power load monitoring data stream into the power load balance identification submodule, and generating D power load balance identification coefficients, wherein D is a positive integer greater than 1;
inputting the D power load balance identification coefficients into the load balance detection output excitation submodule, and calculating a power load balance detection coefficient;
Judging whether the power load balance detection coefficient meets power load balance detection constraint;
if the power load balance detection coefficient does not meet the power load balance detection constraint, generating a power load balance abnormal signal;
Activating a power load balance adjustment module according to the power load balance abnormal signal, and performing load balance adjustment analysis according to the power load balance adjustment module to generate an electric power system adjustment decision;
Building a power load balance detection module, comprising:
invoking an identification sub-module to construct a data set, wherein the identification sub-module to construct the data set comprises a power load monitoring record set and a power load balance identification record set;
The power load monitoring record set comprises load data of the power system in different time periods and different running states, the power load balance identification record set is a result of carrying out balance state identification on the load data, the power load monitoring record set is taken as input data, the power load balance identification record set is taken as output data, D base learners are respectively supervised and learned to generate D power load balance identifiers meeting the constraint of load balance identification precision, and the D base learners are different from each other;
combining the D power load balance identifiers as parallel independent nodes to generate the power load balance identification sub-module;
D load balance recognition precision parameters corresponding to the D power load balance recognizers are obtained, duty ratio calculation is carried out on the D load balance recognition precision parameters, and the load balance detection output excitation submodule is generated, wherein the load balance detection output excitation submodule comprises D load balance recognition output excitation coefficients;
connecting the power load balance identification sub-module with the load balance detection output excitation sub-module to obtain the power load balance detection module;
inputting the D power load balance identification coefficients into the load balance detection output excitation submodule, and calculating the power load balance detection coefficients, wherein the power load balance detection coefficients comprise:
Inputting the D power load balance identification coefficients into a load balance detection output excitation submodule, and carrying out weighted calculation on the D power load balance identification coefficients according to the D power load balance identification output excitation coefficients to obtain power load balance detection coefficients;
performing load balance regulation analysis according to the power load balance regulation module to generate a power system regulation decision, including:
loading a conditioning module first build data set, wherein the conditioning module first build data set comprises a plurality of sample electrical load monitoring data streams;
Performing load balance regulation and control decision confidence sample mining according to each sample power load monitoring data flow in the first construction data set of the regulating module to generate a second construction data set of the regulating module;
Taking the first construction data set of the regulating module as input information, taking the second construction data set of the regulating module as output information, performing supervision training on a preset neural network architecture, and generating the power load balance regulating module when the continuous preset times of regulating decision error coefficients are smaller than or equal to a regulating decision error threshold value;
inputting the power load monitoring data stream into the power load balance adjustment module to obtain a regulation and control decision of the power system;
Performing load balance regulation and control decision confidence sample mining according to each sample power load monitoring data stream in the first construction data set of the regulating module to generate a second construction data set of the regulating module, wherein the method comprises the following steps:
Extracting a first sample power load monitoring data stream according to the first construction data set of the regulating module, wherein the first sample power load monitoring data stream is any one of the first construction data set of the regulating module;
Performing load balance regulation record retrieval according to the first sample power load monitoring data flow to obtain a first sample load balance regulation scheme set;
performing support calculation of each sample scheme according to the first sample load balance regulation scheme set, and generating a first scheme support calculation result;
Carrying out confidence coefficient calculation of each sample scheme according to the first scheme support coefficient calculation result to generate a first scheme confidence coefficient calculation result;
selecting the first sample load balance regulation scheme set according to a sample scheme confidence coefficient threshold value and the first scheme confidence coefficient calculation result to obtain a first confidence sample load balance regulation scheme set which is larger than or equal to the sample scheme confidence coefficient threshold value;
The first set of confidence sample load balancing regulatory schemes is added to the regulatory module second set of build data.
2. The method of claim 1, wherein generating a power system regulation decision further comprises:
Obtaining a power load prediction window;
generating a power load prediction result according to the power load prediction window and the power load monitoring data flow and by combining a power load prediction module;
Comparing and analyzing the power load prediction result with the power load monitoring data stream to determine power load prediction variation characteristic data and a power load prediction variation characteristic index;
judging whether the power load prediction variation characteristic index is larger than or equal to a power load variation threshold value or not;
When the power load prediction variation characteristic index is larger than or equal to the power load variation threshold, carrying out power load balance decision according to the power load prediction variation characteristic data to generate a variation load balance scheme;
And optimizing the power system regulation and control decision according to the variant load balancing scheme to generate a first optimized power regulation and control decision.
3. The method of claim 2, wherein generating a power load prediction result in conjunction with a power load prediction module based on the power load prediction window and the power load monitoring data stream comprises:
the power load prediction module comprises a primary power load prediction model and a secondary power load prediction model, wherein the primary power load prediction model is used for predicting a power load smaller than or equal to a first preset window, and the secondary power load prediction model is used for predicting a power load larger than or equal to a second preset window, and the first preset window is smaller than the second preset window;
And if the power load prediction window is smaller than or equal to the first preset window, activating the primary power load prediction model to predict the power load of the power load monitoring data stream, so as to obtain the power load prediction result.
4. The method of claim 3, wherein if the power load prediction window is greater than/equal to the second predetermined window, activating the secondary power load prediction model to perform power load prediction on the power load monitoring data stream, and obtaining the power load prediction result.
