CN116596286B - Optimized scheduling method, device and equipment for virtual power plant and storage medium - Google Patents
Optimized scheduling method, device and equipment for virtual power plant and storage medium Download PDFInfo
- Publication number
- CN116596286B CN116596286B CN202310879567.XA CN202310879567A CN116596286B CN 116596286 B CN116596286 B CN 116596286B CN 202310879567 A CN202310879567 A CN 202310879567A CN 116596286 B CN116596286 B CN 116596286B
- Authority
- CN
- China
- Prior art keywords
- power
- energy
- scheduling
- electric energy
- virtual
- 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 62
- 238000003860 storage Methods 0.000 title claims abstract description 17
- 238000005457 optimization Methods 0.000 claims abstract description 49
- 238000005096 rolling process Methods 0.000 claims abstract description 18
- YHXISWVBGDMDLQ-UHFFFAOYSA-N moclobemide Chemical compound C1=CC(Cl)=CC=C1C(=O)NCCN1CCOCC1 YHXISWVBGDMDLQ-UHFFFAOYSA-N 0.000 claims abstract 9
- 230000008569 process Effects 0.000 claims description 23
- 230000015654 memory Effects 0.000 claims description 18
- 238000012546 transfer Methods 0.000 claims description 15
- 238000012545 processing Methods 0.000 claims description 14
- 238000004590 computer program Methods 0.000 claims description 12
- 238000005265 energy consumption Methods 0.000 claims description 11
- 238000004519 manufacturing process Methods 0.000 claims description 7
- 230000005540 biological transmission Effects 0.000 claims description 6
- 230000007812 deficiency Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000007246 mechanism Effects 0.000 claims description 5
- 238000012795 verification Methods 0.000 claims description 4
- 238000009826 distribution Methods 0.000 abstract description 10
- 238000010586 diagram Methods 0.000 description 6
- 238000004891 communication Methods 0.000 description 5
- 238000005259 measurement Methods 0.000 description 5
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000002950 deficient Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 235000019577 caloric intake Nutrition 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000005094 computer simulation Methods 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 238000013136 deep learning model Methods 0.000 description 1
- 230000009977 dual effect Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000004146 energy storage Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 230000006855 networking Effects 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000002441 reversible effect Effects 0.000 description 1
- 230000006403 short-term memory Effects 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 239000002699 waste material Substances 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
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06313—Resource planning in a project environment
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- H—ELECTRICITY
- H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
- H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
- 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
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- General Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Marketing (AREA)
- Tourism & Hospitality (AREA)
- Power Engineering (AREA)
- Operations Research (AREA)
- Biodiversity & Conservation Biology (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Quality & Reliability (AREA)
- Educational Administration (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention relates to an optimal scheduling method, device, equipment and storage medium of a virtual power plant, wherein the electric energy richness of a current time stamp of a distributed energy network is identified through an ARIMA model, and a basic electric energy scheduling program is generated based on the electric energy richness; inputting a basic electric energy scheduling program and electric energy richness into a load prediction model to output an optimization prediction node and an optimization prediction line; adopting an online optimization model to perform virtual power scheduling corresponding to an optimization prediction node and an optimization prediction line on a virtual energy network by utilizing a mixed integer linear program, and judging the intra-day scheduling establishment of the virtual power scheduling by utilizing a rolling time domain program; if so, executing an actual power dispatching program corresponding to the virtual power dispatching program under the framework of the basic power dispatching program; the distribution of the power resources is effectively optimized, the running efficiency, stability and safety of the power system are improved, and the digital and intelligent management of the power system is realized.
Description
Technical Field
The invention relates to the technical field of energy scheduling processing models, in particular to an optimal scheduling method, device and equipment for a virtual power plant and a storage medium.
Background
"virtual power plant" (Virtual Power Plant, VPP) is a concept developed in the field of electricity in recent years. The virtual power plant connects a plurality of distributed energy sources, load response equipment, energy storage equipment and the like through the Internet, communication and information technology to form a brand new power system operation mode with central dispatching and networking operation, but the optimization of digital electric energy dispatching can require real-time association of distributed power sources (such as solar photovoltaic and wind power generation equipment) to obtain feedback of a real-scene energy source, and the problems of a large number of data exchanges and a high-speed communication network exist.
Disclosure of Invention
The invention mainly aims to provide an optimal scheduling method, device, equipment and storage medium for a virtual power plant, which effectively optimize the distribution of power resources, improve the running efficiency, stability and safety of a power system and realize the digital and intelligent management of the power system through accurate prediction and intelligent scheduling.
In order to achieve the above purpose, the present invention provides an optimized scheduling method for a virtual power plant, comprising the following steps:
Identifying the electric energy richness of the current timestamp of the distributed energy network by adopting a pre-trained ARIMA model, and generating a basic electric energy scheduling program based on the electric energy richness;
inputting the basic electric energy scheduling program and the electric energy abundance into a preset load prediction model to output an optimal prediction node and an optimal prediction line through the load prediction model, wherein the optimal prediction node and the optimal prediction line are respectively nodes and lines which can be optimally scheduled for electric energy prediction in a distributed energy network with a current time stamp;
performing virtual power scheduling corresponding to an optimization prediction node and an optimization prediction line on a virtual energy network by using a mixed integer linear program by using a preset online optimization model, and judging the intra-day scheduling establishment of the virtual power scheduling by using a rolling time domain program, wherein the virtual energy network is formed by digitizing a distributed energy network;
and if so, executing an actual power scheduler corresponding to the virtual power scheduler under the framework of the basic power scheduler.
Further, the step of identifying the electric energy richness of the current timestamp of the distributed energy network by the ARIMA model comprises the following steps:
Acquiring current time stamped energy grid data including, but not limited to, electrical energy production, electrical energy consumption, electrical energy output, and cable loading;
performing time sequence fitting on the energy network data based on an ARIMA model to perform fitting verification on the energy network data, wherein the time sequence fitting comprises data item comparison on the energy network data and historical energy data to target each energy item in the energy network data;
and carrying out autoregressive processing on each energy fine item by using a modeling list method of an ARIMA model through the calibrated each energy fine item to generate the electric energy richness represented by a list, wherein the autoregressive processing comprises classifying each energy fine item to classify the electric energy richness of each region in a distributed energy network.
Further, the step of generating a base power scheduler based on the power richness comprises:
determining an electric energy surplus region and an electric energy missing region of each region on the distributed energy network according to the electric energy abundance;
and programming a power control carrier PLC (programmable logic controller) aiming at the power surplus region and the power missing region through a preset power scheduling strategy, and generating a basic power scheduling program for transferring the energy of the power surplus region to the power missing region, wherein the preset power scheduling strategy is a preset safety scheduling strategy and comprises energy transfer efficiency and transfer paths.
Further, the load prediction model outputs an optimized prediction node and an optimized prediction line through a basic power scheduler and power richness, and the method comprises the following steps:
performing predictive calculation of power consumption and power increase of the power richness of the current time stamp within preset time based on the pre-stored LSTM historical area energy consumption so as to identify the power consumption predicted amount and the power increase predicted amount corresponding to each energy area of the distributed energy network;
adding the consumption predicted amount and the increase predicted amount to obtain an energy efficiency predicted amount, judging whether the energy efficiency predicted amount is in a preset power supply interval, if so, obtaining excessive electric energy, and if so, obtaining electric energy loss;
if the energy efficiency predicted quantity is in the power supply interval, determining a positive difference quantity or a negative difference quantity between an optimal value and the energy efficiency predicted quantity in the power supply interval by using an attention mechanism;
determining a tuning amount of the predicted energy efficiency amount by the positive difference amount or the negative difference amount, and correspondingly identifying the predicted tuning amount between the predicted consumption amount and the predicted increase amount based on the tuning amount;
And identifying consumption prediction amounts and addition increase or addition decrease of the increase prediction amounts of the lines and the nodes in each area of the distributed energy network by adopting the prediction optimization quantity, so as to obtain optimized prediction nodes and optimized prediction lines of the lines and the nodes in each area according to the basic electric energy scheduling program.
Further, the step of performing virtual power scheduling corresponding to the optimized prediction node and the optimized prediction line on the virtual energy network by using a mixed integer linear program by adopting a preset online optimization model comprises the following steps:
performing discrete point identification and circuit path identification, and virtually constructing a virtual energy network matched with the distributed energy network;
carrying out power grid structure topology on the virtual energy network based on each discrete point and each circuit path so as to configure electric parameters corresponding to each discrete point and each circuit path;
and determining parameter data of nodes and paths of a power grid topological structure of the virtual energy network according to the electrical parameters of each discrete point and the circuit path, so as to perform virtual power scheduling corresponding to the optimized prediction nodes and the optimized prediction lines on the virtual energy network according to the mixed integer linear program.
Further, determining the intra-day scheduling establishment of the virtual power scheduling by using a rolling time domain program includes:
Measuring the time period for realizing virtual power scheduling by adopting the power transmission speed of the distributed energy network preset by the rolling time domain program;
and judging whether the time period accords with the intra-day scheduling establishment in a preset time day or not.
Further, the step of executing the actual power scheduler corresponding to the virtual power scheduler under the framework of the base power scheduler includes:
and generating an actual power schedule corresponding to the virtual power schedule based on the basic power schedule program so as to perform a power schedule process of the distributed energy network according to the actual power schedule.
The invention provides an optimized dispatching device of a virtual power plant, which comprises the following components:
identifying the electric energy richness of the current timestamp of the distributed energy network by adopting a pre-trained ARIMA model, and generating a basic electric energy scheduling program based on the electric energy richness;
inputting the basic electric energy scheduling program and the electric energy abundance into a preset load prediction model to output an optimal prediction node and an optimal prediction line through the load prediction model, wherein the optimal prediction node and the optimal prediction line are respectively nodes and lines which can be optimally scheduled for electric energy prediction in a distributed energy network with a current time stamp;
Performing virtual power scheduling corresponding to an optimization prediction node and an optimization prediction line on a virtual energy network by using a mixed integer linear program by using a preset online optimization model, and judging the intra-day scheduling establishment of the virtual power scheduling by using a rolling time domain program, wherein the virtual energy network is formed by digitizing a distributed energy network;
and if so, executing an actual power scheduler corresponding to the virtual power scheduler under the framework of the basic power scheduler.
The invention also provides computer equipment, which comprises a memory and a processor, wherein the memory stores a computer program, and the processor realizes the steps of the optimal scheduling method of the virtual power plant when executing the computer program.
The invention also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor implements the steps of the optimal scheduling method of a virtual power plant as described in any of the above.
The optimal scheduling method, the optimal scheduling device, the optimal scheduling equipment and the storage medium for the virtual power plant have the following beneficial effects:
(1) The digital checking process is carried out through the virtual energy network, so that each power dispatching is checked on line, and the safety of the power dispatching is greatly improved.
(2) In order to solve the timeliness problem of real energy feedback, a virtual energy network is executed on line to record lines and nodes according to historical information, and the whole operation is executed after all power dispatching details and parameters are confirmed to be established, so that a buffer space for data acquisition is provided, and the severity of the problem is relieved.
(3) The virtual checking calculation is directly carried out by the computer equipment, and the network uploading stability of each path and node in the distributed energy network is not required too much.
Drawings
FIG. 1 is a schematic diagram of an optimized scheduling method for a virtual power plant in accordance with an embodiment of the present invention;
FIG. 2 is a schematic diagram of a method for optimized scheduling of virtual power plants in accordance with yet another embodiment of the present invention;
FIG. 3 is a block diagram of an optimized scheduling device for a virtual power plant in accordance with an embodiment of the present invention;
fig. 4 is a block diagram schematically illustrating a structure of a computer device according to an embodiment of the present invention.
The achievement of the objects, functional features and advantages of the present invention will be further described with reference to the accompanying drawings, in conjunction with the embodiments.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
The optimal scheduling method for the virtual power plant provided by the invention is implemented by taking the computer equipment as an execution main body.
Referring to fig. 1-2, a flow chart of an optimized scheduling method for a virtual power plant according to the present invention includes the following steps:
s1, identifying the electric energy richness of a current timestamp of a distributed energy network by adopting a pre-trained ARIMA model, and generating a basic electric energy scheduling program based on the electric energy richness;
the ARIMA (Auto-Regressive Integrated Moving Average) model is a model of time series prediction, the nature of which is based on autoregressive and moving average generation. The pretraining process of the ARIMA model typically requires a certain amount of historical power data, and by learning the laws of these historical data, the ARIMA model can predict future data.
The ARIMA model here is used to identify the power richness of the distributed energy network current timestamp. The method comprises the following steps:
1. energy grid data for the current time stamp is obtained, including but not limited to, power production, power consumption, power output, cable load, and the like.
