CN110675275B - Electric load regulation and control method and system for demand side response application of virtual power plant - Google Patents
Electric load regulation and control method and system for demand side response application of virtual power plant Download PDFInfo
- Publication number
- CN110675275B CN110675275B CN201910837278.7A CN201910837278A CN110675275B CN 110675275 B CN110675275 B CN 110675275B CN 201910837278 A CN201910837278 A CN 201910837278A CN 110675275 B CN110675275 B CN 110675275B
- Authority
- CN
- China
- Prior art keywords
- power
- power generation
- data
- historical
- load
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 230000004044 response Effects 0.000 title claims abstract description 19
- 238000010248 power generation Methods 0.000 claims abstract description 122
- 230000005611 electricity Effects 0.000 claims abstract description 28
- 230000001105 regulatory effect Effects 0.000 claims abstract description 16
- 230000001276 controlling effect Effects 0.000 claims abstract description 13
- 230000006870 function Effects 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 12
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 claims description 10
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 3
- 238000009826 distribution Methods 0.000 abstract description 9
- 238000013528 artificial neural network Methods 0.000 description 7
- 238000005516 engineering process Methods 0.000 description 3
- 230000002159 abnormal effect Effects 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000012706 support-vector machine Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 238000005311 autocorrelation function Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000002146 bilateral effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005291 chaos (dynamical) Methods 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 238000005314 correlation function Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 238000013213 extrapolation Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012417 linear regression Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 210000002569 neuron Anatomy 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000013112 stability test Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000012360 testing method 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
- 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
-
- 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
- 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A30/00—Adapting or protecting infrastructure or their operation
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/90—Financial instruments for climate change mitigation, e.g. environmental taxes, subsidies or financing
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Public Health (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention provides a method and a system for regulating and controlling electric loads for demand side response application of a virtual power plant, wherein the method comprises the following steps: acquiring the power generation internet price of renewable energy sources, the power generation government subsidy price of renewable energy sources and the user side electricity price information in real time; acquiring time data of a day to be predicted and corresponding meteorological data; predicting power load data and renewable energy power generation output according to the time data and the corresponding meteorological data; and regulating and controlling the power output of the renewable energy according to the power generation internet price of the renewable energy, the power generation government subsidy price of the renewable energy, the user side electricity price information, the power load data and the power generation output power of the renewable energy. The invention provides the accuracy of load and renewable energy output power prediction, and realizes the reasonable control of partial load in the active power distribution network.
Description
Technical Field
The invention relates to the technical field of power load regulation and control, in particular to a method and a system for regulating and controlling power load for demand side response of a virtual power plant.
Background
Under the large background of the reform of the electric power market, electric power gradually returns to commodity attributes, and the electricity price also fluctuates in real time, namely the fluctuation of the electricity price can influence the size of a load, and the fluctuation of the load also can influence the size of the electricity price, so that the electricity price and the electricity price are balanced in the mutual influence process. The load prediction of the power system is the basic work of the power system for scheduling operation and production planning, the load prediction relates to the safe and stable operation of the power system, and the load prediction has immeasurable effect on actual production and life.
On the premise of not changing the existing topological structure of the power grid, the control coordination center aggregates different types of power sources such as distributed power sources, energy storage systems, network-accessible electric vehicles and the like through an advanced coordination control technology, an intelligent metering technology and an information communication technology based on power generation prediction and load prediction, and realizes coordinated and optimized operation of multiple distributed energy sources through an upper software algorithm, so that reasonable and optimized configuration and utilization of resources are promoted. The electric power markets in which the virtual power plant can participate include a daily market, a real-time market, a bilateral contract market, an auxiliary service market and the like, and the participation balance market can help the virtual power plant to stabilize fluctuation of renewable energy sources, reduce the risk of inaccurate output prediction of the renewable energy sources and obtain greater economic benefits.
The demand response may enable the demand side resource to be a virtual resource to participate in grid load scheduling, and the user demand response includes a price-based demand response and an incentive-based demand response. The load side resource and the power side resource are considered in combination, so that the load side scheduling and the power side scheduling are coordinated, and the method is an effective way for solving the problem of uncontrollable new energy power consumption.
The invention patent application with the application number of 201811043955.X and the name of grid load prediction method, device, computer equipment and storage medium provides a prediction model established according to historical data of similar historical days; and predicting the power grid load on the day to be predicted according to the prediction model.
Existing power load prediction researches find that the power consumption habits of users can change along with characteristic factors such as time or weather, and the power load predicted by a single fixed trained power load prediction model can become inaccurate gradually along with the characteristic factors such as time or weather.
Disclosure of Invention
The invention aims to solve the technical problem of providing a method and a system for regulating and controlling electric loads for demand side response application of a virtual power plant, so as to solve the defect that in the prior art, the influence of meteorological factors is not considered in load prediction.
In order to solve the technical problems, the invention provides a method for regulating and controlling electric load for demand side response of a virtual power plant, which comprises the following steps:
acquiring the power generation internet price of renewable energy sources, the power generation government subsidy price of renewable energy sources and the user side electricity price information in real time;
acquiring time data of a day to be predicted and corresponding meteorological data;
predicting power load data and renewable energy power generation output according to the time data and the corresponding meteorological data;
and regulating and controlling the power output of the renewable energy according to the power generation internet price of the renewable energy, the power generation government subsidy price of the renewable energy, the user side electricity price information, the power load data and the power generation output power of the renewable energy.
The method for predicting the power load data and the renewable energy power generation output power according to the time data and the corresponding meteorological data specifically comprises the following steps:
substituting the time data of the day to be predicted and the corresponding meteorological data into a constructed power load prediction model to obtain a predicted value of the power load;
substituting the time data of the day to be predicted and the corresponding meteorological data into a constructed wind power generation output power prediction model to obtain a wind power generation output power prediction value;
substituting the time data of the day to be predicted and the corresponding meteorological data into a constructed photovoltaic power generation output power prediction model to obtain the photovoltaic power generation output power prediction value.
The construction of the power load prediction model specifically comprises the following steps:
acquiring historical power load data of a user side, and time data and historical meteorological data corresponding to the historical power load data;
processing the time data and the historical meteorological data to obtain processed historical time data and historical meteorological data;
and training power load prediction by using the processed historical time data, the historical meteorological data and the historical power load data corresponding to the historical time data, so as to obtain a power load prediction model.
The power load prediction model adopts a radial basis function neural network and an extreme learning machine method to combine and predict.
The method for constructing the wind power generation output power prediction model specifically comprises the following steps:
acquiring historical data of wind power generation output power, historical time data and historical meteorological data of the wind power generation output power;
processing the historical time data and the historical meteorological data of the wind power generation output power to obtain processed wind power generation output power data and corresponding historical time data and historical meteorological data;
and training a wind power generation prediction model by using the processed wind power generation output power data and the historical meteorological data to obtain the wind power generation output power prediction model.
The wind power generation output power prediction model and the photovoltaic power generation output power prediction model adopt ARIMA (p, q) models.
The invention also provides an electric load regulation and control system for demand side response of the virtual power plant, which comprises the following components:
the price acquisition module is used for acquiring the power generation internet price of the renewable energy source, the power generation government subsidy price of the renewable energy source and the user side electricity price information in real time;
the day information acquisition module to be detected is used for acquiring time data of a day to be predicted and corresponding meteorological data;
the prediction module is used for predicting power load data and renewable energy source power generation output according to the time data and the corresponding meteorological data;
the regulation and control module is used for regulating and controlling the power load of the user side according to the power generation internet price of the renewable energy source, the power generation government subsidy price of the renewable energy source, the user side power price information, the power load data and the power generation output power of the renewable energy source.