5. A method according to claim 3, wherein the method comprises:
If the power load prediction window is larger than the first preset window and the power load prediction window is smaller than the second preset window, based on the power load monitoring data flow, calling the primary power load prediction model and the secondary power load prediction model to respectively conduct power load prediction, and generating a first power load prediction result and a second power load prediction result;
and carrying out data fusion on the first power load prediction result and the second power load prediction result to obtain the power load prediction result.
6. The method of claim 1, wherein generating a power system regulation decision further comprises:
performing fault detection according to the power monitoring standard data stream to obtain a power fault detection result and a power fault risk coefficient;
When the power failure risk coefficient is larger than/equal to a power failure risk threshold, performing a failure operation and maintenance decision according to the power failure detection result to generate a power failure operation and maintenance decision;
And optimizing the power system regulation and control decision according to the power failure operation and maintenance decision, and generating a second optimized power regulation and control decision.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410515674.9A CN118263863B (en) | 2024-04-26 | 2024-04-26 | Intelligent control method for power load balance |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410515674.9A CN118263863B (en) | 2024-04-26 | 2024-04-26 | Intelligent control method for power load balance |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN118263863A CN118263863A (en) | 2024-06-28 |
| CN118263863B true CN118263863B (en) | 2024-10-18 |
Family
ID=91605290
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410515674.9A Active CN118263863B (en) | 2024-04-26 | 2024-04-26 | Intelligent control method for power load balance |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118263863B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116646933A (en) * | 2023-07-24 | 2023-08-25 | 北京中能亿信软件有限公司 | Big data-based power load scheduling method and system |
| CN117394397A (en) * | 2023-08-28 | 2024-01-12 | 国网河北省电力有限公司保定供电分公司 | Self-adaptive power load balance control method and electronic equipment |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108539784B (en) * | 2018-04-13 | 2020-01-14 | 华南理工大学 | Demand side response-based microgrid optimal unit and time-of-use electricity price optimization method |
| CN112200373A (en) * | 2020-10-15 | 2021-01-08 | 中国科学院深圳先进技术研究院 | Training method and training device for load prediction model, storage medium and equipment |
| CN117200262A (en) * | 2023-09-07 | 2023-12-08 | 广东电网有限责任公司广州供电局 | Balance processing method and device for cable line and computer equipment |
| CN117833319A (en) * | 2024-01-12 | 2024-04-05 | 深圳市思特克电子技术开发有限公司 | Electric power peak regulation system based on Internet of things |
| CN117878978A (en) * | 2024-01-19 | 2024-04-12 | 国网浙江省电力有限公司温州市洞头区供电公司 | Intelligent balance adjustment method and system for three-phase load unbalance |
-
2024
- 2024-04-26 CN CN202410515674.9A patent/CN118263863B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116646933A (en) * | 2023-07-24 | 2023-08-25 | 北京中能亿信软件有限公司 | Big data-based power load scheduling method and system |
| CN117394397A (en) * | 2023-08-28 | 2024-01-12 | 国网河北省电力有限公司保定供电分公司 | Self-adaptive power load balance control method and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN118263863A (en) | 2024-06-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109164343B (en) | Transformer fault diagnosis method based on characteristic information quantization and weighted KNN | |
| CN116757534B (en) | Intelligent refrigerator reliability analysis method based on neural training network | |
| CN111813084B (en) | Mechanical equipment fault diagnosis method based on deep learning | |
| CN118154174B (en) | Intelligent operation and maintenance cloud platform for industrial equipment | |
| CN114595623A (en) | XGboost algorithm-based unit equipment reference value prediction method and system | |
| CN117633722A (en) | Detection control method and system based on intelligent detection robot | |
| CN110571792A (en) | Analysis and evaluation method and system for operation state of power grid regulation and control system | |
| CN112765873A (en) | LSTM algorithm-based power transformation equipment heating prediction method | |
| CN118469352B (en) | Deep learning driven power grid line loss dynamic prediction and optimization control method | |
| CN118263863B (en) | Intelligent control method for power load balance | |
| CN112580254B (en) | Multi-dimensional analysis and early warning method for converter transformer based on multi-level decision fusion | |
| CN117691756B (en) | Safety early warning management method and system for power distribution cabinet | |
| CN117842303A (en) | Parallel self-adjusting optimal control method for new energy ship power system | |
| CN116401545A (en) | Multimode fusion type turbine runout analysis method | |
| CN118329128B (en) | Method for monitoring running state of electromechanical equipment for remote intelligent processing | |
| CN112862180A (en) | Denitration system inlet NOx concentration prediction method | |
| CN118134023B (en) | Wind-solar output quantitative prediction method and prediction device for electric power system | |
| CN117708508B (en) | Method, device, equipment and storage medium for predicting service life of disconnecting switch | |
| CN117786360A (en) | Detection method and device for vehicle-mounted switching power supply | |
| CN118473291A (en) | Method and system for optimizing motor torque control | |
| CN118300128A (en) | Frequency modulation control strategy optimization method and system for power grid unit | |
| CN118277932A (en) | Method, system, equipment and medium for identifying and correcting abnormal data of electricity load | |
| CN115042227A (en) | Speed reducer maintenance method, maintenance device, and storage medium | |
| CN117923331A (en) | Load control system and method based on crane hoisting | |
| CN118938842A (en) | Big data-based electric furnace production management system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |