CN106651200A - Electrical load management method and system for industrial enterprise aggregate user - Google Patents
Electrical load management method and system for industrial enterprise aggregate user Download PDFInfo
- Publication number
- CN106651200A CN106651200A CN201611248264.4A CN201611248264A CN106651200A CN 106651200 A CN106651200 A CN 106651200A CN 201611248264 A CN201611248264 A CN 201611248264A CN 106651200 A CN106651200 A CN 106651200A
- Authority
- CN
- China
- Prior art keywords
- load
- data
- module
- industrial enterprise
- management
- 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.)
- Pending
Links
- 238000007726 management method Methods 0.000 title claims abstract description 70
- 238000000034 method Methods 0.000 claims abstract description 28
- 238000004519 manufacturing process Methods 0.000 claims abstract description 9
- 238000004458 analytical method Methods 0.000 claims abstract description 8
- 230000005611 electricity Effects 0.000 claims description 21
- 238000013528 artificial neural network Methods 0.000 claims description 17
- 238000004364 calculation method Methods 0.000 claims description 12
- 240000002853 Nelumbo nucifera Species 0.000 claims description 9
- 235000006508 Nelumbo nucifera Nutrition 0.000 claims description 9
- 235000006510 Nelumbo pentapetala Nutrition 0.000 claims description 9
- 238000012544 monitoring process Methods 0.000 claims description 9
- 230000004044 response Effects 0.000 claims description 9
- 230000007246 mechanism Effects 0.000 claims description 7
- 239000003607 modifier Substances 0.000 claims description 5
- 230000008859 change Effects 0.000 claims description 4
- 238000010801 machine learning Methods 0.000 claims description 4
- 238000010606 normalization Methods 0.000 claims description 4
- 238000005457 optimization Methods 0.000 claims description 4
- 230000009467 reduction Effects 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 2
- 210000004218 nerve net Anatomy 0.000 claims 1
- 230000011218 segmentation Effects 0.000 abstract 2
- 238000013480 data collection Methods 0.000 abstract 1
- 238000011240 pooled analysis Methods 0.000 abstract 1
- 238000004422 calculation algorithm Methods 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 8
- 230000006870 function Effects 0.000 description 4
- 230000003993 interaction Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 238000009826 distribution Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000006116 polymerization reaction Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 241001269238 Data Species 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000011217 control strategy Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000004134 energy conservation Methods 0.000 description 2
- 230000033001 locomotion Effects 0.000 description 2
- 230000007935 neutral effect Effects 0.000 description 2
- 238000012546 transfer Methods 0.000 description 2
- 238000012384 transportation and delivery Methods 0.000 description 2
- 201000004569 Blindness Diseases 0.000 description 1
- 244000131316 Panax pseudoginseng Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 238000004378 air conditioning Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000013277 forecasting method Methods 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 230000035772 mutation Effects 0.000 description 1
- 210000005036 nerve Anatomy 0.000 description 1
- 239000003973 paint Substances 0.000 description 1
- 230000000737 periodic effect Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
- G06Q10/06375—Prediction of business process outcome or impact based on a proposed change
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- Entrepreneurship & Innovation (AREA)
- General Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- General Business, Economics & Management (AREA)
- Evolutionary Computation (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Development Economics (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Game Theory and Decision Science (AREA)
- Biophysics (AREA)
- Software Systems (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention discloses an electrical load management method and an electrical load management system for an industrial enterprise aggregate user. The method comprises the steps of: step 1, acquiring real-time load data of the industrial enterprise aggregate user needed for load management from a data collection system, and carrying out load analysis and load data segmentation; step 2, carrying out pooled analysis on historical data of time sequences of each aggregate object according to segmentation results, constructing different predictive models, and predicting future electrical load data based on historical electrical data and real-time electrical load data of the user and influence factors; and step 3, after a load prediction result is obtained, comparing the load data of a load management control scheme with the real-time data in combination with an industrial enterprise production plan and an electrical load usage situation to complete feedback correction. The load management method comprises two parts of load prediction and load control, accomplishes a distributed load management method for an industrial enterprise and solves the problem of load management at the demand side of the industrial enterprise aggregate user.
Description
【Technical field】
The invention belongs to electric load energy conservation technology, more particularly to a kind of industrial enterprise's syndication users electric load pipe
Reason method and system.
【Background technology】
Develop rapidly with economy, the continuous protrusion of the continuous improvement of the level of IT application and global resources problem, rationally open
Send out and utilize the energy, sane development is coordinated in power industry, set up strong intelligent grid and all build and be faced with new challenges.By communication now
Technology and digital Control Technology, improve electrical network intelligent level, and the theory for adapting to Sustainable Development in Future is required, is current electricity
Power industrial development and progressive the only way which must be passed.
The load management of Industry enterprise customer electric power, referring to improves electricity consumption behavior and the use of user by load adjustment technology
Electrically, so as to reduce load peak, obtain and save electric energy, reduce customer charge.Accurate load prediction results can
Sensed in advance load variations trend, is processed by corresponding calculating and provides matched load management control strategy, effectively
Ground load peak load shifting, meets the requirement of dsm.
Dsm be not only specification is carried out to user power utilization behavior, can with according to grid operating conditions to itself
Generated output be adjusted correspondingly, will user side distributed power generation resource unification include dsm category.Load
General differentiated control, is broadly divided into critical load and controllable burden.Critical load is the load for needing to lay special stress on protecting supply of electric power；
And controllable burden in case of emergency can suitably cut off, under normal circumstances can also be by dsm or Demand-side
Response reaches optimization load use, the purpose of energy saving.
Current demand side management technology, especially refine to the DSM based on industrial enterprise in popularization rank
Section, is based primarily upon the regulation and control analogy of legacy system stage load and launches, and Counter-techniques are less.With the electric load of legacy system magnitude
Difference, used as Demand-side, the distribution scope of its distribution system is little, and load radix is less, and number of users is few, and electricity consumption for industrial enterprise
It is relatively simple for structure；Its load value easily produces mutation, and stability is poor, and data can usually be lacked or have that error is very big to be lacked
The bad data of mistake value.And in the load control stage, simple direct load control has blindness and error, need using thin
Change the distributed load management of classification.