Wherein the prediction module comprises:
the power load prediction module is used for substituting the time data of the day to be predicted and the corresponding meteorological data into a constructed power load prediction model to obtain a predicted value of the power load;
the wind power generation output power prediction module is used for substituting the time data of the day to be predicted and the corresponding meteorological data into a constructed wind power generation output power prediction model to obtain a wind power generation output power prediction value;
and the photovoltaic power generation output power prediction module is used for substituting the time data of the day to be predicted and the corresponding meteorological data into the constructed photovoltaic power generation output power prediction model to obtain the photovoltaic power generation output power prediction value.
The power load prediction model adopts a radial basis function neural network and an extreme learning machine method to combine and predict.
The wind power generation output power prediction model and the photovoltaic power generation output power prediction model adopt ARIMA (p, q) models.
The embodiment of the invention has the beneficial effects that: in addition, after the user responds to the electricity price strategy, the electricity consumption is allowed to be interrupted or reduced at certain high price moments, so that the overall power balance of the system is improved; and the electricity consumption requirement is increased in certain low-price stages, so that the distribution of power distribution system resources can be improved, and the phenomena of wind abandoning and electricity abandoning are prevented. If the price incentive strategy is adjusted, the demand response distribution curve is changed along with the strategy, so that reasonable control of partial load of the active power distribution network can be realized.
Drawings
In order to more clearly illustrate the embodiments of the invention or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described, it being obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a schematic flow chart of a method for regulating and controlling an electric load for demand side response of a virtual power plant according to an embodiment of the invention.
Detailed Description
The following description of embodiments refers to the accompanying drawings, which illustrate specific embodiments in which the invention may be practiced.
An embodiment of the present invention provides a method for regulating and controlling an electric load for demand side response of a virtual power plant, which includes the following steps:
s1, acquiring the power generation internet price of renewable energy sources, the power generation government subsidy price of renewable energy sources and the user side electricity price information in real time.
Specifically, the wind power generation internet price, the photovoltaic power generation internet price, the wind power generation government subsidy price, the photovoltaic power generation government subsidy price and the real-time electricity price of a user are obtained in real time.
S2, acquiring time data of a day to be predicted and corresponding meteorological data.
And S3, predicting power load data and renewable energy source power generation output power according to the time data and the corresponding meteorological data.
In one specific embodiment, the predicting the power load data and the renewable energy power generation output according to the time data and the corresponding meteorological data specifically includes:
substituting the time data of the day to be predicted and the corresponding meteorological data into a constructed power load prediction model to obtain a predicted value of the power load; substituting the time data of the day to be predicted and the corresponding meteorological data into a constructed wind power generation output power prediction model to obtain a wind power generation output power prediction value; substituting the time data of the day to be predicted and the corresponding meteorological data into a constructed photovoltaic power generation output power prediction model to obtain the photovoltaic power generation output power prediction value.
In one embodiment, constructing the electrical load prediction model specifically includes: acquiring historical power load data of a user side, and time data and historical meteorological data corresponding to the historical power load data; processing the time data and the historical meteorological data, for example, after obtaining the historical power load data, processing the time of the historical power load data and the abnormal value in the corresponding historical meteorological data, including deleting the historical time data with the abnormal value and the corresponding historical meteorological data, so as to obtain processed historical time data and historical meteorological data; and training power load prediction by using the processed historical time data, the historical meteorological data and the historical power load data corresponding to the historical time data, so as to obtain a power load prediction model.
In order to improve the accuracy of the prediction of the power load prediction model, the power load prediction model adopts one of a space load prediction method, a power elastic coefficient method, a human power consumption method, a power generation unit consumption method, a load density method, a unit consumption method, a trend extrapolation method, a time sequence method, a regression analysis method, an autoregressive moving average method, a neural network method, a support vector machine, a fuzzy set theory, a chaos theory, wavelet analysis, a gray system theory, machine learning, a genetic algorithm or an expert system method, or adopts two or more of the above methods to respectively predict, and then carries out weighted average on the prediction result.
