CN109390938A - A kind of Itellectualized uptown Demand-side short-term load forecasting method and its device - Google Patents

A kind of Itellectualized uptown Demand-side short-term load forecasting method and its device Download PDF

Info

Publication number
CN109390938A
CN109390938A CN201811345114.4A CN201811345114A CN109390938A CN 109390938 A CN109390938 A CN 109390938A CN 201811345114 A CN201811345114 A CN 201811345114A CN 109390938 A CN109390938 A CN 109390938A
Authority
CN
China
Prior art keywords
power load
smoothing
time series
power
moment
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
Application number
CN201811345114.4A
Other languages
Chinese (zh)
Inventor
于波
孙学文
王翠敏
卢欣
李民
吴明雷
孙哲
杨延春
韩慎朝
吴亮
刘裕德
石枫
朱伯苓
张超
郭晓丹
隋淑慧
陈彬
王海巍
张凡
曹晓男
蔡林静
王嘉庚
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
State Grid (tianjin) Integrated Energy Services Co Ltd
Tianjin Energy Saving Service Co Ltd
State Grid Corp of China SGCC
State Grid Tianjin Electric Power Co Ltd
Electric Power Research Institute of State Grid Tianjin Electric Power Co Ltd
Original Assignee
State Grid (tianjin) Integrated Energy Services Co Ltd
Tianjin Energy Saving Service Co Ltd
State Grid Corp of China SGCC
State Grid Tianjin Electric Power Co Ltd
Electric Power Research Institute of State Grid Tianjin Electric Power Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by State Grid (tianjin) Integrated Energy Services Co Ltd, Tianjin Energy Saving Service Co Ltd, State Grid Corp of China SGCC, State Grid Tianjin Electric Power Co Ltd, Electric Power Research Institute of State Grid Tianjin Electric Power Co Ltd filed Critical State Grid (tianjin) Integrated Energy Services Co Ltd
Priority to CN201811345114.4A priority Critical patent/CN109390938A/en
Publication of CN109390938A publication Critical patent/CN109390938A/en
Pending legal-status Critical Current

Links

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
    • 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
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas 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
    • H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
    • H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
    • 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
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Abstract

The present invention relates to a kind of Itellectualized uptown Demand-side short-term load forecasting method and its devices, method includes the following steps: the acquisition 24 hours one day power load data in garden；The 24 hours one day power loads in garden are fitted using time series models, obtain power load match value and trained time series models；By power load match value and actual comparison, calculates average relative error and trained time series models are verified according to average relative error；Power load situation after being predicted one day with trained time series models.The present invention is on the basis of collected historical load data, the time factor of comprehensive analyzing influence load fluctuation, Itellectualized uptown short term tendency is predicted to its modeling analysis using time series models, to formulate hair for garden dispatching of power netwoks, power supply plan provides reference frame, realizes resources regulation to system, guarantee electric energy balance between supply and demand, guarantees that power quality has important role.

Description

A kind of Itellectualized uptown Demand-side short-term load forecasting method and its device
Technical field
The invention belongs to intelligent power grid technology field, especially a kind of Itellectualized uptown Demand-side short-term load forecasting method and Its device.
Background technique
The electro-load forecast of garden is the important link in Power System Planning, and what load forecast needed to solve Be by electric energy can not Mass storage bring electric energy balance between supply and demand problem, and then guarantee power supply quality.With electrical energy pipe The development of reason system (EMS), short-term load forecasting have become one of necessary links of EMS, for the safety for ensureing electric system Economical operation provides support, is mainly used for optimizing Unit Commitment, water power plan, hydro thermal coordination and exchange power planning.It is logical The accurate prediction to short-term electric load is crossed, hair can be formulated for dispatching of power netwoks, power supply plan provides reference frame, and ensures electricity The electric energy equilibrium of supply and demand in net can provide data to production, conveying, distribution and the sale of estimation electric energy and support, make power train System can formulate more economical, reasonable hair, power program, realize energy control, the target of energy-saving and emission-reduction.How to garden Demand-side It is problem in the urgent need to address at present that short-term load forecasting, which carries out accurate prediction,.
Summary of the invention
It is an object of the invention to overcome the deficiencies in the prior art, propose that a kind of design is reasonable and the accurate intelligent garden of prediction Area's Demand-side short-term load forecasting method and its device.
The present invention solves its technical problem and adopts the following technical solutions to achieve:
A kind of Itellectualized uptown Demand-side short-term load forecasting method, comprising the following steps:
Step 1: the acquisition 24 hours one day power load data in garden；
Step 2: being fitted the 24 hours one day power loads in garden using time series models, obtain power load match value And trained time series models；
Step 3: the power load match value and actual comparison that step 2 is obtained calculate average relative error and basis Average relative error verifies trained time series models；
Step 4: the power load situation after being predicted one day using the trained time series models of step 2.
Further, the step 2 is fitted the 24 hours one day power loads in garden using time series models.
Further, the time series models that the step 2 uses are as follows:
In formula,Respectively single exponential smoothing, double smoothing and Three-exponential Smoothing t when The power load match value at quarter, α are smoothing factor,Respectively single exponential smoothing, double smoothing And the power load match value at Three-exponential Smoothing t-1 moment.
Further, the value of the smoothing factor α is 0.1~0.3.
Further, the average relative error in the step 3 is calculated according to following formula:
In formula,For the power load match value of Three-exponential Smoothing t moment, ytIt is practical for the power load of t moment Value.
Further, the prediction technique of the step 4 is calculated according to following formula:
In formula, ytFor the power load actual value of t moment, T indicates to predict advanced period, at、bt、ctIt is flat for index three times The related coefficient of sliding prediction model；Respectively single exponential smoothing, double smoothing and refer to three times The power load match value of the smooth t moment of number, α is smoothing factor.
A kind of device for realizing Itellectualized uptown Demand-side short-term load forecasting method, including following module:
Power load data acquisition module: the acquisition 24 hours one day power load data in garden；
Power load data fitting module: the fitting 24 hours one day power loads in garden obtain power load match value And trained time series models；
Average relative error computing module: by power load match value and actual comparison, average relative error is calculated simultaneously Trained time series models are verified according to average relative error；
Electro-load forecast module: the power load situation after being predicted one day using trained time series models.
Further, the power load data fitting module uses following time series models:
In formula,Respectively single exponential smoothing, double smoothing and Three-exponential Smoothing t when The power load match value at quarter, α are smoothing factor,Respectively single exponential smoothing, double smoothing And the power load match value at Three-exponential Smoothing t-1 moment.
Further, the average relative error computing module uses following computation model:
In formula,For the power load match value of Three-exponential Smoothing t moment, ytIt is practical for the power load of t moment Value.
Further, the electro-load forecast module uses following prediction model:
In formula, ytFor the power load actual value of t moment, T indicates to predict advanced period, at、bt、ctIt is flat for index three times The related coefficient of sliding prediction model；Respectively single exponential smoothing, double smoothing and refer to three times The power load match value of the smooth t moment of number, α is smoothing factor.
The advantages and positive effects of the present invention are:
1, the present invention is on the basis of collected historical load data, time of comprehensive analyzing influence load fluctuation because Element predicts Itellectualized uptown short term tendency to its modeling analysis using time series models, to be garden dispatching of power netwoks system Fixed hair, power supply plan provide reference frame, and then effectively realize distributing rationally, balanced load, improving management efficiency for resource, Resources regulation is realized to system, guarantee electric energy balance between supply and demand, guarantees that power quality has important role.
2, the time series models that the present invention uses have very strong stability and systematicness, think most recent past state Gesture, the influence future that can continue to a certain extent, it is only necessary to control the size of smoothing factor α, can obtain better Fitting and prediction effect relatively tally with the actual situation to the power processing such as non-of the data of different time, and prediction model can be automatic It identifies the variation of data pattern and is adjusted, method is simple and is easily achieved.
Detailed description of the invention
Fig. 1 is garden power load tendency chart；
Fig. 2 is α1Garden power load actual value and match value trend graph when=0.1；
Fig. 3 is α1Garden power load actual value and match value trend graph when=0.3；
Fig. 4 is α1Garden power load actual value and match value trend graph when=0.5.
Specific embodiment
The embodiment of the present invention is further described below in conjunction with attached drawing.
Itellectualized uptown Demand-side short-term load forecasting method of the invention, includes the following steps:
Step 1: acquiring certain 24 hours one day power load data in garden, and observe its tendency situation, acquisition data are such as Shown in table 1.
1 garden of table, 24 hours power load data (× 103kW)
According to the garden power load situation of table 1, it is as shown in Figure 1 to draw its trend graph.It will be seen from figure 1 that garden one It power load substantially parabolically trend, peak times of power consumption between 10:00-14:00, when power load is presented very strong Intersexuality, this plays certain directive function to the selection of prediction model.Time series models have very strong stability and rule Property, think most recent past situation, it the influence future that can continue to a certain extent, can be with by the selection of smoothing factor α Reach this purpose.
Step 2: using time series models be fitted the 24 hours power loads in garden, obtain power load match value and Trained time series models model.
In this step, the time series models are calculated according to following formula:
In formula,Respectively single exponential smoothing, double smoothing and Three-exponential Smoothing t when The power load match value at quarter, α are smoothing factor,Respectively single exponential smoothing, double smoothing And the power load match value at Three-exponential Smoothing t-1 moment.
In addition, smoothing factor α value interval is [0,1], selecting suitable weighting coefficient α is the key that improve precision of prediction Place, wherein α value is bigger, and weighting coefficient Aftershock decay speed is faster, so actually α value size plays control participation averagely Historical data number effect, according to " new data gives biggish flexible strategy, and legacy data gives lesser flexible strategy " principle, Here α is taken respectively1=0.1, α2=0.3, α3=0.5 is predicted, and according to the suitable smooth system of average relative error selection Number.
α is successively calculated according to Three-exponential Smoothing model1=0.1, α2=0.3 and α3It is primary when=0.5, secondary, refer to three times Number smooth value, table 2 give α1It is when=0.1 as a result, α2=0.3 and α3=0.5 result can similarly calculate.
Table 2 is primary, secondary, Three-exponential Smoothing value
Actual value and match value and average relative error are as shown in table 3 under different smoothing factor α, and trend graph is respectively as schemed 2, shown in 3,4.
The 3 24 hours power loads in garden (× 10 of table3KW) match value and average relative error
Step 3: the power load match value and actual comparison that time series models will be used to obtain calculate average opposite Error simultaneously verifies trained time series models according to average relative error.
In this step, average relative error is calculated according to following formula:
The size of ε reflects the accuracy of time series models fitting garden power load, and ε is smaller, illustrates time series The match value of model more can approach actual value well, can be very good the feasibility for illustrating model.It is small according to garden 24 in table 3 When power load match value combine the value of the average relative error ε under the available different smoothing factor α of above-mentioned calculation formula, As shown in table 3.As can be seen from Table 3, when α=0.1, ε=13%, average relative error is minimum, can also see in conjunction with Fig. 2,3,4 Out when α=0.1, models fitting effect is best, therefore the model that can choose α=0.1 carries out the prediction of next step.
This step, for judging fitting effect, judges that fitting effect is the standard in order to verify model according to average relative error True property.Due to establishing a model, some indexs are needed certainly to judge its reasonability, and for this prediction model, pass through The deviation of its predicted value and actual value judges that reasonability is most simple direct effective means.
Step 4: the power load situation after being predicted one day using the trained time series models of step 2.
Periodicity is t=25 at present, data related in table 2 is substituted into model, calculate Nonlinear Prediction Models is Number at、bt、ct。
The prediction model of third index flatness are as follows:
a25=3 × 2.75-3 × 2.85+2.88=2.7
Establish Nonlinear Prediction Models:
It predicts subsequent time garden power load, predicts that the advanced period is that (T indicates to predict advanced period, T=0 T=1 Indicating that predicted value is second day 0:00, T=1 indicates that predicted value is second day 1:00, and so on), substitute into prediction model In,
The power load value of subsequent time is acquired.
The device of realization Itellectualized uptown Demand-side short-term load forecasting method of the invention, including following module:
Power load data acquisition module: the acquisition 24 hours one day power load data in garden；
Power load data fitting module: the fitting 24 hours one day power loads in garden obtain power load match value And trained time series models；The power load data fitting module uses following time series models:
In formula,Respectively single exponential smoothing, double smoothing and Three-exponential Smoothing t when The power load match value at quarter, α are smoothing factor,Respectively single exponential smoothing, double smoothing And the power load match value at Three-exponential Smoothing t-1 moment.
Average relative error computing module: by power load match value and actual comparison, average relative error is calculated simultaneously Trained time series models are verified according to average relative error；The average relative error computing module calculates mould using following Type:
In formula,For the power load match value of Three-exponential Smoothing t moment, ytIt is practical for the power load of t moment Value.
Electro-load forecast module: the power load situation after being predicted one day using trained time series models. The electro-load forecast module uses following prediction model:
In formula, ytFor the power load actual value of t moment, T indicates to predict advanced period, at、bt、ctIt is flat for index three times The related coefficient of sliding prediction model；Respectively single exponential smoothing, double smoothing and refer to three times The power load match value of the smooth t moment of number, α is smoothing factor.
It is emphasized that embodiment of the present invention be it is illustrative, without being restrictive, therefore packet of the present invention Include and be not limited to embodiment described in specific embodiment, it is all by those skilled in the art according to the technique and scheme of the present invention The other embodiments obtained, also belong to the scope of protection of the invention.

Claims (10)

1. a kind of Itellectualized uptown Demand-side short-term load forecasting method, it is characterised in that the following steps are included:
Step 1: the acquisition 24 hours one day power load data in garden；
Step 2: the fitting 24 hours one day power loads in garden obtain power load match value and trained time series mould Type；
Step 3: the power load match value and actual comparison that step 2 is obtained calculate average relative error and according to average Relative error verifies trained time series models；
Step 4: the power load situation after being predicted one day using the trained time series models of step 3.
2. a kind of Itellectualized uptown Demand-side short-term load forecasting method according to claim 1, it is characterised in that: the step Rapid 2 are fitted the 24 hours one day power loads in garden using time series models.
3. a kind of Itellectualized uptown Demand-side short-term load forecasting method according to claim 2, it is characterised in that: when described Between series model be calculated as follows:
In formula,Respectively single exponential smoothing, double smoothing and Three-exponential Smoothing t moment Power load match value, α are smoothing factor,Respectively single exponential smoothing, double smoothing and The power load match value at Three-exponential Smoothing t-1 moment.
4. a kind of transforming plant primary equipment breakdown judge according to claim 3 and processing decision system, it is characterised in that: The value of the smoothing factor α is 0.1~0.3.
5. a kind of Itellectualized uptown Demand-side short-term load forecasting method according to claim 1, it is characterised in that: the step Average relative error in rapid 3 is calculated according to following formula:
In formula,For the power load match value of Three-exponential Smoothing t moment, ytFor the power load actual value of t moment.
6. a kind of Itellectualized uptown Demand-side short-term load forecasting method according to claim 1, it is characterised in that: the step Rapid 4 prediction technique is calculated according to following formula:
In formula, ytFor the power load actual value of t moment, T indicates to predict advanced period, at、bt、ctFor Three-exponential Smoothing prediction The related coefficient of model；Respectively single exponential smoothing, double smoothing and Three-exponential Smoothing t The power load match value at moment, α are smoothing factor.
7. a kind of device for realizing the Itellectualized uptown Demand-side short-term load forecasting method as described in any one of claim 1 to 6, It is characterized in that: including following module:
Power load data acquisition module: the acquisition 24 hours one day power load data in garden；
Power load data fitting module: the fitting 24 hours one day power loads in garden obtain power load match value and instruction The time series models perfected；
Average relative error computing module: by power load match value and actual comparison, average relative error and basis are calculated Average relative error verifies trained time series models；
Electro-load forecast module: the power load situation after being predicted one day using trained time series models.
8. a kind of device for realizing Itellectualized uptown Demand-side short-term load forecasting method according to claim 7, feature Be: the power load data fitting module uses following time series models:
In formula,Respectively single exponential smoothing, double smoothing and Three-exponential Smoothing t moment Power load match value, α are smoothing factor,Respectively single exponential smoothing, double smoothing and The power load match value at Three-exponential Smoothing t-1 moment.
9. a kind of device for realizing Itellectualized uptown Demand-side short-term load forecasting method according to claim 8, feature Be: the average relative error computing module uses following computation model:
In formula,For the power load match value of Three-exponential Smoothing t moment, ytFor the power load actual value of t moment.
10. a kind of device for realizing Itellectualized uptown Demand-side short-term load forecasting method according to claim 7, feature Be: the electro-load forecast module uses following prediction model:
In formula, ytFor the power load actual value of t moment, T indicates to predict advanced period, at、bt、ctFor Three-exponential Smoothing prediction The related coefficient of model；Respectively single exponential smoothing, double smoothing and Three-exponential Smoothing t The power load match value at moment, α are smoothing factor.
CN201811345114.4A 2018-11-13 2018-11-13 A kind of Itellectualized uptown Demand-side short-term load forecasting method and its device Pending CN109390938A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201811345114.4A CN109390938A (en) 2018-11-13 2018-11-13 A kind of Itellectualized uptown Demand-side short-term load forecasting method and its device