【The content of the invention】
It is an object of the invention to overcome above-mentioned deficiency, there is provided a kind of industrial enterprise's syndication users management of power load method
And system, the load management method constitutes with load prediction and spatial load forecasting two large divisions, completes the distribution for industrial enterprise
Formula load management method, solves the problems, such as the Demand-side load management of industrial enterprise's syndication users.
To reach above-mentioned purpose, technical scheme below is present invention employs：
A kind of industrial enterprise's syndication users management of power load method, comprises the following steps：
Step 1, the Real-time Load number of industrial enterprise's syndication users of required load management is obtained from data collecting system
According to, carry out load Analysis and load data subdivision, with Demand Side Response mechanism as goal orientation, to load data carry out classification with
Feature extraction, load data is subdivided into：Basic guarantee load, production schedule load, weather sensitive load, controllable lighting load
With the type load of random load five；
Step 2, carries out Macro or mass analysis, with god according to subdivision result by the time series historical data of each aggregate objects
Jing networks and the data digging method of the machine learning different forecast models of structure, based on user's history electricity consumption data, real-time electricity consumption
Load data and influence factor are predicting following power load data；
Step 3, after obtaining load prediction results, with reference to industrial enterprise's production schedule and power load service condition, uses
Demand Side Response mechanism carrys out administrative loads；The load data of load management regulation and control scheme and real time data are compared, feedback is completed
Amendment.
The foundation of described forecast model is, based on user power utilization historical data, to analyze user from electricity consumption historical data and use
Electricity custom, the influence factor of equipment running status and electricity consumption trend and environment, power load and time relationship, set up electricity consumption and bear
Lotus forecast model.
Described Demand Side Response mechanism includes direct load control, interruptible load and tou power price.
Industry enterprise customer side power load prediction history data source is in SCADA electric power monitoring systems, the data of collection
First pre-processed, preprocess method includes data cleansing, dimensionality reduction and data normalization.
At control point of the administrative loads before predicted load reaches maximum demand, by the interior requirement curve model for setting
Criterion carries out demand control work, that is, compare requirement value and predicted load judges to adjust load, selects current most suitable
Energy-saving scheme, controls in advance maximum demand.
A kind of industrial enterprise's syndication users power load management system, including load data acquisition module, meteorological data obtain
Delivery block, database, neural network prediction module, error calculation correcting module and data display unit；
Wherein, described load data acquisition module, is connected with SCADA electric power monitoring systems, for obtaining load management
Required historical load data and real-time load data；
Described meteorological data acquisition module, is connected with weather site interface, meteorological number needed for for obtaining load management
According to；
Described database, connection historical load data acquisition module and meteorological data acquisition module, for storing history
Load data, real-time load data and meteorological data；
Described neural network prediction module, is connected with database, for based on user's history electricity consumption data, real-time electricity consumption
Load data and influence factor are predicting following power load data；
Described error calculation correcting module, is connected with neural network prediction module and load data acquisition module, is used for
The load data of load management regulation and control scheme and real time data are compared, feedback modifiers are completed, real-time modified load data are simultaneously excellent
Change the database of training neural network prediction module；
Described data display unit, is connected with database, neural network prediction module and error calculation correcting module, uses
In man-machine interaction, including the classification of data query, Drawing of Curve, system loading shows and load control scheme is pushed.
Also include date discrimination module, date discrimination module be connected with database, for by obtain predict date day and
Built-in calendar is compared, and the load data in database is arranged as into time series according to time sampling interval, and subdivision classifies as phase
Like day data set.
Described data display unit includes data inquiry module, Drawing of Curve module, system loading sort module and bears
Lotus regulates and controls module；
Described data inquiry module, realizes that user specifies day or set period inquiry for data query；
Described Drawing of Curve module, for draw specified day history load curve, all kinds of load curves, real-time curve,
Prediction curve, Real-time Error comparison chart and longer period historical load trend, and show load value；
Described system loading sort module, for showing all kinds of load classification methods, and shows corresponding load curve；
Described load control module, bear before and after estimated regulation and control for pushing load management regulation and control scheme, and intuitively showing
Lotus curvilinear motion situation.
Also include intelligent control module, intelligent control module connects with neural network prediction module and error calculation correcting module
Connect, for completing to automatically adjust according to load management and optimization control scheme and real-time system structure, scheme is pushed and excess load
Report to the police, carry out direct load control or notify client as needed and be controlled load by operating a switch according to actual conditions.
Compared with prior art, the present invention at least has following technique effect：
Industrial enterprise's syndication users management of power load method of the present invention completes load management for industrial enterprise, negative
Lotus is predicted, it then follows the principle of " first segment and predict again ", i.e., for each user in Industry enterprise customer polymerization carries out characteristic
Analysis, different qualities classification is subdivided into using clustering algorithm by user load, then using different prediction algorithms carries out load respectively
Load prediction results under various prediction algorithms are finally weighted summation by prediction, are finally predicted the outcome；Spatial load forecasting
In the stage, predicting the outcome as Primary Reference foundation for short-term prediction and ultra-short term is mutually tied with load importance and part throttle characteristics
Close, complete load control scheme；Than the prediction of conventional system stage load, load refinement is more effectively completed, more meet Demand-side load
Characteristic, more effectively completes power load excacation.