Taking a radial basis function neural network and an extreme learning machine method as an example, the combination prediction is as follows: firstly, training a model network by utilizing massive power load historical data acquired by a data acquisition module, secondly, inputting a load influence factor influence weight characteristic value into a trained model, and then predicting future power loads according to the model. And calculating characteristic factors such as historical load, daily average air temperature, daily temperature difference, holiday type, month number and days and the like of the same week in actual work.
The training network model of the proposed method is expressed as:
wherein alpha is i =[α i1 ,α i2 ,...,α in ]For connecting the connection weight between the kernel function and the output layer, n represents the number of the connection weight;for the output of the ith kernel function, N refers to the number of kernel functions, f N (x) Refers to the output of the training model network.
The prediction model is
Wherein y is a predicted value, H is an hidden layer matrix, H T Is the transpose of the H matrix, lambda is the scale factor, T is the time variable, and N is the number of kernel functions.
The prediction performance parameter, namely the prediction result error err is:
wherein y is i The power load predicted value of the ith day is obtained through a predicted model of the ith day; t is t i Is y i And K is the predicted days according to the corresponding actual value of the power load.
The prediction steps are as follows:
step 1: giving N training sets, and M neurons of a radial basis function neural network;
step 2: setting the center of the kernel function and the center influence width;
step 3: calculating hidden layer matrix H and matrix H generalized inverse matrix H + ;
Step 4: calculating the weight of an output layer;
step 5: inputting a test set to obtain a prediction result, and calculating an error of a training set;
step 6: and obtaining an optimal prediction result.
In a specific embodiment, the constructing the wind power generation output power prediction model specifically includes: acquiring historical data of wind power generation output power, historical time data and historical meteorological data of the wind power generation output power; processing the historical time data and the historical meteorological data of the wind power generation output power to obtain processed wind power generation output power data and corresponding historical time data and historical meteorological data; and training a wind power generation prediction model by using the processed wind power generation output power data and the historical meteorological data to obtain the wind power generation output power prediction model.
The output power of the distributed renewable energy sources such as wind power generation, photovoltaic power generation and the like can be predicted by adopting an ARIMA model, a neural network, a support vector machine, a multiple linear regression and other algorithms.
Wherein the ARIMA (p, q) model is
Wherein x is t For the output power sample value, u t Is a zero-mean white noise sequence, p is an autoregressive order, q is a moving average order,is an Autoregressive (AR) coefficient, θ i Is the running average (MA) coefficient.
The prediction method comprises the following steps:
step 1: carrying out stability test on the original data;
step 2: the value of the order (p, q) and the number of differences d of the corresponding ARIMA model are determined.
Step 3: and estimating ARIMA model parameters by adopting a least square method. In ARIMA, record
The residual term is
Δx t =x t -f i (x,a)
When Deltax t And a is the least squares parameter estimate when the sum of squares is at a minimum.
Step 4: and checking whether the model is reasonable or not by performing a residual sequence autocorrelation function and a partial correlation function.
Step 5: the model is determined through model type identification, order determination, parameter estimation, inspection and the like, and output power prediction of distributed renewable energy sources such as electric wind power generation, photovoltaic power generation and the like is performed.
S4, regulating and controlling the output power of the renewable energy according to the power generation internet price of the renewable energy, the power generation government subsidy price of the renewable energy, the power price information of the user, the power load data and the power generation output power of the renewable energy.
Specifically, the electricity price is macroscopically regulated and controlled according to the national policy, the time-sharing electricity price is adopted, the electricity consumption is allowed to be interrupted or reduced at the high price time, the electricity demand is increased at the low price time, and the output power of distributed renewable energy sources such as wind power generation, photovoltaic power generation and the like is regulated and controlled by combining the predicted data of the power load data.