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201811345114.4A CN109390938A (en) 2018-11-13 2018-11-13 A kind of Itellectualized uptown Demand-side short-term load forecasting method and its device

Publications (1)

Publication Number Publication Date
CN109390938A true CN109390938A (en) 2019-02-26

Family

ID=65428625

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201811345114.4A Pending CN109390938A (en) 2018-11-13 2018-11-13 A kind of Itellectualized uptown Demand-side short-term load forecasting method and its device

Country Status (1)

Country Link
CN (1) CN109390938A (en)

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101976841A (en) * 2010-10-21 2011-02-16 河北省电力研究院 Balance matching method for all classes of load forecasting indexes of power system
CN102855343A (en) * 2011-06-10 2013-01-02 阿自倍尔株式会社 Capacity prediction device, capacity prediction method, and capacity prediction program
JP2014165934A (en) * 2013-02-21 2014-09-08 Central Research Institute Of Electric Power Industry Method, device and program for estimating variation of total power generation output from natural energy type distributed power source group
CN106779147A (en) * 2016-11-18 2017-05-31 重庆邮电大学 A kind of electro-load forecast method based on self adaptation level Time Series Clustering
CN107453396A (en) * 2017-08-02 2017-12-08 安徽理工大学 A kind of Multiobjective Optimal Operation method that distributed photovoltaic power is contributed

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101976841A (en) * 2010-10-21 2011-02-16 河北省电力研究院 Balance matching method for all classes of load forecasting indexes of power system
CN102855343A (en) * 2011-06-10 2013-01-02 阿自倍尔株式会社 Capacity prediction device, capacity prediction method, and capacity prediction program
JP2014165934A (en) * 2013-02-21 2014-09-08 Central Research Institute Of Electric Power Industry Method, device and program for estimating variation of total power generation output from natural energy type distributed power source group
CN106779147A (en) * 2016-11-18 2017-05-31 重庆邮电大学 A kind of electro-load forecast method based on self adaptation level Time Series Clustering
CN107453396A (en) * 2017-08-02 2017-12-08 安徽理工大学 A kind of Multiobjective Optimal Operation method that distributed photovoltaic power is contributed