The management system of the present invention is pre- by load data acquisition module, meteorological data acquisition module, database, neutral net
Survey module, error calculation correcting module and data display unit composition, the management of power load of whole Industry enterprise customer polymerization
System is effectively managed to realize target with load, in combination with SCADA electric power monitoring systems, completes bi-directional data with database mutual
Connection, and realize operable friendly man-machine interface.And by described neural network prediction module to the history electricity consumption based on user
Data, real-time power load data and influence factor are predicting following power load data；Error calculation correcting module is by load
The load data of management regulation scheme is compared with real time data, completes feedback modifiers, and real-time modified load data simultaneously optimize training
The relevant parameter of neural network prediction module；Final data display unit is used for man-machine interaction, carries out data query, curve and paints
System, system loading classification show and load control scheme is pushed.Whole load management system is simple and reliable, can efficiently accomplish negative
Lotus refines, and more meets Demand-side part throttle characteristics, carries out the distributed load management of classification.
【Description of the drawings】
Fig. 1 is industrial enterprise's syndication users Power system load data classification；
Fig. 2 is industrial enterprise's syndication users management of power load control technology module diagram；
Fig. 3 is industrial enterprise's syndication users load forecast flow chart；
Fig. 4 is industrial enterprise's syndication users power load management system schematic diagram.
【Specific embodiment】
With reference to the accompanying drawings and detailed description the present invention is described in detail.
The short-term load forecasting and load management of Industry enterprise customer side power load under intelligent grid, it is desirable in intelligent electricity
Under the dsm of net is required, with reference to Industry enterprise customer side power load own characteristic, usage history load and other ginsengs
On the basis of examining data, the load of following short-term or even ultra-short term is accurately predicted, and realizes Payload control and management,
To reach the purpose of accurate prediction Effective Regulation energy science management.
A kind of industrial enterprise's syndication users management of power load method basic step of the present invention is：Load data is segmented, born
The realization of lotus prediction, spatial load forecasting and load management system.Specifically include following steps：
First, the industrial enterprise's aggregate objects for required load management carry out load Analysis and load data subdivision.
Load data acquisition is carried out to the required research object for carrying out load management, the i.e. data collecting system of industrial enterprise, it is perfect
Data prepare and data prediction work；Load data is segmented according to the method and load self-characteristic of data clusters.
The load data subdivision is referred to and for load to complete feature extraction and effectively classification according to certain standard.Due to
Widely using for SCADA electric power monitoring systems, can easily obtain real time mass customer charge data, with reference to above-mentioned physics point
Class and algorithm are clustered, and with dsm as goal orientation, load can more effectively be classified and feature extraction.
The temperature adjustment loads such as the different load different characteristics covered of industrial enterprise Demand-side user, such as air-conditioning are subject to temperature
The loads such as the inside even from weather such as rainfall, illumination are affected by fine day or wet weather etc., and industrial production electricity consumption and the production schedule
It is related.It is high low as constraints with complicated classification degree with prediction accuracy according to all kinds of part throttle characteristics, consider direct load
The Demand Side Response mechanism such as control, interruptible load, tou power price, using clustering algorithm, with reference to load self-characteristic, such as Fig. 1
It is shown, it is divided into basic guarantee load, production schedule load, weather sensitive load, the class of controllable lighting load and random load etc. five
Load.
Secondly, the time series historical data of each groups of users is carried out into Macro or mass analysis according to subdivision result, with god
The data digging method different forecast models of structure such as Jing networks and machine learning, with reference to Correlative Influence Factors, complete each type load
Data prediction works.
The load prediction refer to based on the other influences such as user's history electricity consumption data, real-time power load data and meteorology because
Usually predict power load.The foundation of model be based on a large amount of electricity consumption historical datas, from these data analyze user power utilization custom,
Equipment running status and electricity consumption trend and environmental impact factor, power load and time relationship etc., set up electro-load forecast mould
Type, using intelligent algorithms such as data minings, the data such as following power load of prediction.
Industry enterprise customer side power load prediction history data are mainly derived from SCADA electric power monitoring systems, due to life
The reason such as the plan of producing, load transfer, system be unstable, having bad data needs to carry out data prediction.Because load data exists
In collection and transmission exist disappearance and mistake, data should be pre-processed first, predominantly data cleansing, dimensionality reduction and
Data normalization.
Then, according to load forecast result and directly control, the dsm means such as control can be interrupted complete to bear
Lotus management regulation scheme, scheme regulation and control afterload data are compared with real time data, complete feedback modifiers.
The spatial load forecasting is referred to after acquisition load prediction results, used with reference to industrial enterprise's production schedule and power load
The means such as situation, direct load control, load scheduling transfer, the flexible load control of the response of use demand side carry out administrative loads.
At control point before predicted load reaches maximum demand, system carries out needing by the interior requirement curve model criterion for setting
Amount control work.Based on the demand control technology of load prediction, current most suitable energy-saving scheme is may be selected, controlled in advance maximum
Requirement, is prevented effectively from overload operation or even generation of tripping, it is ensured that energy-saving safe is produced.
Finally, the realization of the management of power load method of Industry enterprise customer polymerization, load management method is according to load pipe
Reason system is launched, and system realizes that data are automatically imported derivation, data processing, load prediction, spatial load forecasting, curve and the work(such as show
Energy.
The realization of described management system, the structure specific works of integral load management are divided into load forecasting method and directly
Application load predicts the outcome carries out two parts of demand control.As shown in Fig. 2 wherein predicted portions are obtained including historical load data
Delivery block, meteorological data acquisition module, date discrimination module, neural network prediction module, error calculation correcting module, load are bent
Line drafting module and prediction data export module；And control section mainly includes Real time data acquisition, load data and number in real time
According to modules such as comparison, control strategy enforcements.
Wherein, historical load data acquisition module and meteorological data acquisition module are obtained needed for load management from data-interface
Load data and meteorological data；Date discrimination module is compared by obtaining prediction date day with built-in calendar, and prediction day is divided
To working day, weekend or festivals or holidays etc., constitute suitable similar day data set；Neural network prediction module is similar by input
Day data set, is predicted the outcome using neural network prediction；Error calculation correcting module is by comparing with load prediction knot
Fruit and real-time load data, real-time modified load data simultaneously optimize training neutral net, lift later stage precision of prediction；Load curve
Drafting module and prediction data export module belong to man-machine interaction part, and backstage is predicted the outcome by derived from curve and data
Mode shows user, wherein load curve drafting module to show prediction curve and real-time curve in same reference axis, real
When refresh curve, and prediction data can in real time export as EXCEL file.