According to the electric load regulation and control method for the demand side response of the virtual power plant, provided by the embodiment of the invention, meteorological factors are considered in the process of predicting the electric load of a user and the power output of renewable energy sources, so that the prediction accuracy is improved, in addition, after the user responds to an electric price strategy, the power consumption is allowed to be interrupted or reduced at certain high price moments, and the overall power balance of the system is improved; and the electricity consumption requirement is increased in certain low-price stages, so that the distribution of power distribution system resources can be improved, and the phenomena of wind abandoning and electricity abandoning are prevented. If the price incentive strategy is adjusted, the demand response distribution curve is changed along with the strategy, so that reasonable control of partial load of the active power distribution network can be realized.
Based on the first embodiment of the present invention, the second embodiment of the present invention provides an electric load regulation system for demand side response of a virtual power plant, which specifically includes:
the price acquisition module is used for acquiring the power generation internet price of the renewable energy source, the power generation government subsidy price of the renewable energy source and the user side electricity price information in real time;
the day information acquisition module to be detected is used for acquiring time data of a day to be predicted and corresponding meteorological data;
the prediction module is used for predicting power load data and renewable energy source power generation output according to the time data and the corresponding meteorological data;
the regulation and control module is used for regulating and controlling the power load of the user side according to the power generation internet price of the renewable energy source, the power generation government subsidy price of the renewable energy source, the user side power price information, the power load data and the power generation output power of the renewable energy source.
Wherein the prediction module comprises:
the power load prediction module is used for substituting the time data of the day to be predicted and the corresponding meteorological data into a constructed power load prediction model to obtain a predicted value of the power load;
the wind power generation output power prediction module is used for substituting the time data of the day to be predicted and the corresponding meteorological data into a constructed wind power generation output power prediction model to obtain a wind power generation output power prediction value;
and the photovoltaic power generation output power prediction module is used for substituting the time data of the day to be predicted and the corresponding meteorological data into the constructed photovoltaic power generation output power prediction model to obtain the photovoltaic power generation output power prediction value.
The power load prediction model adopts a radial basis function neural network and an extreme learning machine method to combine and predict.
The wind power generation output power prediction model and the photovoltaic power generation output power prediction model adopt ARIMA (p, q) models.
The foregoing disclosure is illustrative of the present invention and is not to be construed as limiting the scope of the invention, which is defined by the appended claims.
Claims (5)
1. The electric load regulation and control method for the demand side response of the virtual power plant is characterized by comprising the following steps of:
acquiring the power generation internet price of renewable energy sources, the power generation government subsidy price of renewable energy sources and the user side electricity price information in real time;
acquiring time data and meteorological data of a day to be predicted;
predicting the power load data and the renewable energy source power generation output power according to the time data and the meteorological data, and specifically comprising the following steps: substituting the time data and the meteorological data of the day to be predicted into a constructed power load prediction model to obtain a predicted value of the power load; substituting the time data and the meteorological data of the day to be predicted into a constructed wind power generation output power prediction model to obtain a wind power generation output power prediction value; substituting the time data and the meteorological data of the day to be predicted into a constructed photovoltaic power generation output power prediction model to obtain a photovoltaic power generation output power prediction value;
the method for regulating and controlling the power output of the renewable energy source according to the power generation internet price of the renewable energy source, the power generation government subsidy price of the renewable energy source, the user side power price information, the power load data and the power generation output power of the renewable energy source specifically comprises the following steps: the time-sharing electricity price is adopted, the electricity consumption is allowed to be interrupted or reduced at the high price time, the electricity consumption requirement is increased at the low price time, and the wind power generation output power and the photovoltaic power generation output power are regulated and controlled by combining the predicted value of the electric load;
the construction of the power load prediction model specifically comprises the following steps:
acquiring historical power load data of a user side, and time data and historical meteorological data corresponding to the historical power load data; processing the time data and the historical meteorological data to obtain processed historical time data and historical meteorological data; training a power load prediction model by using the processed historical time data, the historical meteorological data and the historical power load data corresponding to the historical time data, so as to obtain the power load prediction model, wherein the power load prediction model is expressed as:
wherein y is a predicted value, H is an hidden layer matrix, H T Is the transpose of the H matrix,is a scale factor, T is a time variable, N is the number of kernel functions, ++>Is->An output of the kernel function;
the prediction performance parameter, namely the prediction result error err is:
in the method, in the process of the invention,is->The predicted value of the natural electric load is obtained through a prediction model of the ith day; />Is->Corresponding actual value of the electrical load, +.>The number of days was predicted.