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
张君: "基于梯度优化自适应指数平滑法的风电场短期风速预测方法研究", 《机电工程》 *

Similar Documents

Publication Publication Date Title
CN109508857B (en) Multi-stage planning method for active power distribution network
Saleh et al. Load aggregation from generation-follows-load to load-follows-generation: Residential loads
CN102074954B (en) Comprehensive energy-conservation evaluation and decision-making method for urban and rural distribution network
CN103150600B (en) A kind of power grid security analysis system
CN107895971A (en) Regional Energy internet dispatching method based on stochastic programming and Model Predictive Control
CN101813941B (en) Energy efficiency optimizing and dispatching system for cold, heat and electricity triple supply equipment
CN103942613B (en) Method for grid and province two-stage real-time generation schedule coordinative optimization under generalized tie line mode
CN111340299B (en) Multi-objective optimal scheduling method for micro-grid
CN106532751B (en) A kind of distributed generation resource efficiency optimization method and system
CN104537428B (en) One kind meter and the probabilistic economical operation appraisal procedure of wind power integration
CN102184453A (en) Wind power combination predicting method based on fuzzy neural network and support vector machine
CN112952805A (en) Electric hydrogen energy system scheduling method considering flexible hydrogen demand
CN103390116A (en) Method for predicting electricity generation power of photovoltaic power station in step-by-step way
CN102938093A (en) Wind power forecasting method
CN107276069A (en) Approximate the polymerization modeling method and system of a kind of area power grid resident temperature control load
CN109272353B (en) System dynamic probability energy flow analysis method considering comprehensive demand response uncertainty
CN108182485A (en) A kind of power distribution network maintenance opportunity optimization method and system
CN103116814B (en) A kind of area power grid main equipment medium term load forecasting system
CN109412148A (en) The translatable load model construction method of meter and Environmental costs and Spot Price
Du et al. A microgrid energy management system with demand response
CN106447132A (en) A medium-and-long term generating capacity prediction method for a regional photovoltaic power station group
CN106485603A (en) A kind of short-term wind speed forecasting method being applied to wind-power electricity generation
CN113935856A (en) Method and device for controlling electric energy, processor and computer readable storage medium
CN108921368A (en) Balanced cooperative game controller based on virtual power plant
CN111178618A (en) Intelligent power grid load prediction method

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
CB02 Change of applicant information
CB02 Change of applicant information

Address after: 300452 209 (TG no.750), 2nd floor, animation building C, No.126, animation Middle Road, eco city, Binhai New Area, Tianjin

Applicant after: STATE GRID (TIANJIN) INTEGRATION ENERGY SERVICE Co.,Ltd.

Applicant after: ELECTRIC POWER SCIENCE & RESEARCH INSTITUTE OF STATE GRID TIANJIN ELECTRIC POWER Co.

Applicant after: STATE GRID TIANJIN ENERGY SAVING SERVICE CO.,LTD.

Applicant after: STATE GRID TIANJIN ELECTRIC POWER Co.

Applicant after: STATE GRID CORPORATION OF CHINA

Address before: 300384 Tianjin city Xiqing District Road No. 8 four Haitai branch

Applicant before: ELECTRIC POWER SCIENCE & RESEARCH INSTITUTE OF STATE GRID TIANJIN ELECTRIC POWER Co.

Applicant before: STATE GRID (TIANJIN) INTEGRATION ENERGY SERVICE Co.,Ltd.

Applicant before: STATE GRID TIANJIN ENERGY SAVING SERVICE Co.,Ltd.

Applicant before: STATE GRID TIANJIN ELECTRIC POWER Co.

Applicant before: STATE GRID CORPORATION OF CHINA

RJ01 Rejection of invention patent application after publication
RJ01 Rejection of invention patent application after publication

Application publication date: 20190226