The concrete device of load management is as shown in figure 4, by data interface unit, database, application layer, key-course, presentation layer
Deng composition.
Data interface unit：It is responsible for providing the interface of historical load data and meteorological data to whole load management system,
Corresponding load data acquisition module, by electric power data acquisition and supervisor control (SCADA) from each gateway device ammeter
Place obtains load data, samples according to time interval and use time series arrangement；Obtained by the weather site interface of meteorological observatory
Take meteorological data.
Database：Including real-time data base and historical data base, real-time data base has prediction same day real-time load data group
Into historical data base is made up of history daily load data and correspondence meteorological data, and historical data is through data cleansing.
Application layer：The basic function of load prediction and control whole flow process is completed, data are imported to be responsible for being led from data-interface
Enter data and export to database and presentation layer, load data pretreatment obtains using by data cleansing and data normalization
Come the data set predicted, load prediction module completes prediction work, and prediction data is exported to database and presentation layer, and load
Management completes load demand control with optimal control, and according to load prediction results and built-in demand control data spatial load forecasting is completed
Scheme is exported to presentation layer and key-course.
Key-course：Complete to automatically adjust according to load management and optimization control scheme and real-time system structure, scheme is pushed
With excess load report to the police etc. function, according to actual conditions carry out direct load control or notify as needed client and by operate a switch into
Row control load.
Presentation layer：As man-machine interactive platform, with data query, Drawing of Curve, display systems load classification and load
The functions such as regulation and control scheme.Data query realizes that user specifies day or set period inquiry；Curve can draw specified day historical load
Curve, all kinds of load curves, real-time curve, prediction curve, Real-time Error comparison chart and longer period historical load trend
Etc., can mouse take and to show a load value；System loading classification feature can intuitively show each type load point using circuit system figure
Class method, and show corresponding load curve；Load control scheme is intuitively shown pre- using the method real time propelling movement scheme for pushing
Load curve situation of change before and after meter regulation and control.
Embodiment 1：
By taking certain industry park energy conservation as an example, various user types such as factory, R＆D institution, hotel are covered in industry park.It is first
The load data subdivision based on clustering algorithm and five river physical characteristics is first carried out, load prediction work is segmented based on load data
Launch, pre- flow gauge is as shown in Figure 3.Load data when daily 24, a point was taken per 15 minutes, and whole day is born for 96 points totally as history
Lotus input quantity.A certain day data include historical load data, meteorological data and same day meteorologic factor, use time sequence, nerve
The methods such as network, machine learning are predicted, and improve algorithm contrast precision, and introduce weather conditions and production schedule factor etc. and repair
Just predict the outcome.Prediction uses " similar day " rule, i.e., have the date of same type with the prediction day, and in the same period
It is interior, the load variations rule of conversion similar to prediction day presentation.The same period of nearest several same type days range prediction day
Interior, the load of similar day can be that close Changing Pattern is presented.Similar day is selected according to property periodic, and according to different load
Influence factor will set up different load model, it will improve prediction accuracy.
The Visualization Platform structure of management of power load method is constituted as shown in figure 4, conjunctive use SCADA electric power onlines
Monitoring system, SQL server databases and MTALAB softwares.System is broadly divided into data-interface part, database, application layer,
Presentation layer and key-course.Data-interface mainly has SCADA load datas interface and weather forecast interface, derives according to data command
Interface, is connected using odbc data source mode with database.
In data interface tier, data are obtained using each gateway device ammeter in SCADA electric power online monitoring systems, and tied
Close meteorological observatory's data-interface to import historical load data and meteorological data, meteorological data covers day most high and low temperature, and day is relative
Humidity, day maximum wind velocity etc..Data are directed into platform using Ethernet, and are stored in real-time data base.In application layer, load is completed
The work such as data prediction, load prediction and load management optimal control, prediction data is deposited to database in real time, and with it is real-time
Contrast round-off error.Application layer is connected by odbc data source mode with database, is showed predicting the outcome by presentation layer
User, realizes the data query and curve intuitively function such as displaying, and realizes man-machine interaction.Simultaneously load optimal control result will be led
Enter intelligent control module, be supplied directly to user's control scheme or complete to automatically control under certain authority.
Claims (9)
1. a kind of industrial enterprise's syndication users management of power load method, it is characterised in that comprise the following steps：
Step 1, the real-time load data of industrial enterprise's syndication users of required load management is obtained from data collecting system, is entered
Row load Analysis and load data are segmented, and with Demand Side Response mechanism as goal orientation, load data are classified and characteristic
Extract, load data is subdivided into：Basic guarantee load, production schedule load, weather sensitive load, controllable lighting load and with
The type load of machine load five；
Step 2, carries out Macro or mass analysis, with nerve net according to subdivision result by the time series historical data of each aggregate objects
Network and the data digging method of the machine learning different forecast models of structure, based on user's history electricity consumption data, real-time power load
Data and influence factor are predicting following power load data；
Step 3, after obtaining load prediction results, with reference to industrial enterprise's production schedule and power load service condition, use demand
Side response mechanism carrys out administrative loads；The load data of load management regulation and control scheme and real time data are compared, feedback modifiers are completed.
2. industrial enterprise's syndication users management of power load method according to claim 1, it is characterised in that described is pre-
The foundation for surveying model is, based on user power utilization historical data, user power utilization custom, equipment operation to be analyzed from electricity consumption historical data
The influence factor of state and electricity consumption trend and environment, power load and time relationship, set up electro-load forecast model.
3. industrial enterprise's syndication users management of power load method according to claim 1, it is characterised in that described need
Side response mechanism is asked to include direct load control, interruptible load and tou power price.
4. industrial enterprise's syndication users management of power load method according to claim 1, it is characterised in that industrial enterprise
User side load forecast historical data derives from SCADA electric power monitoring systems, and the data of collection are first pre-processed, pre- place
Reason method includes data cleansing, dimensionality reduction and data normalization.
5. industrial enterprise's syndication users management of power load method according to claim 1, it is characterised in that administrative loads
At control point before predicted load reaches maximum demand, requirement control is carried out by the interior requirement curve model criterion for setting
Work processed, that is, compare requirement value and predicted load judges to adjust load, selects current most suitable energy-saving scheme, controls in advance
Maximum demand.
6. a kind of industrial enterprise's syndication users power load management system, it is characterised in that including load data acquisition module, gas
Image data acquisition module, database, neural network prediction module, error calculation correcting module and data display unit；
Wherein, described load data acquisition module, is connected with SCADA electric power monitoring systems, needed for for obtaining load management
Historical load data and real-time load data；
Described meteorological data acquisition module, is connected with weather site interface, meteorological data needed for for obtaining load management；
Described database, connection historical load data acquisition module and meteorological data acquisition module, for storing historical load
Data, real-time load data and meteorological data；
Described neural network prediction module, is connected with database, for based on user's history electricity consumption data, real-time power load
Data and influence factor are predicting following power load data；
Described error calculation correcting module, is connected with neural network prediction module and load data acquisition module, for bearing
The load data of lotus management regulation scheme is compared with real time data, completes feedback modifiers, and real-time modified load data simultaneously optimize instruction
Practice the database of neural network prediction module；
Described data display unit, is connected, for people with database, neural network prediction module and error calculation correcting module
Machine is interacted, including the classification of data query, Drawing of Curve, system loading shows and load control scheme is pushed.
7. a kind of industrial enterprise's syndication users power load management system according to claim 6, it is characterised in that also wrap
Date discrimination module is included, date discrimination module is connected with database, for being compared with built-in calendar by obtaining prediction date day,
Load data in database is arranged as into time series according to time sampling interval, subdivision classifies as similar day data set.
8. a kind of industrial enterprise's syndication users power load management system according to claim 6, it is characterised in that described
Data display unit include data inquiry module, Drawing of Curve module, system loading sort module and load control module；
Described data inquiry module, realizes that user specifies day or set period inquiry for data query；
Described Drawing of Curve module, for drawing specified day history load curve, all kinds of load curves, real-time curve, prediction
Curve, Real-time Error comparison chart and longer period historical load trend, and show load value；
Described system loading sort module, for showing all kinds of load classification methods, and shows corresponding load curve；
Described load control module, for pushing load management regulation and control scheme, and intuitively shows that load is bent before and after estimated regulation and control
Line situation of change.
9. a kind of industrial enterprise's syndication users power load management system according to claim 6, it is characterised in that also wrap
Intelligent control module is included, intelligent control module is connected with neural network prediction module and error calculation correcting module, for foundation
Load management and optimization control scheme and real-time system structure complete to automatically adjust, scheme is pushed and excess load is reported to the police, according to real
Border situation carries out direct load control or notifies client as needed and be controlled load by operating a switch.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611248264.4A CN106651200A (en) | 2016-12-29 | 2016-12-29 | Electrical load management method and system for industrial enterprise aggregate user |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201611248264.4A CN106651200A (en) | 2016-12-29 | 2016-12-29 | Electrical load management method and system for industrial enterprise aggregate user |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106651200A true CN106651200A (en) | 2017-05-10 |
Family
ID=58835962
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201611248264.4A Pending CN106651200A (en) | 2016-12-29 | 2016-12-29 | Electrical load management method and system for industrial enterprise aggregate user |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106651200A (en) |
Cited By (39)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107330567A (en) * | 2017-07-20 | 2017-11-07 | 云南电网有限责任公司电力科学研究院 | Distribution switch-time load Forecasting Methodology based on big data technology |
| CN107748940A (en) * | 2017-11-16 | 2018-03-02 | 国网上海市电力公司 | A kind of energy conservation potential Quantitative prediction methods |
| CN107784455A (en) * | 2017-11-16 | 2018-03-09 | 鼎信信息科技有限责任公司 | A kind of power network peak load shifting method based on trade power consumption database and distribution transforming weight overload prediction |
| CN108053056A (en) * | 2017-11-25 | 2018-05-18 | 国网辽宁省电力有限公司经济技术研究院 | A kind of power industry load forecasting method that can improve precision of prediction |
| CN108628964A (en) * | 2018-04-18 | 2018-10-09 | 江苏运时数据软件股份有限公司 | A kind of intelligent scene enterprise big data system |
| CN108985513A (en) * | 2018-07-17 | 2018-12-11 | 合肥工业大学 | Industrial enterprise's Electric Load Prediction System |
| CN109492883A (en) * | 2018-10-18 | 2019-03-19 | 山东工业职业学院 | A kind of efficiency artificial intelligence on-line analysis system and method |
| CN109783716A (en) * | 2019-01-21 | 2019-05-21 | 贵州黔源电力股份有限公司 | A kind of power supply and demand data automatically extract and processing system and method |
| CN110008251A (en) * | 2019-03-07 | 2019-07-12 | 平安科技（深圳）有限公司 | Data processing method, device and computer equipment based on time series data |
| CN110135761A (en) * | 2019-05-27 | 2019-08-16 | 国网河北省电力有限公司沧州供电分公司 | For power demand side response Load Regulation method of commerce, system and terminal device |
| WO2019169706A1 (en) * | 2018-03-09 | 2019-09-12 | 亿可能源科技（上海）有限公司 | Demand prediction method, demand control method, and system |
| WO2020015453A1 (en) * | 2018-07-19 | 2020-01-23 | 华为技术有限公司 | Data processing method and system |
| CN111144654A (en) * | 2019-12-27 | 2020-05-12 | 深圳供电局有限公司 | Park energy management configuration method and device based on Internet of things |
| CN111415192A (en) * | 2020-02-27 | 2020-07-14 | 重庆森鑫炬科技有限公司 | Water quality prediction method for user based on big data |
| CN111525563A (en) * | 2020-05-23 | 2020-08-11 | 国家电网有限公司 | Accurate long-term power load prediction method |
| CN111564848A (en) * | 2020-06-09 | 2020-08-21 | 剑科云智(深圳)科技有限公司 | Intelligent power dispatching method and power utilization load prediction device for micro power grid |
| CN111596255A (en) * | 2020-07-27 | 2020-08-28 | 国网江西省电力有限公司电力科学研究院 | Metering error remote online detection method of reinforcement learning algorithm |
| CN111898821A (en) * | 2020-07-28 | 2020-11-06 | 国网山东省电力公司禹城市供电公司 | Power load prediction method, system and device |
| CN112332404A (en) * | 2020-10-12 | 2021-02-05 | 国网冀北电力有限公司计量中心 | Intelligent management system and method for heating service |
| CN112488418A (en) * | 2020-12-14 | 2021-03-12 | 中国南方电网有限责任公司 | Full-topology load prediction method and device and computer equipment |
| CN112696728A (en) * | 2021-01-22 | 2021-04-23 | 北京嘉洁能科技股份有限公司 | Control system for balancing electric load and reducing electric capacity increase |
| CN113326897A (en) * | 2021-06-25 | 2021-08-31 | 国网冀北电力有限公司承德供电公司 | Temperature measurement plan generation method and device for overhead transmission line and electronic equipment |
| CN113632131A (en) * | 2019-04-10 | 2021-11-09 | 三菱电机株式会社 | Power management device |
| CN113780901A (en) * | 2021-11-10 | 2021-12-10 | 国网江苏省电力有限公司营销服务中心 | Network load cooperative control method applied to energy controller |
| CN113887809A (en) * | 2021-10-11 | 2022-01-04 | 国网新疆电力有限公司巴州供电公司 | Power distribution network supply and demand balance method, system, medium and computing equipment under double-carbon target |
| CN113919572A (en) * | 2021-10-14 | 2022-01-11 | 国网信息通信产业集团有限公司 | Load prediction method, device and system |
| CN114118580A (en) * | 2021-11-29 | 2022-03-01 | 国网山东省电力公司东营供电公司 | Yellow river basin pollution source monitoring and early warning method based on electric power-environmental protection data fusion analysis |
| CN114169637A (en) * | 2021-12-21 | 2022-03-11 | 天纳能源科技（上海）有限公司 | Energy-saving optimization evaluation system |
| CN114372602A (en) * | 2020-10-15 | 2022-04-19 | 国网江苏省电力有限公司 | System protection intelligent analysis system and method based on load aggregation management platform |
| CN114662043A (en) * | 2022-05-25 | 2022-06-24 | 广东电网有限责任公司佛山供电局 | Real-time evaluation method for user load response condition and related device thereof |
| US11455323B2 (en) | 2018-07-19 | 2022-09-27 | Huawei Cloud Computing Technologies Co., Ltd. | Data processing method and system |
| CN116151509A (en) * | 2023-02-13 | 2023-05-23 | 国家电投集团数字科技有限公司 | Power information management method and system based on data fusion |
| CN116979531A (en) * | 2023-09-25 | 2023-10-31 | 山西京能售电有限责任公司 | Novel energy data monitoring method and method for monitoring auxiliary power market |
| CN117132420A (en) * | 2023-10-27 | 2023-11-28 | 国网湖北省电力有限公司营销服务中心(计量中心) | Response characteristic analysis method and system of power demand response object |
| CN117293829A (en) * | 2023-11-27 | 2023-12-26 | 国网湖北省电力有限公司 | Power peak shaving method based on 5G and 4G short sharing double-network mutual authentication wireless communication |
| CN117335416A (en) * | 2023-11-24 | 2024-01-02 | 国网浙江省电力有限公司 | Method, device, equipment and storage medium for optimizing power load |
| CN117424231A (en) * | 2023-12-14 | 2024-01-19 | 深圳市华星数字有限公司 | Energy-saving power distribution control system and method |
| CN118195286A (en) * | 2024-05-20 | 2024-06-14 | 成都秦川物联网科技股份有限公司 | Energy management method based on industrial Internet of things, internet of things system and equipment |
| CN112365083B (en) * | 2020-11-26 | 2024-08-20 | 深圳供电局有限公司 | Power load prediction method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102722145A (en) * | 2012-05-17 | 2012-10-10 | 深圳市科陆电子科技股份有限公司 | Intelligent household appliance control system |
| CN102999791A (en) * | 2012-11-23 | 2013-03-27 | 广东电网公司电力科学研究院 | Power load forecasting method based on customer segmentation in power industry |
| CN103972896A (en) * | 2014-05-13 | 2014-08-06 | 国家电网公司 | Load modeling and optimal control method based on demand response |
| US20140336934A1 (en) * | 2013-05-07 | 2014-11-13 | Atomic Energy Council - Institute Of Nuclear Energy Research | Ensemble wind power forecasting platform system and operational method thereof |
| CN105590174A (en) * | 2015-12-29 | 2016-05-18 | 南京因泰莱电器股份有限公司 | Enterprise power consumption load prediction method based on K-means clustering RBF neural network |
-
2016
- 2016-12-29 CN CN201611248264.4A patent/CN106651200A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102722145A (en) * | 2012-05-17 | 2012-10-10 | 深圳市科陆电子科技股份有限公司 | Intelligent household appliance control system |
| CN102999791A (en) * | 2012-11-23 | 2013-03-27 | 广东电网公司电力科学研究院 | Power load forecasting method based on customer segmentation in power industry |
| US20140336934A1 (en) * | 2013-05-07 | 2014-11-13 | Atomic Energy Council - Institute Of Nuclear Energy Research | Ensemble wind power forecasting platform system and operational method thereof |
| CN103972896A (en) * | 2014-05-13 | 2014-08-06 | 国家电网公司 | Load modeling and optimal control method based on demand response |
| CN105590174A (en) * | 2015-12-29 | 2016-05-18 | 南京因泰莱电器股份有限公司 | Enterprise power consumption load prediction method based on K-means clustering RBF neural network |
Non-Patent Citations (1)
| Title |
|---|
| 张明光: "《电力系统远动及调度自动化》", 30 April 2010 * |
Cited By (53)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107330567A (en) * | 2017-07-20 | 2017-11-07 | 云南电网有限责任公司电力科学研究院 | Distribution switch-time load Forecasting Methodology based on big data technology |
| CN107748940A (en) * | 2017-11-16 | 2018-03-02 | 国网上海市电力公司 | A kind of energy conservation potential Quantitative prediction methods |
| CN107784455A (en) * | 2017-11-16 | 2018-03-09 | 鼎信信息科技有限责任公司 | A kind of power network peak load shifting method based on trade power consumption database and distribution transforming weight overload prediction |
| CN107748940B (en) * | 2017-11-16 | 2021-10-12 | 国网上海市电力公司 | Power-saving potential quantitative prediction method |
| CN108053056A (en) * | 2017-11-25 | 2018-05-18 | 国网辽宁省电力有限公司经济技术研究院 | A kind of power industry load forecasting method that can improve precision of prediction |
| WO2019169706A1 (en) * | 2018-03-09 | 2019-09-12 | 亿可能源科技（上海）有限公司 | Demand prediction method, demand control method, and system |
| CN110245771B (en) * | 2018-03-09 | 2021-08-20 | 亿可能源科技（上海）有限公司 | Demand prediction method, demand control method and system |
| CN110245771A (en) * | 2018-03-09 | 2019-09-17 | 亿可能源科技（上海）有限公司 | Requirement prediction technique, demand control method and system |
| CN108628964A (en) * | 2018-04-18 | 2018-10-09 | 江苏运时数据软件股份有限公司 | A kind of intelligent scene enterprise big data system |
| CN108628964B (en) * | 2018-04-18 | 2021-08-06 | 江苏运时数据软件股份有限公司 | Intelligent scene-based enterprise big data system |
| CN108985513A (en) * | 2018-07-17 | 2018-12-11 | 合肥工业大学 | Industrial enterprise's Electric Load Prediction System |
| WO2020015453A1 (en) * | 2018-07-19 | 2020-01-23 | 华为技术有限公司 | Data processing method and system |
| US11455323B2 (en) | 2018-07-19 | 2022-09-27 | Huawei Cloud Computing Technologies Co., Ltd. | Data processing method and system |
| CN109492883A (en) * | 2018-10-18 | 2019-03-19 | 山东工业职业学院 | A kind of efficiency artificial intelligence on-line analysis system and method |
| CN109783716A (en) * | 2019-01-21 | 2019-05-21 | 贵州黔源电力股份有限公司 | A kind of power supply and demand data automatically extract and processing system and method |
| CN110008251A (en) * | 2019-03-07 | 2019-07-12 | 平安科技（深圳）有限公司 | Data processing method, device and computer equipment based on time series data |
| CN110008251B (en) * | 2019-03-07 | 2023-07-04 | 平安科技（深圳）有限公司 | Data processing method and device based on time sequence data and computer equipment |
| WO2020177366A1 (en) * | 2019-03-07 | 2020-09-10 | 平安科技（深圳）有限公司 | Data processing method and apparatus based on time sequence data, and computer device |
| CN113632131A (en) * | 2019-04-10 | 2021-11-09 | 三菱电机株式会社 | Power management device |
| CN110135761A (en) * | 2019-05-27 | 2019-08-16 | 国网河北省电力有限公司沧州供电分公司 | For power demand side response Load Regulation method of commerce, system and terminal device |
| CN111144654A (en) * | 2019-12-27 | 2020-05-12 | 深圳供电局有限公司 | Park energy management configuration method and device based on Internet of things |
| CN111415192A (en) * | 2020-02-27 | 2020-07-14 | 重庆森鑫炬科技有限公司 | Water quality prediction method for user based on big data |
| CN111525563A (en) * | 2020-05-23 | 2020-08-11 | 国家电网有限公司 | Accurate long-term power load prediction method |
| CN111564848A (en) * | 2020-06-09 | 2020-08-21 | 剑科云智(深圳)科技有限公司 | Intelligent power dispatching method and power utilization load prediction device for micro power grid |
| CN111596255A (en) * | 2020-07-27 | 2020-08-28 | 国网江西省电力有限公司电力科学研究院 | Metering error remote online detection method of reinforcement learning algorithm |
| CN111898821A (en) * | 2020-07-28 | 2020-11-06 | 国网山东省电力公司禹城市供电公司 | Power load prediction method, system and device |
| CN112332404A (en) * | 2020-10-12 | 2021-02-05 | 国网冀北电力有限公司计量中心 | Intelligent management system and method for heating service |
| CN112332404B (en) * | 2020-10-12 | 2022-09-16 | 国网冀北电力有限公司计量中心 | Intelligent management system and method for heating service |
| CN114372602A (en) * | 2020-10-15 | 2022-04-19 | 国网江苏省电力有限公司 | System protection intelligent analysis system and method based on load aggregation management platform |
| CN112365083B (en) * | 2020-11-26 | 2024-08-20 | 深圳供电局有限公司 | Power load prediction method and system |
| CN112488418A (en) * | 2020-12-14 | 2021-03-12 | 中国南方电网有限责任公司 | Full-topology load prediction method and device and computer equipment |
| CN112488418B (en) * | 2020-12-14 | 2023-09-26 | 中国南方电网有限责任公司 | Full topology load prediction method and device and computer equipment |
| CN112696728A (en) * | 2021-01-22 | 2021-04-23 | 北京嘉洁能科技股份有限公司 | Control system for balancing electric load and reducing electric capacity increase |
| CN113326897A (en) * | 2021-06-25 | 2021-08-31 | 国网冀北电力有限公司承德供电公司 | Temperature measurement plan generation method and device for overhead transmission line and electronic equipment |
| CN113887809A (en) * | 2021-10-11 | 2022-01-04 | 国网新疆电力有限公司巴州供电公司 | Power distribution network supply and demand balance method, system, medium and computing equipment under double-carbon target |
| CN113919572A (en) * | 2021-10-14 | 2022-01-11 | 国网信息通信产业集团有限公司 | Load prediction method, device and system |
| CN113780901A (en) * | 2021-11-10 | 2021-12-10 | 国网江苏省电力有限公司营销服务中心 | Network load cooperative control method applied to energy controller |
| CN114118580A (en) * | 2021-11-29 | 2022-03-01 | 国网山东省电力公司东营供电公司 | Yellow river basin pollution source monitoring and early warning method based on electric power-environmental protection data fusion analysis |
| CN114169637B (en) * | 2021-12-21 | 2022-09-27 | 天纳能源科技（上海）有限公司 | Energy-saving optimization evaluation system |
| CN114169637A (en) * | 2021-12-21 | 2022-03-11 | 天纳能源科技（上海）有限公司 | Energy-saving optimization evaluation system |
| CN114662043A (en) * | 2022-05-25 | 2022-06-24 | 广东电网有限责任公司佛山供电局 | Real-time evaluation method for user load response condition and related device thereof |
| CN116151509A (en) * | 2023-02-13 | 2023-05-23 | 国家电投集团数字科技有限公司 | Power information management method and system based on data fusion |
| CN116979531A (en) * | 2023-09-25 | 2023-10-31 | 山西京能售电有限责任公司 | Novel energy data monitoring method and method for monitoring auxiliary power market |
| CN116979531B (en) * | 2023-09-25 | 2023-12-12 | 山西京能售电有限责任公司 | Novel energy data monitoring method and method for monitoring auxiliary power market |
| CN117132420B (en) * | 2023-10-27 | 2024-02-27 | 国网湖北省电力有限公司营销服务中心(计量中心) | Response characteristic analysis method and system of power demand response object |
| CN117132420A (en) * | 2023-10-27 | 2023-11-28 | 国网湖北省电力有限公司营销服务中心(计量中心) | Response characteristic analysis method and system of power demand response object |
| CN117335416A (en) * | 2023-11-24 | 2024-01-02 | 国网浙江省电力有限公司 | Method, device, equipment and storage medium for optimizing power load |
| CN117335416B (en) * | 2023-11-24 | 2024-03-01 | 国网浙江省电力有限公司 | Method, device, equipment and storage medium for optimizing power load |
| CN117293829B (en) * | 2023-11-27 | 2024-02-20 | 国网湖北省电力有限公司 | Power peak shaving method based on 5G and 4G short sharing double-network mutual authentication wireless communication |
| CN117293829A (en) * | 2023-11-27 | 2023-12-26 | 国网湖北省电力有限公司 | Power peak shaving method based on 5G and 4G short sharing double-network mutual authentication wireless communication |
| CN117424231A (en) * | 2023-12-14 | 2024-01-19 | 深圳市华星数字有限公司 | Energy-saving power distribution control system and method |
| CN117424231B (en) * | 2023-12-14 | 2024-03-15 | 深圳市华星数字有限公司 | Energy-saving power distribution control system and method |
| CN118195286A (en) * | 2024-05-20 | 2024-06-14 | 成都秦川物联网科技股份有限公司 | Energy management method based on industrial Internet of things, internet of things system and equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106651200A (en) | Electrical load management method and system for industrial enterprise aggregate user | |
| Lin et al. | An improved moth-flame optimization algorithm for support vector machine prediction of photovoltaic power generation | |
| Dong et al. | Wind power day-ahead prediction with cluster analysis of NWP | |
| Reynolds et al. | Upscaling energy control from building to districts: Current limitations and future perspectives | |
| CN103390116B (en) | Use the photovoltaic power station power generation power forecasting method of stepping mode | |
| Shi et al. | Hybrid forecasting model for very-short term wind power forecasting based on grey relational analysis and wind speed distribution features | |
| CA2964806C (en) | Forecasting net load in a distributed utility grid | |
| CN105590174A (en) | Enterprise power consumption load prediction method based on K-means clustering RBF neural network | |
| CN109670627A (en) | Method for controlling the automatic cloud of energy storage system | |
| CN102184453A (en) | Wind power combination predicting method based on fuzzy neural network and support vector machine | |
| US11070058B2 (en) | Forecasting net load in a distributed utility grid | |
| CN104899665A (en) | Wind power short-term prediction method | |
| CN104008432A (en) | Micro-grid short-term load forecasting method based on EMD-KELM-EKF | |
| EP3343496A1 (en) | Method and system for energy management in a facility | |
| CN103093288A (en) | Partition power grid bus load prediction system based on weather information | |
| Liu et al. | Edge sensing data-imaging conversion scheme of load forecasting in smart grid | |
| Lin et al. | A hybrid short-term load forecasting approach for individual residential customer | |
| CN104123595A (en) | Power distribution network load prediction method and system | |
| CN116128094A (en) | Industrial park energy management system and method based on digital twinning | |
| CN112950001B (en) | Intelligent energy management and control system and method based on cloud edge closed-loop architecture | |
| Long et al. | Research on energy-efficiency building design based on bim and artificial intelligence | |
| CN108346009A (en) | A kind of power generation configuration method and device based on user model self study | |
| Fan et al. | Study on load monitoring and demand side management strategy based on Elman neural network optimized by sparrow search algorithm | |
| CN110135617A (en) | A kind of prediction technique of improvement short term under meteorological factor influence based on part throttle characteristics | |
| CN109934396A (en) | A kind of regional network for the load fining prediction technique based on two stages reduction |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170510 |