2. The method according to claim 1, wherein constructing a wind power generation output power prediction model specifically comprises:
acquiring historical data of wind power generation output power, historical time data and historical meteorological data of the wind power generation output power;
processing the historical time data and the historical meteorological data of the wind power generation output power to obtain processed wind power generation output power data and corresponding historical time data and historical meteorological data;
and training a wind power generation output power prediction model by using the processed wind power generation output power data and the historical meteorological data to obtain the wind power generation output power prediction model.
3. The method of claim 2, wherein the wind power generation output power prediction model and the photovoltaic power generation output power prediction model employ ARIMA (p, q) models, p being an autoregressive order, q being a moving average order.
4. An electrical load regulation system for demand side response of a virtual power plant, comprising:
the price acquisition module is used for acquiring the power generation internet price of the renewable energy source, the power generation government subsidy price of the renewable energy source and the user side electricity price information in real time;
the day information acquisition module to be detected is used for acquiring time data and meteorological data of the day to be predicted; the prediction module is used for predicting power load data and renewable energy source power generation output according to the time data and the meteorological data;
the regulation and control module is used for regulating and controlling the power load of the user side according to the power generation internet price of the renewable energy source, the power generation government subsidy price of the renewable energy source, the user side power price information, the power load data and the power generation output power of the renewable energy source;
the prediction module includes:
the power load prediction module is used for substituting the time data and the meteorological data of the day to be predicted into a constructed power load prediction model to obtain a predicted value of the power load;
the wind power generation output power prediction module is used for substituting the time data and the meteorological data of the day to be predicted into a constructed wind power generation output power prediction model to obtain a wind power generation output power prediction value;
the photovoltaic power generation output power prediction module is used for substituting the time data and the meteorological data of the day to be predicted into a constructed photovoltaic power generation output power prediction model to obtain a photovoltaic power generation output power prediction value;
the construction of the power load prediction model specifically comprises the following steps:
acquiring historical power load data of a user side, and time data and historical meteorological data corresponding to the historical power load data; processing the time data and the historical meteorological data to obtain processed historical time data and historical meteorological data; training a power load prediction model by using the processed historical time data, the historical meteorological data and the historical power load data corresponding to the historical time data, so as to obtain the power load prediction model, wherein the power load prediction model is expressed as:
wherein y is a predicted value, H is an hidden layer matrix, H T Is the transpose of the H matrix,is a scale factor, T is a time variable, N is the number of kernel functions, ++>Is->An output of the kernel function;
the prediction performance parameter, namely the prediction result error err is:
in the method, in the process of the invention,is->The predicted value of the natural electric load is obtained through a prediction model of the ith day; />Is->Corresponding actual value of the electrical load, +.>The number of days was predicted.