2. And performing time sequence fitting on the obtained energy network data by using an ARIMA model. The purpose of this process is to find rules or trends between the current energy data and the historical energy data for subsequent prediction.
3. Autoregressive processing is carried out on the results of the time series fitting, and a list representing the electric energy richness is generated. This list may be used as a basis for subsequent power scheduling decisions.
Based on the power richness, a base power scheduler is generated accordingly. This procedure is a policy or rule established for determining the distribution and flow of power. If the power richness of a region is high, the region may be defined as a power surplus region, and the energy is preferentially transferred out in the basic power scheduler. Conversely, if the electric energy abundance of a certain region is low, that region may be defined as an electric energy loss region, and priority is given to transferring energy.
The method is a dynamic adaptation process, and is adjusted according to the real-time electric energy richness, so that the power distribution on the energy network is optimized, and the efficiency and reliability of power use are improved.
S2, inputting the basic electric energy scheduling program and the electric energy abundance into a preset load prediction model to output an optimized prediction node and an optimized prediction line through the load prediction model, wherein the optimized prediction node and the optimized prediction line are nodes and lines which can be optimally scheduled in electric energy prediction in a distributed energy network with a current time stamp respectively;
First, a basic power scheduler and a power richness are input to a preset load prediction model. The base power scheduler tells the model the current power distribution and flow direction, while the power richness represents the power situation for each region. These two inputs may provide the current state of the electrical network and the resource distribution.
The load prediction model then begins processing the input data. This model is pre-trained and it can understand the input data and analyze it according to rules and weights within it. In short, the purpose of this model is to predict which nodes and lines have a tendency to change in power demand under the current timestamp, and there is the possibility of optimizing power scheduling.
The prediction model outputs an optimized prediction node and an optimized prediction line. This refers to nodes and lines where power scheduling can be optimized under the current timestamp. For example, certain nodes may be overloaded or underpowered, and the power requirements of these nodes may be balanced by scheduling optimizations; some lines may be busy or idle, and power resources can be efficiently and comprehensively utilized through scheduling optimization.
Thus, through the processing of the load prediction model, the computer equipment obtains the optimal prediction node and the optimal prediction line, and provides a reference for power dispatching optimization of the distributed energy network. It should be noted that this process is not disposable, but rather needs to be constantly adjusted and optimized to accommodate real-time conditions and demand changes in the power grid.
S3, performing virtual power scheduling corresponding to an optimization prediction node and an optimization prediction line on a virtual energy network by using a mixed integer linear program by using a preset online optimization model, and judging the intra-day scheduling establishment of the virtual power scheduling by using a rolling time domain program, wherein the virtual energy network is formed by digitizing a distributed energy network;
the online optimization model is a machine learning model, and can process and analyze data in real time to find out an optimal power dispatching strategy. The on-line optimization model receives the optimization prediction nodes and the optimization prediction lines as inputs, and then searches for an optimal power scheduling scheme according to a preset optimization principle, such as minimizing loss or maximizing efficiency. Mixed integer linear program: the online optimization model will employ a mathematical optimization technique called Mixed Integer Linear Program (MILP). MILP is an optimized model capable of handling both continuous and discrete variables, well suited for describing problems such as power scheduling. The optimization model will produce an optimal solution that satisfies constraints (e.g., power balance, grid safety, etc.). Scrolling time domain program: by scrolling the time domain program, the establishment of the generated virtual power schedule can be determined. The basic idea of the scrolling time domain procedure is: dynamic correction is performed by using the predicted error, and a time window is continuously advanced to feed back real-time information. Based on the current power situation and the previous predictions and actual results, a rolling horizon program may be used to determine whether virtual power scheduling may be implemented. Virtual energy network: is a digitized formation of the distributed energy network, that is, it is a computer model of the distributed energy network. Operating it is equivalent to operating in a distributed energy network. The virtual power scheduling of the optimized prediction node and the optimized prediction line is performed in the virtual energy network. The final objective of all the steps and links is to achieve better power dispatching, and by optimizing the coordination of the power supply, the load and the power transmission line, the power utilization rate can be remarkably improved, the loss can be reduced, and the stability and the reliability of the power grid can be improved.
And S4, if so, executing an actual power dispatching program corresponding to the virtual power dispatching under the framework of the basic power dispatching program.
Judging the establishment of virtual power scheduling: the computer device uses a rolling time domain program to check the virtual power schedule to confirm whether it is viable in the actual power grid. This includes checking whether various constraints (e.g., power safety, power risk, power demand, etc.) are met or not, and whether conditions are better than current scheduling schemes, etc. Only if all conditions are met will the virtual power scheduler be deemed executable. Implementing actual power scheduling: the established virtual power schedule will be converted into an actual power schedule. This means that all instructions and actions in the virtual scheduling scheme will be executed in the physical power network. The power resources will be reallocated and scheduled according to a virtual power scheduling scheme, which includes links of power production, power supply, power transmission, and power usage. In the framework of the basic power scheduler: the above operations are performed in the framework of a basic power scheduler. This means that all operations and the whole execution process of the power grid are completed in the basic power dispatching program, and the optimization principle of algorithms such as mixed integer linear programs and the like is followed, so that the basic operation rules and safety requirements of the power grid are met.
In one embodiment, the ARIMA model identifies the power richness of the current timestamp of the distributed energy grid, comprising:
acquiring current time stamped energy grid data including, but not limited to, electrical energy production, electrical energy consumption, electrical energy output, and cable loading;
performing time sequence fitting on the energy network data based on an ARIMA model to perform fitting verification on the energy network data, wherein the time sequence fitting comprises data item comparison on the energy network data and historical energy data to target each energy item in the energy network data;
and carrying out autoregressive processing on each energy fine item by using a modeling list method of an ARIMA model through the calibrated each energy fine item to generate the electric energy richness represented by a list, wherein the autoregressive processing comprises classifying each energy fine item to classify the electric energy richness of each region in a distributed energy network.
In the specific implementation process, energy network data are acquired: data of a current distributed energy network is first acquired, wherein the data comprises various power information such as electric energy production, electric energy consumption, electric energy output, cable load and the like. Each information point represents an aspect of the operation of the energy network. ARIMA model and time series fitting: once the energy grid data is acquired, a time series fit of the data can be made based on the ARIMA model that has been pre-trained. In this process, existing energy grid data is compared with historical energy data, and each data is focused and compared in detail. In this way, the computer device can derive the characteristics and rules of each data item. Energy fine item calibration: then, each energy item needs to be calibrated. Calibration is actually a comparison mechanism that compares existing energy items with historical data to find similarities and differences between them. In this way, the generation of the virtual energy network is then reconciled with the actual energy network. Autoregressive processing with ARIMA: next, the autoregressive process is carried out on all the calibrated energy fine items based on the modeling list method of the ARIMA model. The autoregressive process is actually to explore the dynamic relationship of each energy term itself over time. The result of the autoregressive process is a series of lists that can represent the abundance of electrical energy. Electric energy richness classification: the autoregressive process also includes classifying each energy term to determine the power richness of the various regions in the distributed energy grid. Such classification will help to understand the power demand and power supply conditions of the various areas for more efficient power scheduling and optimization.
In one embodiment, the step of generating a base power scheduler based on the power richness comprises:
determining an electric energy surplus region and an electric energy missing region of each region on the distributed energy network according to the electric energy abundance;
and programming a power control carrier PLC (programmable logic controller) aiming at the power surplus region and the power missing region through a preset power scheduling strategy, and generating a basic power scheduling program for transferring the energy of the power surplus region to the power missing region, wherein the preset power scheduling strategy is a preset safety scheduling strategy and comprises energy transfer efficiency and transfer paths.
In a specific implementation process, if an electric energy surplus region and an electric energy missing region of each region on a distributed energy network are determined according to the electric energy abundance, then a preset power scheduling strategy is combined with power control carrier PLC (Performance/Low Consumer broadband power carrier communication technology) programming to generate a basic electric energy scheduling program for transferring the energy of the electric energy surplus region to the electric energy missing region, wherein the implementation principle is as follows: determining an electric energy surplus region and an electric energy deficiency region: according to the electric energy richness obtained by the calculation in the last step, the computer equipment can be understood as the electric energy supply state of each specific area on the distributed energy network. The rich (excess) and the deficient (missing) areas can be identified to make the corresponding power control strategy. Preset power scheduling strategies: in the scheme, the preset power scheduling strategy is used for ensuring that the power transfer from the power surplus region to the power deficiency region is performed safely and efficiently, and the power scheduling strategy takes multiple factors such as energy transfer efficiency and transfer paths into consideration. For example, path selection should be prioritized with the shortest path and the lowest loss. Power control carrier PLC programming: the scheme uses a programming mode of a power control carrier PLC to execute a power scheduling strategy. The PLC is a communication tool, can perform power line communication in a power system, and is characterized by being stable and reliable, and capable of realizing large-scale power information transmission. This will allow a preset power scheduling scheme to be performed by means of a power message transmitting power from the power surplus region to the power deficient region. Generating a basic power scheduler: the PLC programming will make a corresponding power scheduling program, which is based on the power richness, the power scheduling strategy and the implementation of the power control carrier wave, so as to smoothly transfer the energy of the power surplus region to the power missing region. Such scheduling strategies aim to provide more accurate, finer management of the distribution and utilization of electrical energy, optimize power system performance, reduce energy waste, and improve the safety and stability of the overall power system as much as possible.
In one embodiment, the step of inputting the basic power scheduler and the power richness into a preset load prediction model to output an optimized prediction node and an optimized prediction line through the load prediction model includes:
s21, carrying out predictive calculation on the power consumption and the power increase of the power richness of the current timestamp in preset time based on the pre-stored LSTM historical area power consumption so as to identify the power consumption predicted amount and the power increase predicted amount corresponding to each energy area of the distributed energy network;
s22, adding the consumption predicted amount and the increase predicted amount to obtain an energy efficiency predicted amount, judging whether the energy efficiency predicted amount is in a preset power supply interval, if so, obtaining excessive electric energy, and if so, obtaining electric energy loss;
s23, if the energy efficiency prediction quantity is in the power supply interval, determining a positive difference quantity or a negative difference quantity between an optimal value and the energy efficiency prediction quantity in the power supply interval by using an attention mechanism;
s24, determining a predicted tuning amount of the energy efficiency predicted amount through the positive difference amount or the negative difference amount, and correspondingly identifying the predicted tuning amount between the consumption predicted amount and the increase predicted amount based on the tuning amount;
And S25, identifying consumption predicted quantity and addition increment or addition decrement of the increment predicted quantity of the lines and the nodes in each area of the distributed energy network by adopting the prediction optimization quantity, so as to obtain optimized prediction nodes and optimized prediction lines of the lines and the nodes in each area according to the basic electric energy scheduling program.
In a specific implementation process, in S21, prediction of energy consumption is performed using an LSTM (Long Short-Term Memory) model. LSTM is a deep learning model that is particularly good at processing sequence data with temporal properties. Here, the computer device applies LSTM to and models historical energy consumption data in various energy regions of the distributed power grid. The historical energy consumption data of each area stored in advance is used for prediction on the current time stamp through the LSTM model. It is particularly noted that this prediction is for each energy zone within a predetermined period of time, i.e. it is possible to predict how much energy each zone may consume and how much energy may be newly increased during a future period of time. In S22, the amount of electric energy consumption (consumption prediction amount) and the amount of electric energy increase (increase prediction amount) that may be reached in a period of time in the future for each energy source region predicted by the LSTM model are first obtained. Then, the consumption prediction amount and the increase prediction amount are added to calculate the energy efficiency prediction amount of each energy region in this period. The energy efficiency prediction amount is equivalent to the sum of the power supplied by the areas in a preset time period, and can reflect the overall state of the power of each specific energy area in the time period. In S23, an attention mechanism algorithm is employed for determining the relationship between the optimum value (ideal point of preset power supply section) and the energy efficiency prediction amount. In S24, the objective of this step is to determine the adjustment value (tuning amount) of the energy efficiency pre-measurement based on the positive or negative difference amount calculated before the computer device, and find the adjustment value between the consumption pre-measurement and the increase pre-measurement accordingly. When the computer device has a positive or negative difference, the gap between the predicted amount of energy efficiency and the preset optimal value of the computer device can be evaluated. This gap may tell the computer device how much power is needed to be added (positive difference) or how much power is saved (negative difference) to achieve optimal power supply and demand balance. By "determining the amount of tuning of the predicted amount of energy efficiency" it is meant that the computer device calculates how much electrical energy needs to be tuned by this amount of difference so that the predicted energy efficiency is closer to the preset optimal value of the computer device. This value may be adjusted in the forward direction (indicating that the power supply is too much and needs to be reduced) or in the reverse direction (indicating that the power supply is not sufficient and needs to be increased). Then, "the predicted tuning amount between the consumption predicted amount and the increase predicted amount is recognized by the positive difference amount or the negative difference amount correspondence" represents that the computer device needs to find the adjustment value between the consumption predicted amount and the increase predicted amount according to the adjustment value. In this case, the computer device further analyzes the previously determined tuning amount to find out whether the specific amount to be adjusted from the consumption pre-measurement amount or the increase pre-measurement amount and the specific amount to be adjusted, so that the power supply and demand are more balanced. In S25, this step involves optimizing the distribution of electrical energy to each area of the distributed energy network using the predicted tuning amounts we have calculated before. By "identifying the consumption predictions of the lines and nodes in each area of the distributed energy network using the predictive tuning amounts and adding up or adding down the predictions" we will use the predictive tuning amounts calculated previously to adjust the consumption predictions and adding up predictions of the lines and nodes in each area of the network. Specifically, if an increase in power is required, we add the tuning amount to the consumption prediction amount or the increase prediction amount; instead, if the power needs to be reduced, we subtract the tuning amount from them. Where lines and nodes represent specific parts of the power network, where lines refer to paths of power transfer in the power network, and nodes represent precise points of location in the power network, such as a cell or a building. Next, "to obtain the optimized prediction nodes and optimized prediction lines of the lines and nodes of the respective areas according to the base power scheduler". By this we mean that after the previous adjustments we can optimize the lines and nodes of each area with the basic power scheduler (i.e. an energy management system that can automatically allocate power to achieve optimal efficiency). In particular, we will obtain an optimized prediction value of each regional line and node, which reflects the power supply and demand conditions expected to be reached after passing through the scheduler, helping us to adjust and optimize the supply of electrical energy.
In one embodiment, the step of performing, on the virtual energy network, virtual power scheduling corresponding to the optimized prediction node and the optimized prediction line by using a mixed integer linear program with a preset online optimization model includes:
performing discrete point identification and circuit path identification, and virtually constructing a virtual energy network matched with the distributed energy network;
carrying out power grid structure topology on the virtual energy network based on each discrete point and each circuit path so as to configure electric parameters corresponding to each discrete point and each circuit path;
and determining parameter data of nodes and paths of a power grid topological structure of the virtual energy network according to the electrical parameters of each discrete point and the circuit path, so as to perform virtual power scheduling corresponding to the optimized prediction nodes and the optimized prediction lines on the virtual energy network according to the mixed integer linear program.
In the specific implementation process, first, the discrete point identification and the circuit path identification are performed to virtually construct a virtual energy network matched with the distributed energy network through the discrete point identification and the circuit path identification. Meaning that we first need to identify points of importance (discrete points) and paths (circuit paths) for power transfer in a distributed energy network. Then, based on the information, a virtual energy network matched with the actual distributed network is constructed. Then, the virtual energy network is subjected to power grid structure topology based on the discrete points and the circuit paths so as to configure the electric parameters corresponding to the discrete points and the circuit paths. This means that we will configure the structure of the virtual energy network according to the actual situation, including the topology of the network and the electrical parameters including discrete points and circuit paths. Next, "parameter data of nodes and paths of the grid topology of the virtual energy network are determined according to the electrical parameters of the discrete points and the circuit paths. In this step we confirm the parameter data of the nodes and paths in the virtual energy network that are actually in use, based on the electrical parameters of the discrete points and circuit paths located and configured in the previous step. These data are key information for understanding the grid operating conditions and optimizing the power distribution. And finally, carrying out optimal prediction nodes and virtual power scheduling corresponding to the optimal prediction lines on the virtual energy network according to the mixed integer linear program. The on-line optimization model of Mixed Integer Linear Program (MILP) is used, and virtual power scheduling of the optimization prediction nodes and the optimization prediction lines is performed by utilizing all parameter data confirmed by the user in the virtual energy network, so that energy intake and supply are effectively managed, and the whole system is more efficient and balanced to operate.
In one embodiment, determining the intra-day schedule satisfaction of the virtual power schedule using a rolling horizon program includes:
measuring the time period for realizing virtual power scheduling by adopting the power transmission speed of the distributed energy network preset by the rolling time domain program;
and judging whether the time period accords with the intra-day scheduling establishment in a preset time day or not.
In a specific implementation, the length of time/period required to complete virtual power scheduling is measured using a power transfer rate preset by a rolling time domain program, which is the rate at which power is transferred from one location to another in a distributed energy network. Then "judge whether the time period accords with the schedule establishment in the day of the preset time day" will be performed. And comparing the time of day scheduling by using the measured time period. The intra-day schedule typically represents a power schedule made during the day, for example, some power systems may have a daily power schedule plan. If the time period for implementing the virtual power schedule is within a preset time range within a day, then the day schedule may be considered as being established, and this virtual power schedule may be implemented in the day schedule.
Specifically, based on the framework of the basic power scheduler, the step of executing the actual power scheduler corresponding to the virtual power schedule includes:
and generating an actual power schedule corresponding to the virtual power schedule based on the basic power schedule program so as to perform a power schedule process of the distributed energy network according to the actual power schedule.
Referring to fig. 3, a schematic structural diagram of an optimized dispatching device for a virtual power plant according to the present invention includes:
the identification unit 1 is used for identifying the electric energy richness of the current timestamp of the distributed energy network by adopting a pre-trained ARIMA model and generating a basic electric energy scheduling program based on the electric energy richness;
the grid unit 2 is used for inputting the basic electric energy scheduling program and the electric energy abundance into a preset load prediction model so as to output an optimized prediction node and an optimized prediction line through the load prediction model, wherein the optimized prediction node and the optimized prediction line are respectively nodes and lines which can be optimally scheduled in electric energy prediction in a distributed energy network with a current time stamp;
the judging unit 3 is used for carrying out virtual power scheduling corresponding to the optimized prediction node and the optimized prediction line on the virtual energy network by adopting a preset online optimization model through a mixed integer linear program, and judging the intra-day scheduling establishment of the virtual power scheduling through a rolling time domain program, wherein the virtual energy network is formed by digitizing a distributed energy network;
And an execution unit 4 for executing an actual power scheduler corresponding to the virtual power scheduler based on the framework of the basic power scheduler if the virtual power scheduler is established.
In this embodiment, for specific implementation of each unit in the above embodiment of the apparatus, please refer to the description in the above embodiment of the method, and no further description is given here.
Referring to fig. 4, in an embodiment of the present invention, there is further provided a computer device, which may be a server, and the internal structure of the computer device may be as shown in fig. 4. The computer device includes a processor, a memory, a display screen, an input device, a network interface, and a database connected by a system bus. Wherein the computer is configured to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, computer programs, and a database. The internal memory provides an environment for the operation of the operating system and computer programs in the non-volatile storage media. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used for communicating with an external terminal through a network connection. The computer program is executed by a processor to implement a method.
S1, identifying the electric energy richness of a current timestamp of a distributed energy network by adopting a pre-trained ARIMA model, and generating a basic electric energy scheduling program based on the electric energy richness;
s2, inputting the basic electric energy scheduling program and the electric energy abundance into a preset load prediction model to output an optimized prediction node and an optimized prediction line through the load prediction model, wherein the optimized prediction node and the optimized prediction line are nodes and lines which can be optimally scheduled in electric energy prediction in a distributed energy network with a current time stamp respectively;
s3, performing virtual power scheduling corresponding to an optimization prediction node and an optimization prediction line on a virtual energy network by using a mixed integer linear program by using a preset online optimization model, and judging the intra-day scheduling establishment of the virtual power scheduling by using a rolling time domain program, wherein the virtual energy network is formed by digitizing a distributed energy network;
and S4, if so, executing an actual power dispatching program corresponding to the virtual power dispatching under the framework of the basic power dispatching program.
It will be appreciated by those skilled in the art that the architecture shown in fig. 4 is merely a block diagram of a portion of the architecture in connection with the present inventive arrangements and is not intended to limit the computer devices to which the present inventive arrangements are applicable.
An embodiment of the present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the above method. It is understood that the computer readable storage medium in this embodiment may be a volatile readable storage medium or a nonvolatile readable storage medium.
In summary, the electric energy richness of the current timestamp of the distributed energy network is identified by adopting a pre-trained ARIMA model, and a basic electric energy scheduling program is generated based on the electric energy richness; inputting the basic electric energy scheduling program and the electric energy abundance into a preset load prediction model to output an optimal prediction node and an optimal prediction line through the load prediction model, wherein the optimal prediction node and the optimal prediction line are respectively nodes and lines which can be optimally scheduled for electric energy prediction in a distributed energy network with a current time stamp; performing virtual power scheduling corresponding to an optimization prediction node and an optimization prediction line on a virtual energy network by using a mixed integer linear program by using a preset online optimization model, and judging the intra-day scheduling establishment of the virtual power scheduling by using a rolling time domain program, wherein the virtual energy network is formed by digitizing a distributed energy network; if so, executing an actual power scheduler corresponding to the virtual power scheduler under the framework of the basic power scheduler; accurate prediction and intelligent scheduling are realized, the distribution of power resources is effectively optimized, the running efficiency, stability and safety of the power system are improved, and the digital and intelligent management of the power system is realized.
Those skilled in the art will appreciate that implementing all or part of the above described methods may be accomplished by way of a computer program stored on a non-transitory computer readable storage medium, which when executed, may comprise the steps of the embodiments of the methods described above. Any reference to memory, storage, database, or other medium provided by the present invention and used in embodiments may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), dual data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous Link DRAM (SLDRAM), memory bus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM, among others.
It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, apparatus, article, or method that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, apparatus, article, or method. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, apparatus, article or method that comprises the element.
The foregoing description is only of the preferred embodiments of the present invention and is not intended to limit the scope of the invention, and all equivalent structures or equivalent processes using the descriptions and drawings of the present invention or direct or indirect application in other related technical fields are included in the scope of the present invention.
Claims (7)
1. The optimal scheduling method for the virtual power plant is characterized by comprising the following steps of:
identifying the electric energy richness of the current timestamp of the distributed energy network by adopting a pre-trained ARIMA model, and generating a basic electric energy scheduling program based on the electric energy richness;
Inputting the basic electric energy scheduling program and the electric energy abundance into a preset load prediction model to output an optimal prediction node and an optimal prediction line through the load prediction model, wherein the optimal prediction node and the optimal prediction line are respectively nodes and lines which can be optimally scheduled for electric energy prediction in a distributed energy network with a current time stamp;
performing virtual power scheduling corresponding to an optimization prediction node and an optimization prediction line on a virtual energy network by using a mixed integer linear program by using a preset online optimization model, and judging the intra-day scheduling establishment of the virtual power scheduling by using a rolling time domain program, wherein the virtual energy network is formed by digitizing a distributed energy network;
if so, executing an actual power scheduler corresponding to the virtual power scheduler based on the framework of the basic power scheduler;
the ARIMA model identifies the electric energy richness of the current timestamp of the distributed energy network, comprising the following steps:
acquiring energy network data of a current time stamp, wherein the energy network data comprises electric energy production capacity, electric energy consumption capacity, electric energy output capacity and cable load;
performing time sequence fitting on the energy network data based on an ARIMA model to perform fitting verification on the energy network data, wherein the time sequence fitting comprises data item comparison on the energy network data and historical energy data to target each energy item in the energy network data;
Performing autoregressive processing on each energy fine item by using a modeling list method of an ARIMA model through the calibrated each energy fine item to generate the electric energy richness represented by a list, wherein the autoregressive processing comprises classifying each energy fine item to classify the electric energy richness of each region in a distributed energy network;
generating a base power scheduler based on the power richness, comprising:
determining an electric energy surplus region and an electric energy missing region of each region on the distributed energy network according to the electric energy abundance;
programming a power control carrier PLC (programmable logic controller) aiming at an electric energy excess region and an electric energy deficiency region through a preset power scheduling strategy, and generating a basic electric energy scheduling program for transferring the energy of the electric energy excess region to the electric energy deficiency region, wherein the preset power scheduling strategy is a preset safety scheduling strategy and comprises energy transfer efficiency and transfer paths;
and carrying out virtual power scheduling corresponding to the optimized prediction node and the optimized prediction line on the virtual energy network by adopting a preset online optimization model and utilizing a mixed integer linear program, wherein the method comprises the following steps of:
performing discrete point identification and circuit path identification, and virtually constructing a virtual energy network matched with the distributed energy network;
Carrying out power grid structure topology on the virtual energy network based on each discrete point and each circuit path so as to configure electric parameters corresponding to each discrete point and each circuit path;
and determining parameter data of nodes and paths of a power grid topological structure of the virtual energy network according to the electrical parameters of each discrete point and the circuit path, so as to perform virtual power scheduling corresponding to the optimized prediction nodes and the optimized prediction lines on the virtual energy network according to the mixed integer linear program.
2. The optimal scheduling method of a virtual power plant according to claim 1, wherein the step of inputting the basic power scheduling program and the power richness to a preset load prediction model to output an optimal prediction node and an optimal prediction line through the load prediction model comprises:
performing predictive calculation of power consumption and power increase of the power richness of the current time stamp within preset time based on the pre-stored LSTM historical area energy consumption so as to identify the power consumption predicted amount and the power increase predicted amount corresponding to each energy area of the distributed energy network;
adding the consumption predicted amount and the increase predicted amount to obtain an energy efficiency predicted amount, judging whether the energy efficiency predicted amount is in a preset power supply interval, if so, obtaining excessive electric energy, and if so, obtaining electric energy loss;
If the energy efficiency predicted quantity is in the power supply interval, determining a positive difference quantity or a negative difference quantity between an optimal value and the energy efficiency predicted quantity in the power supply interval by using an attention mechanism;
determining a tuning amount of the predicted energy efficiency amount by the positive difference amount or the negative difference amount, and correspondingly identifying the predicted tuning amount between the predicted consumption amount and the predicted increase amount based on the tuning amount;
and identifying consumption prediction amounts and addition increase or addition decrease of the increase prediction amounts of the lines and the nodes in each area of the distributed energy network by adopting the prediction optimization quantity, so as to obtain optimized prediction nodes and optimized prediction lines of the lines and the nodes in each area according to the basic electric energy scheduling program.
3. The optimal scheduling method for a virtual power plant according to claim 1, wherein determining an intra-day scheduling satisfaction of the virtual power schedule using a rolling time domain program comprises:
measuring the time period for realizing virtual power scheduling by adopting the power transmission speed of the distributed energy network preset by the rolling time domain program;
and judging whether the time period accords with the intra-day scheduling establishment in a preset time day or not.
4. The optimal scheduling method of a virtual power plant according to claim 1, wherein the step of executing an actual power scheduler corresponding to a virtual power schedule based on the framework of the base power scheduler comprises:
and generating an actual power schedule corresponding to the virtual power schedule based on the basic power schedule program so as to perform a power schedule process of the distributed energy network according to the actual power schedule.
5. An optimized scheduling device for a virtual power plant, comprising:
the identification unit is used for identifying the electric energy richness of the current timestamp of the distributed energy network by adopting a pre-trained ARIMA model and generating a basic electric energy scheduling program based on the electric energy richness;
the grid unit is used for inputting the basic electric energy scheduling program and the electric energy abundance into a preset load prediction model so as to output an optimized prediction node and an optimized prediction line through the load prediction model, wherein the optimized prediction node and the optimized prediction line are nodes and lines which can be optimally scheduled in electric energy prediction in a distributed energy network with a current time stamp respectively;
the judging unit is used for carrying out virtual power scheduling corresponding to the optimized prediction node and the optimized prediction line on the virtual energy network by adopting a preset online optimization model through a mixed integer linear program, and judging the intra-day scheduling establishment of the virtual power scheduling through a rolling time domain program, wherein the virtual energy network is formed by digitizing a distributed energy network;
The execution unit is used for executing an actual power dispatching program corresponding to virtual power dispatching under the framework of the basic power dispatching program if the virtual power dispatching is established;
the ARIMA model identifies the electrical energy abundance of a current timestamp of a distributed energy network, comprising:
acquiring energy network data of a current time stamp, wherein the energy network data comprises electric energy production capacity, electric energy consumption capacity, electric energy output capacity and cable load;
performing time sequence fitting on the energy network data based on an ARIMA model to perform fitting verification on the energy network data, wherein the time sequence fitting comprises data item comparison on the energy network data and historical energy data to target each energy item in the energy network data;
performing autoregressive processing on each energy fine item by using a modeling list method of an ARIMA model through the calibrated each energy fine item to generate the electric energy richness represented by a list, wherein the autoregressive processing comprises classifying each energy fine item to classify the electric energy richness of each region in a distributed energy network;
generating a base power scheduler based on the power richness, comprising:
determining an electric energy surplus region and an electric energy missing region of each region on the distributed energy network according to the electric energy abundance;
Programming a power control carrier PLC (programmable logic controller) aiming at an electric energy excess region and an electric energy deficiency region through a preset power scheduling strategy, and generating a basic electric energy scheduling program for transferring the energy of the electric energy excess region to the electric energy deficiency region, wherein the preset power scheduling strategy is a preset safety scheduling strategy and comprises energy transfer efficiency and transfer paths;
and carrying out virtual power scheduling corresponding to the optimized prediction node and the optimized prediction line on the virtual energy network by adopting a preset online optimization model and utilizing a mixed integer linear program, wherein the method comprises the following steps of:
performing discrete point identification and circuit path identification, and virtually constructing a virtual energy network matched with the distributed energy network;
carrying out power grid structure topology on the virtual energy network based on each discrete point and each circuit path so as to configure electric parameters corresponding to each discrete point and each circuit path;
and determining parameter data of nodes and paths of a power grid topological structure of the virtual energy network according to the electrical parameters of each discrete point and the circuit path, so as to perform virtual power scheduling corresponding to the optimized prediction nodes and the optimized prediction lines on the virtual energy network according to the mixed integer linear program.
6. A computer device comprising a memory and a processor, the memory having stored therein a computer program, characterized in that the processor, when executing the computer program, implements the steps of the method for optimized scheduling of a virtual power plant according to any one of claims 1 to 4.
7. A computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when being executed by a processor, implements the steps of the method for optimized scheduling of a virtual power plant according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310879567.XA CN116596286B (en) | 2023-07-18 | 2023-07-18 | Optimized scheduling method, device and equipment for virtual power plant and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310879567.XA CN116596286B (en) | 2023-07-18 | 2023-07-18 | Optimized scheduling method, device and equipment for virtual power plant and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116596286A CN116596286A (en) | 2023-08-15 |
| CN116596286B true CN116596286B (en) | 2024-04-16 |
Family
ID=87590363
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310879567.XA Active CN116596286B (en) | 2023-07-18 | 2023-07-18 | Optimized scheduling method, device and equipment for virtual power plant and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116596286B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117318110B (en) * | 2023-11-28 | 2024-03-08 | 惠州市长晟科技有限公司 | Distributed micro electric energy storage system, method, computer equipment and storage medium |
| CN117827933B (en) * | 2024-01-02 | 2024-06-07 | 北京易成慧众能源科技有限公司 | Power transaction data graph generation method and system |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103824134A (en) * | 2014-03-06 | 2014-05-28 | 河海大学 | Two-stage optimized dispatching method for virtual power plant |
| CN109066690A (en) * | 2018-09-13 | 2018-12-21 | 福建省农村信用社联合社 | A kind of regional power supply dispatching method for producing electricity consumption |
| CN110416998A (en) * | 2019-07-01 | 2019-11-05 | 华北电力大学 | A kind of complicated distribution scheduling Control management system in area based on virtual power plant |
| CN113852135A (en) * | 2021-09-22 | 2021-12-28 | 广东电网有限责任公司 | Virtual power plant energy scheduling method, device, storage medium and platform |
| CN114037191A (en) * | 2022-01-07 | 2022-02-11 | 深圳江行联加智能科技有限公司 | Virtual power plant optimal scheduling method, device, equipment and medium based on big data |
| CN114139780A (en) * | 2021-11-16 | 2022-03-04 | 国网山西省电力公司电力科学研究院 | Coordinated optimization method and system for virtual power plant and power distribution network containing distributed power supply |
| CN114977330A (en) * | 2022-07-11 | 2022-08-30 | 湖南大学 | Building distributed photovoltaic-storage battery system continuous operation scheduling method and platform |
| CN115759317A (en) * | 2022-06-09 | 2023-03-07 | 国网天津市电力公司 | Power load regulation and control method and device, electronic equipment and storage medium |
| CN115983612A (en) * | 2023-03-20 | 2023-04-18 | 国网安徽省电力有限公司合肥供电公司 | Distributed source network load storage scheduling optimization method based on virtual power plant |
| CN116207739A (en) * | 2023-05-04 | 2023-06-02 | 南方电网数字电网研究院有限公司 | Optimal scheduling method and device for power distribution network, computer equipment and storage medium |
-
2023
- 2023-07-18 CN CN202310879567.XA patent/CN116596286B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103824134A (en) * | 2014-03-06 | 2014-05-28 | 河海大学 | Two-stage optimized dispatching method for virtual power plant |
| CN109066690A (en) * | 2018-09-13 | 2018-12-21 | 福建省农村信用社联合社 | A kind of regional power supply dispatching method for producing electricity consumption |
| CN110416998A (en) * | 2019-07-01 | 2019-11-05 | 华北电力大学 | A kind of complicated distribution scheduling Control management system in area based on virtual power plant |
| CN113852135A (en) * | 2021-09-22 | 2021-12-28 | 广东电网有限责任公司 | Virtual power plant energy scheduling method, device, storage medium and platform |
| CN114139780A (en) * | 2021-11-16 | 2022-03-04 | 国网山西省电力公司电力科学研究院 | Coordinated optimization method and system for virtual power plant and power distribution network containing distributed power supply |
| CN114037191A (en) * | 2022-01-07 | 2022-02-11 | 深圳江行联加智能科技有限公司 | Virtual power plant optimal scheduling method, device, equipment and medium based on big data |
| CN115759317A (en) * | 2022-06-09 | 2023-03-07 | 国网天津市电力公司 | Power load regulation and control method and device, electronic equipment and storage medium |
| CN114977330A (en) * | 2022-07-11 | 2022-08-30 | 湖南大学 | Building distributed photovoltaic-storage battery system continuous operation scheduling method and platform |
| CN115983612A (en) * | 2023-03-20 | 2023-04-18 | 国网安徽省电力有限公司合肥供电公司 | Distributed source network load storage scheduling optimization method based on virtual power plant |
| CN116207739A (en) * | 2023-05-04 | 2023-06-02 | 南方电网数字电网研究院有限公司 | Optimal scheduling method and device for power distribution network, computer equipment and storage medium |
Non-Patent Citations (1)
| Title |
|---|
| 蒋惠凤.《中长期电力负荷预测技术与应用》.东南大学出版社,2016,第128-130页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116596286A (en) | 2023-08-15 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116596286B (en) | Optimized scheduling method, device and equipment for virtual power plant and storage medium | |
| US10504195B2 (en) | System and method for decentralized energy production | |
| JP2023129546A (en) | System and method for optimal control of energy storage system | |
| Catalão et al. | Optimal offering strategies for wind power producers considering uncertainty and risk | |
| EP3471029A1 (en) | Method for automatic cloud control of energy storage systems | |
| US20220373989A1 (en) | System for configuring demand response for energy grid assets | |
| Ruelens et al. | Demand side management of electric vehicles with uncertainty on arrival and departure times | |
| CN112508306A (en) | Self-adaptive method and system for power production configuration | |
| Nazemi et al. | A mixed-integer distributionally robust chance-constrained model for optimal topology control in power grids with uncertain renewables | |
| CN117895513B (en) | Power grid regulation and control method, system, equipment and medium based on power transaction analysis | |
| CN118117668A (en) | Cold region comprehensive energy optimal scheduling method based on wind energy and solar energy | |
| CN113690885A (en) | Power supply control method and power supply platform | |
| JP2020039222A (en) | Power supply-demand control device, power supply-demand control system, and power supply-demand control method | |
| Esmaeeli et al. | Determination of optimal reserve contribution of thermal units to afford the wind power uncertainty | |
| CN117879059A (en) | Optimizing scheduling method and device for new energy power grid, computer equipment and medium | |
| Urbano et al. | Energy infrastructure of the factory as a virtual power plant: Smart energy management | |
| CN117595398A (en) | Power system flexibility optimization method and device | |
| Anders et al. | Proactive guidance for dynamic and cooperative resource allocation under uncertainties | |
| EP4027474A1 (en) | Power control device and power control method | |
| Nikovski et al. | Factored markov decision process models for stochastic unit commitment | |
| Gao et al. | A review of different methodologies for solving the problem of wind power's fluctuation | |
| CN113298329A (en) | Training and strategy generating method, system, computer device and storage medium | |
| Minhas | Load balancing in smart dc micro-grid using delay tolerant user demands | |
| CN118333338B (en) | Data processing method and system of charging management platform | |
| CN118014318B (en) | Dynamic management method and device for electric power energy demand based on multi-energy 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 |