5. The system according to claim 4, wherein:
the wind power generation output power prediction model and the photovoltaic power generation output power prediction model adopt ARIMA (p, q) models, p is an autoregressive order, and q is a moving average order.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910837278.7A CN110675275B (en) | 2019-09-05 | 2019-09-05 | Electric load regulation and control method and system for demand side response application of virtual power plant |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910837278.7A CN110675275B (en) | 2019-09-05 | 2019-09-05 | Electric load regulation and control method and system for demand side response application of virtual power plant |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110675275A CN110675275A (en) | 2020-01-10 |
CN110675275B true CN110675275B (en) | 2023-12-05 |
Family
ID=69076518
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910837278.7A Active CN110675275B (en) | 2019-09-05 | 2019-09-05 | Electric load regulation and control method and system for demand side response application of virtual power plant |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110675275B (en) |
Families Citing this family (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111509705A (en) * | 2020-04-24 | 2020-08-07 | 明阳智慧能源集团股份公司 | Power distribution network prediction system |
CN111697570A (en) * | 2020-05-25 | 2020-09-22 | 国网河北省电力有限公司石家庄市藁城区供电分公司 | Power grid load prediction method |
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 |
CN113283659B (en) * | 2021-06-03 | 2022-11-22 | 上海分未信息科技有限公司 | Power load response task allocation method for virtual power plant |
CN113256016A (en) * | 2021-06-04 | 2021-08-13 | 广东电网有限责任公司珠海供电局 | Load prediction method and system based on virtual power plant operation |
CN114465231B (en) * | 2022-02-14 | 2023-06-13 | 南京邮电大学盐城大数据研究院有限公司 | Power access method and system for offshore wind power generation |
CN115169734B (en) * | 2022-08-01 | 2023-08-04 | 周口师范学院 | Wind power generation prediction system and method based on Internet of things |
Family Cites Families (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107742900A (en) * | 2017-11-10 | 2018-02-27 | 国网四川省电力公司技能培训中心 | Wind-light storage intelligent micro-grid economic dispatch control method |
CN108808743B (en) * | 2018-05-28 | 2020-08-21 | 华东理工大学 | Communication network-based multi-energy micro-grid energy prediction and optimal scheduling method |
-
2019
- 2019-09-05 CN CN201910837278.7A patent/CN110675275B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN110675275A (en) | 2020-01-10 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110675275B (en) | Electric load regulation and control method and system for demand side response application of virtual power plant | |
US20190265768A1 (en) | Method, system and storage medium for predicting power load probability density based on deep learning | |
Khotanzad et al. | A neuro-fuzzy approach to short-term load forecasting in a price-sensitive environment | |
CN112950098B (en) | Comprehensive energy system-based energy planning method and device and terminal equipment | |
CN112183849A (en) | Short-term electric power quantity prediction method based on artificial neural network | |
CN112926770A (en) | Unified data metering and collecting system based on digital twins | |
CN112149890A (en) | Comprehensive energy load prediction method and system based on user energy label | |
CN114140176B (en) | Adjustable capacity prediction method and device for load aggregation platform | |
CN112365056A (en) | Electrical load joint prediction method and device, terminal and storage medium | |
CN110212551B (en) | Micro-grid reactive power automatic control method based on convolutional neural network | |
CN110796307A (en) | Distributed load prediction method and system for comprehensive energy system | |
CN114372360A (en) | Method, terminal and storage medium for power load prediction | |
CN115222106A (en) | User day-ahead load prediction method of self-adaptive model | |
CN112308270A (en) | Long-term electricity load prediction method and device and computer implementation system | |
CN115470862A (en) | Dynamic self-adaptive load prediction model combination method | |
CN104834975A (en) | Power network load factor prediction method based on intelligent algorithm optimization combination | |
CN116070769A (en) | Ultra-short-term wind power plant power multi-step interval prediction modularization method and device thereof | |
Putri et al. | Short-term forecasting of electricity consumption revenue on Java-Bali electricity system using Jordan recurrent neural network | |
CN113887809A (en) | Power distribution network supply and demand balance method, system, medium and computing equipment under double-carbon target | |
CN112307675B (en) | Neural network-based temperature-sensitive load separation identification method and system | |
CN113935856A (en) | Method and device for controlling electric energy, processor and computer readable storage medium | |
CN110414776B (en) | Quick response analysis system for power utilization characteristics of different industries | |
CN109767037A (en) | A kind of prediction technique of summer Daily treatment cost | |
CN113837486B (en) | RNN-RBM-based distribution network feeder long-term load prediction method | |
CN115864461A (en) | Control method of electric power energy storage system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |