CN116365606B - High-proportion renewable energy source consumption optimization method - Google Patents

High-proportion renewable energy source consumption optimization method Download PDF

Info

Publication number
CN116365606B
CN116365606B CN202310643050.0A CN202310643050A CN116365606B CN 116365606 B CN116365606 B CN 116365606B CN 202310643050 A CN202310643050 A CN 202310643050A CN 116365606 B CN116365606 B CN 116365606B
Authority
CN
China
Prior art keywords
information
real
time
decision
node
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
Application number
CN202310643050.0A
Other languages
Chinese (zh)
Other versions
CN116365606A (en
Inventor
徐雪松
徐凯
曾子洋
唐加乐
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Hunan University of Technology
Original Assignee
Hunan University of Technology
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Hunan University of Technology filed Critical Hunan University of Technology
Priority to CN202310643050.0A priority Critical patent/CN116365606B/en
Publication of CN116365606A publication Critical patent/CN116365606A/en
Application granted granted Critical
Publication of CN116365606B publication Critical patent/CN116365606B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Classifications

    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/38—Arrangements for parallely feeding a single network by two or more generators, converters or transformers
    • H02J3/46—Controlling of the sharing of output between the generators, converters, or transformers
    • H02J3/466—Scheduling the operation of the generators, e.g. connecting or disconnecting generators to meet a given demand
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/23—Updating
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F30/00—Computer-aided design [CAD]
    • G06F30/20—Design optimisation, verification or simulation
    • G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/04—Circuit arrangements for ac mains or ac distribution networks for connecting networks of the same frequency but supplied from different sources
    • H02J3/06—Controlling transfer of power between connected networks; Controlling sharing of load between connected networks
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J3/00—Circuit arrangements for ac mains or ac distribution networks
    • H02J3/28—Arrangements for balancing of the load in a network by storage of energy
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F2113/00—Details relating to the application field
    • G06F2113/04—Power grid distribution networks
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
    • H02J2203/10—Power transmission or distribution systems management focussing at grid-level, e.g. load flow analysis, node profile computation, meshed network optimisation, active network management or spinning reserve management
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2203/00—Indexing scheme relating to details of circuit arrangements for AC mains or AC distribution networks
    • H02J2203/20—Simulating, e g planning, reliability check, modelling or computer assisted design [CAD]
    • H—ELECTRICITY
    • H02—GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02J—CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
    • H02J2300/20—The dispersed energy generation being of renewable origin
    • H02J2300/22—The renewable source being solar energy
    • H02J2300/24—The renewable source being solar energy of photovoltaic origin
    • 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
    • H02J2300/00—Systems for supplying or distributing electric power characterised by decentralized, dispersed, or local generation
    • H02J2300/20—The dispersed energy generation being of renewable origin
    • H02J2300/28—The renewable source being wind energy
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
    • Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
    • Y04S10/00—Systems supporting electrical power generation, transmission or distribution
    • Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications

Abstract

The application relates to a high-proportion renewable energy source consumption optimization method, which comprises the following steps: s1: establishing a network model of a renewable energy consumption system of a block chain micro-grid; the operation of the device is divided into a day-ahead stage and a day-middle stage; day before stage, S2: collecting equipment history information, and generating an objective function based on the equipment history information; solving the objective function to obtain pre-decision information; stage in day, S3: collecting real-time information of equipment; updating the pre-decision information at the current moment based on the real-time information of the equipment; solving the compensation decision information at the next moment; s4: calculating real-time decision information of the next moment in real time based on the updated pre-decision information and the compensation decision information; s5: and carrying out digestion decision guidance on the equipment at the next moment based on the real-time decision information at the next moment. The high-proportion renewable energy source absorption optimization method provided by the application can realize the efficient absorption of renewable energy sources.

Description

High-proportion renewable energy source consumption optimization method
Technical Field
The application relates to the technical field of renewable energy consumption optimization, in particular to a high-proportion renewable energy consumption optimization method.
Background
The micro-grid is a novel power system relative to the traditional energy network, and is an energy network which is composed of renewable energy sources such as various wind power, photovoltaic and other power equipment according to a certain topological structure and can independently operate or be interconnected with the traditional energy network. The micro-grid is an important form of accessing the distributed renewable energy source into the main network, and is a key link for improving the capacity of renewable energy source digestion. The blockchain has a distributed and disclosed non-tamperable regional co-treatment mode, and can make great contribution to the formulation and execution optimization of renewable energy consumption decisions in a micro-grid scene.
The traditional energy network energy management mode is centralized, and the output mode cannot be efficiently consumed, so that renewable energy with high uncertainty and random characteristics can be obtained. In the existing novel power system technology taking the micro-grid as the renewable energy grid-connected interface, the high-efficiency absorption of renewable energy cannot be realized because the renewable energy historical data is not abundant, the description of the absorption model is inaccurate, and the high-time delay is solved by the multi-objective model.
Disclosure of Invention
Based on the above, it is necessary to provide a renewable energy consumption optimization method based on a micro-grid two-stage model, specifically a high-proportion renewable energy consumption optimization method, aiming at the defects of the prior art.
The invention provides a high-proportion renewable energy source consumption optimization method, which comprises the following steps:
s1: establishing a network model of a renewable energy consumption system of a block chain micro-grid; the operation of the device is divided into a day-ahead stage and a day-middle stage;
in the early stage of the day,
s2: collecting equipment history information, and generating an objective function based on the equipment history information; solving the objective function to obtain pre-decision information;
in the middle of the day period, the time of day,
s3: collecting real-time information of equipment; updating the pre-decision information at the current moment based on the real-time information of the equipment; solving the compensation decision information at the next moment;
s4: calculating real-time decision information of the next moment in real time based on the updated pre-decision information and the compensation decision information;
s5: and carrying out digestion decision guidance on the equipment at the next moment based on the real-time decision information at the next moment.
The high-proportion renewable energy source consumption optimization method provided by the invention solves the problems of low renewable energy source historical data, inaccurate consumption model description, high time delay of solving a multi-objective model and the like in the existing novel power system technology, and can realize the efficient consumption of renewable energy sources.
Drawings
In order to more clearly illustrate the embodiments of the application 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 application, 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 flow chart of a high-ratio renewable energy consumption optimization method according to an embodiment of the present application.
Detailed Description
In order that the above objects, features and advantages of the application will be readily understood, a more particular description of the application will be rendered by reference to the appended drawings. In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application. The present application may be embodied in many other forms than described herein and similarly modified by those skilled in the art without departing from the spirit of the application, whereby the application is not limited to the specific embodiments disclosed below.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "plurality" means at least two, for example, two, three, etc., unless specifically defined otherwise.
As shown in fig. 1, the present embodiment provides a high-proportion renewable energy consumption optimization method, which includes:
s1: establishing a network model of a renewable energy consumption system of a block chain micro-grid; its operation is divided into a pre-day stage and an mid-day stage.
Specifically, the network model of the renewable energy consumption system of the blockchain micro-grid comprises a consumption decision information acquisition center node set, a consumption decision optimization calculation center node set and a consumption decision guiding center scheduling node set;
the consumption decision information acquisition center node set comprises a consumption decision day-ahead information acquisition center node set and a consumption decision real-time information acquisition center node set;
the node set of the information acquisition center before the consumption decision is recorded as follows:
；
wherein ,representing a day-ahead information acquisition node of a wind generating set, < >>Representing solar information acquisition node of photovoltaic generator set, < ->Representing the limited set of information acquisition nodes before the day of the traditional thermal power generating unit, and +.>Limited set of information acquisition nodes before daily representing local load>Representing a limited set of day-ahead information collection nodes of the energy storage device, < >>Representing a limited set of information acquisition nodes before the day of the power grid tide, < ->Representing the finite element set of the traditional thermal power generating unit, < - >Representing a finite element set of the energy storage device model, +.>Representing a local load model finite element set, < ->Representing a finite element set of the power grid tide model,crepresent the firstcA traditional thermal power generating unit is arranged;drepresent the firstdA local load model;srepresent the firstsA plurality of energy storage device models;lrepresenting the first grid power flow model.
Further, the day-ahead information acquisition node of the wind generating set is expressed as:
；
wherein ,indicating that wind generating set generates intelligent contract against network, < ->Intelligent contracts for representing historical data collection of wind generating set, < ->Is->An information queue maintained by a day-ahead information acquisition node of the wind generating set; />Indicating that the wind generating set is intActual output power at moment +.>Indicating that the photovoltaic generator set is intMaximum output power at a moment;
the solar-day-front information acquisition node of the photovoltaic generator set is expressed as:
；
wherein ,indicating that photovoltaic generator set generates intelligent contract against network, < ->Intelligent contract for representing historical data collection of photovoltaic generator set>Is->An information queue maintained by a solar information acquisition node of the photovoltaic generator set; />Indicating that the photovoltaic generator set is intActual output power at moment +.>Indicating that the photovoltaic generator set is intMaximum output power at a moment; / >Representing a set of time finite elements;
the limited set of the day-ahead information acquisition nodes of the traditional thermal power generating unit is expressed as:
；
wherein ,the historical data collection intelligent contract of the traditional thermal generator set is represented; the other parameters are information queues maintained by a limited set of information acquisition nodes of the traditional thermal power generating unit before the day; />、/>、/>Respectively represent the traditional thermal power generating setcAt the position oftActual output power, minimum output power and maximum processing power at moment; />Represents a traditional thermal power generating setcAt the position oftOperating state at time ∈>、/>Respectively represent the traditional thermal power generating setcAt the position oftOperating the switching state at the moment; />、/>Respectively represent the traditional thermal power generating setcForce-exerting climbing constraint; />、/>Respectively represent the traditional thermal power generating setcForce output climbing constraint under a switching state;
the local load day-ahead information acquisition node finite set is expressed as:
；
wherein ,intelligent representation local load history data collectionContract (S)>An information queue maintained for a limited set of local load day-ahead information acquisition nodes; />、/>、/>Respectively represent local load modelsdAt the position oftReal load power, minimum load power and maximum load power at moment; />、/>Respectively represent local load modelsdMaximum downhill load power, maximum uphill load power;
The limited set of the information acquisition nodes before the day of the energy storage equipment is expressed as:
；
wherein ,representing an energy storage device historical data collection intelligent contract;an information queue maintained for a limited set of information acquisition nodes of the energy storage device before the day; />、/>、/>Respectively represent energy storage equipment modelssAt the position oftTime actual storage, minimum storage limit and maximum storage limit; />、/>、/>Respectively represent energy storage equipment modelssAt the position oftExchanging power, discharging power and charging power at moment; />、/>Respectively represent energy storage equipment modelssA discharge damping coefficient and a charge damping coefficient of the vehicle; />Representing an energy storage device activation time; />Representing a finite element set of the energy storage device model;
the limited set of the power grid tide day-ahead information acquisition nodes is expressed as:
；
wherein ,an intelligent contract is acquired for the power grid tide history data,is->An information queue maintained by a limited set of information acquisition nodes before the daily trend of the power grid; />、/>、/>Respectively represent the power flow model of the power gridlAt the position oftActual transmission power, minimum transmission power and maximum transmission power at the moment; />、/>Respectively represent the power flow model of the power gridlAt the position oftThe moment actually outputs the node, the receiving node; />Representing nodes in power flow of power gridqAt the position oftThe actual voltage angle at the moment; />Model for representing power flow of power gridlResistance value of (2); / >Model for representing power flow of power gridlIs used for the transmission coefficient of the transmission coefficient(s).
The consumption decision real-time information acquisition center node set is recorded as follows:
；
wherein ,representing real-time information acquisition node of wind generating set, < >>Representing real-time information acquisition node of photovoltaic generator set, < >>Representing the limited set of real-time information acquisition nodes of the traditional thermal power generating unit>Representing local load real-time information acquisition node finite set, < ->For the finite set of energy storage equipment real-time information acquisition nodes, < >>And the power grid tide real-time information acquisition node finite set is represented.
Further, the real-time information acquisition node of the wind generating set is expressed as:
；
wherein ,collecting intelligent contracts for real-time data of wind generating sets in real time, < >>Is a wind generating settReal-time output power at the moment; real-time information acquisition node through wind generating set>Real-time data acquisition intelligent contract of upper wind generating set>The intelligent algorithm automatically collects and maintains the real-time information queue +.>；
The real-time information acquisition node of the photovoltaic generator set is expressed as:
；
wherein ,intelligent contracts are collected for real-time data of photovoltaic generator sets in real time, < >>Is a photovoltaic generator settReal-time output power at the moment; real-time information acquisition node through photovoltaic generator set >Intelligent contract for collecting real-time data of upper photovoltaic generator set in real time>The intelligent algorithm automatically collects and maintains real-time information queues in real time；
The traditional thermal power generating unit real-time information acquisition node finite set is expressed as:
；
wherein ,intelligent contract for real-time data acquisition of traditional thermal power generating unit>Is a traditional thermal power generating setcAt the position oftReal-time output power at time, +.>Is a traditional thermal power generating setcAt the position oftThe real-time output state is under the moment,、/>is a traditional thermal power generating setcAt the position oftThe real-time output switching state is realized at the moment; real-time information acquisition node limited set through traditional thermal power generating unit>Intelligent contract for collecting real-time data of traditional thermal power generating unit in real time>The intelligent algorithm automatically collects and maintains real-time information queues in real time。
The local load real-time information acquisition node finite set is expressed as:
；
wherein ,collecting intelligent contracts for local load real-time data in real time, < >>For local loaddAt the position oftReal-time load power at the moment; specifically, real-time information acquisition node finite set through local load +.>Intelligent contract for collecting real-time data of upper local load in real time>The intelligent algorithm automatically collects and maintains real-time information queues in real time 。
The power grid tide real-time information acquisition node finite set is expressed as:
；
wherein ,collecting intelligent contracts for real-time data of power grid tide in real time>For the power flow of the electric networklAt the position oftReal-time transmission power at a time instant; collecting node finite set through power grid tide real-time information>Intelligent contract for collecting real-time data of power flow of upper power grid in real time>The intelligent algorithm automatically collects and maintains the real-time information queue +.>。
The consumption decision optimization computing center node set is recorded as follows:
；
wherein ,target optimization calculation center node representing day-ahead stage multi-target model>Representing a multi-objective deep reinforcement learning optimization computation center node, < ->Representing a crowd algorithm optimizing computation center node, ++>And representing the central node of the multi-target deep reinforcement learning optimization calculation of the daily roller.
The consumption decision guiding center scheduling node set is recorded as:
；
wherein ,value driving center dispatching node representing limited set of traditional thermal power generating unit>Value driven hub dispatch node representing local load finite set,/a value driven hub dispatch node representing local load finite set>Information driven central dispatch node representing a finite set of energy storage devices,>information driven central dispatch node representing a limited set of grid flows +.>An information driven central dispatch node for a limited set of renewable energy sources, denoted +. >，/>Information driven central dispatch node representing a wind park,/->Information representing the photovoltaic generator set drives the central dispatch node.
In the early stage of the day,
s2: collecting equipment history information, and generating an objective function based on the equipment history information; and solving the objective function to obtain pre-decision information.
Specifically, the equipment history information comprises wind generating set output history data, photovoltaic generating set output history data, traditional thermal power generating set output history data, local load absorption capacity history data, energy storage capacity history data of energy storage equipment and power grid tide history data;
the output historical data of the wind generating set is automatically acquired by a wind generating set historical data acquisition intelligent contract in a wind generating set day-ahead information acquisition node;
the photovoltaic generator set output historical data is automatically acquired by a photovoltaic generator set historical data acquisition intelligent contract in a photovoltaic generator set day-ahead information acquisition node;
the traditional thermal power generating unit output historical data is automatically acquired by traditional thermal power generating unit historical data acquisition intelligent contracts with limited and concentrated traditional thermal power generating unit day-ahead information acquisition nodes;
The local load absorption capacity historical data is automatically acquired by a local load historical data acquisition intelligent contract in a limited set of local load day-ahead information acquisition nodes;
the energy storage capacity historical data of the energy storage equipment are automatically acquired by an intelligent contract for acquiring the historical data of the energy storage equipment, wherein the historical data of the energy storage equipment is collected in a limited set of information acquisition nodes before the date of the energy storage equipment;
and the power grid power flow historical data is automatically acquired by a power grid power flow historical data acquisition intelligent contract in a limited set of power grid power flow daily information acquisition nodes.
Further, generating the objective function by the nodes in the consumption decision optimization computing center node set based on the equipment history information includes:
step 1: collecting constraint information through the day-ahead stage multi-target model target optimization computing center node; the constraint information comprises wind generating set constraint, photovoltaic generating set constraint, traditional thermal power generating set constraint, local load constraint, energy storage equipment constraint and power grid tide constraint;
the constraint of the wind generating set is as follows:，/>；
the constraint of the photovoltaic generator set is as follows:，/>；
the constraint of the traditional thermal power generating unit is as follows:
，/>，/>；
；
；
；
；
；
wherein ,、/>、/>respectively represent the traditional thermal power generating setcAt the position oftActual output power, minimum output power and maximum processing power at moment, wherein the unit is Kw; / >Represents a traditional thermal power generating setcAt the position oftThe running state under the moment of time is that,、/>respectively represent the traditional thermal power generating setcAt the position oftOperating the switching state at the moment; />、/>Respectively represent the traditional thermal power generating setcThe output climbing constraint is carried out, and the unit is Kw; />、/>Respectively represent the traditional thermal power generating setcAnd the unit of the force climbing constraint under the switching state is Kw.
Further, whenRepresents a traditional thermal power generating setcAt the position oftThe device is in an operation state at the moment; when (when)Represents a traditional thermal power generating setcAt the position oftIs in a closed state at the moment,
further, whenRepresents a traditional thermal power generating setcAt the position oftSwitching from a start-up state to a shut-down state at moment; when->Represents a traditional thermal power generating setcAt the position oftThe time is not converted from the starting state to the closing state,
further, whenRepresents a traditional thermal power generating setcAt the position oftSwitching from the off state to the on state at the moment; when->Represents a traditional thermal power generating setcAt the position oftThe time is not converted from the off state to the on state.
The local load constraints are:
，/>，/>；
；
wherein ,、/>、/>respectively represent local load modelsdAt the position oftReal load power, minimum load power and maximum load power at moment, wherein the unit is Kw; />、/>Respectively represent local load models dMaximum downhill load power, maximum uphill load power in Kw.
The energy storage device is constrained as follows:
，/>，/>；
；
；
；
；
wherein ,、/>、/>respectively represent energy storage equipment modelssAt the position oftThe unit of the moment actual storage amount, the minimum storage limit and the maximum storage limit is Kwh; />、/>、/>Respectively represent energy storage equipment modelssAt the position oftThe time exchange power, the discharge power and the charging power are in Kw; />、/>Respectively represent energy storage equipment modelssA discharge damping coefficient and a charge damping coefficient of the vehicle; />Representing a period of time in h;t 0 indicating the energy storage device activation time.
The power grid tide constraint is as follows:
，/>，/>；
；
；
wherein ,、/>、/>respectively represent the power flow model of the power gridlAt the position oftThe unit of the real transmission power, the minimum transmission power and the maximum transmission power at the moment is Kw;s(l)t、c(l)trespectively represent the power flow model of the power gridlAt the position oftThe moment actually outputs the node, the receiving node; />Representing nodes in power flow of power gridqAt the position oftThe actual voltage angle at the moment is rad; />Model for representing power flow of power gridlResistance value of (2) in->；/>Model for representing power flow of power gridlTransmission coefficient of (1) in KV 2 /rad；/>Representing a finite set of node elements in the power flow of the power grid.
Step 2: determining a lowest running cost objective function of the micro-grid, a lowest waste wind and light rate objective function in the micro-grid and a lowest exchange power frequency objective function of the micro-grid and the main network piece based on the constraint information and the equipment history information;
Further, the minimum objective function calculation formula of the running cost of the micro-grid is as follows:
；
wherein ,、/>、/>、/>、/>、/>respectively representtLocal load electricity consumption cost, main network electricity purchasing cost and traditional thermal power generating unit at momentcGenerating cost and traditional thermal power generating unitcStarting cost and traditional thermal power generating unitcParking cost and power grid tidelThe transmission cost is as follows: meta/Kwh.
The calculation formula of the lowest objective function of the wind and light rejection rate in the micro-grid is as follows:
；
the minimum objective function calculation formula of the micro-grid-main network element exchange power frequency is as follows:
；
；
wherein ,representing a microgrid model intAnd adding exchange power with the main network at the moment, wherein the unit is kw.
Step 3: and combining the lowest running cost objective function of the micro-grid, the lowest wind and light rejection rate objective function in the micro-grid and the lowest exchange power frequency objective function of the micro-grid-main network element, and minimizing the functions to generate the objective function.
Further, solving the objective function to obtain pre-decision information includes:
step 1: the crowd-sourcing algorithm optimizing calculation center node adopts the crowd-sourcing algorithm to carry out iterative solution on the objective function to obtain a first solving result; the iterative solution calculation formula is as follows:
；
；
；
Wherein min represents minimization;represent the firstτ+1 iterative microgrid operation cost minimum objective function; />Represent the firstτ+1 iterative minimum objective function of wind and light rejection rate in the micro-grid; />Represent the firstτ+1 iterative microgrid-main network element exchange power frequency minimum objective function; />Represent the firstτThe micro-grid operation cost of the iteration is the lowest objective function; />Represent the firstτThe lowest objective function of the wind and light rejection rate in the micro-grid of the secondary iteration; />Represent the firstτThe micro-grid-main network element exchange power frequency of the secondary iteration is the lowest objective function; />Representing an objective function;
further, for each optimization objective in a solution process, i.e. in iterationτMicro-grid operation cost at timeMinimum, within micro-grid, wind-discarding and light-discarding rate->Minimum, micro-grid-main-grid exchange power frequency +>At the lowest, iterative solution is carried out on the inside of each optimization target through a swarm intelligence algorithm, and the swarm intelligence algorithm is specifically as follows:
；
wherein ,representing individualsnFirst, theτSolving a decision value in the optimization target in the generation +1; />And->Two population intelligent decisions, namely an individual decision and a population decision; />Is [0,1]Random numbers in between;wgradually decreasing from 1 to 0 along with the iteration times; specific individual decision- >And population decision->The method comprises the following steps:
；
wherein ,βindicating the extent to which individual decisions affect the population,is [0,1]Random numbers in between; />Representing population to individualsnA range of influence in the optimization objective; />Representing the currentτAnd substituting the global optimal solution under the optimization target.
；
wherein ,γrepresenting the diffusion range of population decision affecting populations;representing individualsnFirst, theτInstead, the decision value in the optimization objective is solved.
Step 2: the multi-objective deep reinforcement learning optimization computing center node takes the first solving result as experience guidance, and carries out secondary solving on the objective function through multi-objective deep reinforcement learning to obtain pre-decision information;
the pre-decision information includes: the method comprises the steps of outputting pre-decision information of each time period of a wind generating set, outputting pre-decision information of each time period of a photovoltaic generating set, pre-state information of each time period of a traditional thermal power generating set, outputting pre-decision information, pre-energy storage information of each time period of an energy storage device model, pre-load information of each time period of a local load model and pre-transmission information of each time period of a power grid tide model.
In this embodiment, the wind generating set day-ahead information collection node includes a wind generating set generating a reactive network intelligent contract, where the wind generating set generating the reactive network intelligent contract is used to train the first generating reactive network model; inputting the output history data of the wind generating set into the trained first generation reactance network model to obtain predicted output information of the wind generating set; the wind generating set predicted force information is used for expanding the force history data of the wind generating set;
The photovoltaic generator set day-ahead information acquisition node comprises a photovoltaic generator set generation antagonism network intelligent contract, wherein the photovoltaic generator set generation antagonism network intelligent contract is used for training a second generation antagonism network model; inputting the output history data of the photovoltaic generator set into the trained second generation countermeasure network model to obtain predicted output information of the photovoltaic generator set; and the photovoltaic generator set predicted output information is used for expanding the photovoltaic generator set output historical data.
Further, the method comprises the steps of,、/>by adding noise, a sample data set +.>The method comprises the steps of carrying out a first treatment on the surface of the Generating a real data set from the history data by screening +.>The method comprises the steps of carrying out a first treatment on the surface of the Finally, the sample data set is treated by a discriminator D>And real data set->Judging the number; the judgment result is fed back to the generator G, and parameters of the generator G are adjusted through a gradient descent method; finally, a generator G which can generate a renewable energy output scene is obtained.
Input data is composed of historical data、/>The constructed renewable energy sunrise data (divided per hour);
the generator G in the generation process is constructed based on a self-attention mechanism model; the discriminator D is constructed based on a twin network model; the generated countermeasure network architecture is used for generating a renewable energy output scene; the training goal of generator G is to generate a sample dataset Is misidentified and classified by the arbiter D into the real dataset +.>In (a) and (b); the training object of the arbiter D is to identify the sample data generated by the generator G in the samples.
The neural network structure of generator D is as follows:
；
wherein ,zrepresenting the data from history、/>Adding noise to obtain a feature vector;P z z() representing feature vectorszProbability distribution of (2);Q(z)、K(z)、V(z) Respectively represent a query, a key and a value vector, allzObtaining after linear transformation;d k representation ofzIs a vector dimension, softmax (), representing the normalization function.
The neural network structure of the arbiter G composed of twin networks of MLP multilayer neurons is as follows:
；
；
；
；
wherein,、/>respectively representing the neuron characteristic training weights in a 1-level hidden layer and a 2-level hidden layer in a training generation data neural network in the twin network; />、/>Respectively representing neuron bias in a 1-level hidden layer and a 2-level hidden layer in a training generation data neural network in the twin network; />、/>Representing training in the twin network to generate an intermediate output vector and a result output vector of the data neural network; />、/>And representing intermediate output vectors and result output vectors of the training real data neural network in the twin network.
Training a data neural network generated in a discriminant G formed by a twin network consisting of MLP multi-layer neurons and training a real data neural network to use a cross entropy loss function as a loss function together, and updating the neural network by a gradient descent method 、/>、/>、/>、/>、/>、/>、/>Parameters, cross entropy loss function in the process are expressed as follows: />
；
Further, a generated countermeasure network model for generating a renewable energy output scene based on historical data is obtained through the generator G and the discriminator D, and model training targets are as follows:
；
and obtaining the predicted output information of the renewable energy wind generating set and the renewable energy photovoltaic generating set under the final uncertainty through the process.
In the middle of the day period, the time of day,
s3: collecting real-time information of equipment; updating the pre-decision information at the current moment based on the real-time information of the equipment; and solving the compensation decision information at the next moment.
Specifically, the device real-time information includes: real-time output data of a wind generating set, real-time output data of a photovoltaic generating set, real-time output data of a traditional thermal power generating set, real-time local load capacity consumption data, real-time storage capacity data of energy storage equipment and real-time power flow data of a power grid;
the real-time output data of the wind generating set is automatically acquired by a real-time data acquisition intelligent contract of the wind generating set in a real-time information acquisition node of the wind generating set;
the output real-time data of the photovoltaic generator set is automatically acquired by a photovoltaic generator set real-time data acquisition intelligent contract in a photovoltaic generator set real-time information acquisition node;
The real-time output data of the traditional thermal power generating set is automatically acquired by a traditional thermal power generating set real-time data acquisition intelligent contract with limited and concentrated real-time information acquisition nodes of the traditional thermal power generating set;
the local load absorption capacity real-time data is automatically acquired by a local load real-time data acquisition intelligent contract in a limited set of local load real-time information acquisition nodes;
the energy storage capacity real-time data of the energy storage device are automatically acquired by an energy storage device real-time data acquisition intelligent contract in a limited set of energy storage device real-time information acquisition nodes;
the power grid power flow real-time data is automatically acquired by a power grid power flow real-time data acquisition intelligent contract in a limited and concentrated mode of a power grid power flow real-time information acquisition node.
Further, the daily roller multi-target deep reinforcement learning optimization computation center node comprises a daily stage multi-target model construction intelligent contract, a multi-target deep reinforcement learning optimization computation intelligent contract and a daily roller guide information optimization computation intelligent contract; automatically collecting real-time information of the equipment at the current moment by constructing intelligent contracts through the mid-day stage multi-target modelUpdating the pre-decision information of the current moment by using the real-time information of the device of the current moment, and converting the time range from [ t,24]Modified to [t+1,24]；
Automatically solving the compensation decision information at the next moment through a multi-target deep reinforcement learning algorithm on the multi-target deep reinforcement learning optimization calculation intelligent contract; the compensation decision information of the next moment comprises: the method comprises the steps of outputting compensation decision information of a wind generating set at the next moment, outputting compensation decision information of a photovoltaic generating set at the next moment, compensating state information of a traditional thermal power generating set at the next moment, outputting compensation decision information, compensating energy storage information of energy storage equipment at the next moment, compensating load information of a local load model at the next moment and compensating transmission information of a power grid tide model at the next moment.
S4: real-time decision information of the next moment is calculated in real time based on the updated pre-decision information and the compensation decision information.
Specifically, based on the updated pre-decision information and the compensation decision information, the daily roller guide information optimally calculates intelligent contracts to automatically calculate real-time decision information at the next moment in real time; the real-time decision information of the next moment comprises: the method comprises the steps of outputting decision guiding information of a wind generating set at the next moment, outputting decision guiding information of a photovoltaic generating set at the next moment, real-time state information of a traditional thermal power generating set at the next moment, outputting decision guiding information, energy storage guiding information of energy storage equipment at the next moment, load guiding information of a local load model at the next moment and transmission power guiding information of a power grid tide model at the next moment.
The calculation formulas are as follows:
；
；
；
；
；
；
；
；
；
；
；
wherein,、/>respectively representing that the renewable energy source wind generating set and the photovoltaic generating set are obtainedtDecision guiding information of the output at the moment +1; />、/>、/>Respectively represent the acquisition of the traditional thermal power generating unittReal-time state guiding information of the machine set at the moment +1; />Indicating that the traditional thermal power generating unit is obtainedtDecision guiding information of the output at the moment +1; />、/>、/>Respectively representing the energy storage equipment modeltEnergy storage guiding information at time +1; />Representing local load model derivationtLoad guidance information at time +1; />Representing the power grid tide modeltTransmitting power steering information at time +1;αthe learning duty ratio representing the daily compensation decision is [0,1]I.e. whenαThe decision model considers more real-time information when approaching 1, whenαThe decision model takes more history information into account when approaching 0, typically taking 0.5./>
S5: and carrying out digestion decision guidance on the equipment at the next moment based on the real-time decision information at the next moment.
The method specifically comprises the following steps:
the information driving center dispatching node of the wind generating set guides the maximum output power of each period of the wind generating set based on the output decision guiding information of the next moment of the wind generating set;
the information driving center dispatching node of the photovoltaic generator set guides the maximum output power of each period of the photovoltaic generator set based on the output decision guiding information of the next moment of the photovoltaic generator set;
The occurrence of the 'waste wind and waste light' event can be avoided by guiding the wind generating set and the maximum output power of the photovoltaic generating set in each period.
The value driving center dispatching node of the limited set of the traditional thermal power generating unit carries out renewable energy source assisted digestion guide and load bottom guide on the traditional thermal power generating unit through value driving based on real-time state information and output decision guide information of the traditional thermal power generating unit at the next moment;
further, the method comprises the steps of,
；
；
；
；
；
；
wherein,、/>respectively represent the traditional thermal power generating setcAt the position oftThe renewable energy source under +1 time assists in the elimination cost and the load bottom cost, and the unit is: meta/Kwh; />Represents a traditional thermal power generating setcAt the position oftThe actual power generation cost at +1 time is given in units of: meta/Kwh; />、/>Respectively show that the traditional thermal power generator is intThe renewable energy source assistance absorption coefficient and the load bottom coefficient under the drive of the moment value, namely when the actual power generation is +>The lower the electricity is than the optimal decision power generation +.>Time->The coefficient can be gradually increased (up to 0.3), so that the load bottom cost is continuously increased, the power generation cost is increased, and the traditional thermal power generating unit is finally guidedcAt the position oftIncreasing the power generation power at the moment; when the actual power generation is + >The higher the electricity is than the optimal decision power generation +.>Time->The coefficient can be gradually increased (up to 0.3), so that the auxiliary consumption cost of renewable energy sources is continuously increased, the power generation cost is increased, and the traditional thermal power generating unit is finally guidedcAt the position oftReducing the power generation power at the moment; />Represents a traditional thermal power generating setcAt the position oftGuidance of value drives at the moment, i.e. when +.>Represents a traditional thermal power generating setcAt the position oftThe value is driven to be the bottom of the load pocket at the moment when +.>Represents a traditional thermal power generating setcAt the position oftThe value is driven to be renewable energy sources to assist in digestion at the moment.
The value driving center dispatching node of the local load finite set carries out renewable energy source consumption compensation guidance and overload consumption punishment guidance on the local load model through value driving based on load guiding information of the local load model at the next moment;
further, the method comprises the steps of,
；
；
；
；
；
wherein,、/>respectively represent local loadsdAt the position oftRenewable energy source absorption compensation and overload absorption penalty at +1 time, the units are: meta/Kwh; />Respectively represent local loadsdAt the position oftThe actual electricity cost at +1 time is given in: meta/Kwh; />、/>Respectively represent local loads intThe renewable energy source consumption compensation coefficient and the overload consumption penalty coefficient under the drive of the moment value, namely when the actual electric power is + >The lower the optimal decision power generation is +>Time->The coefficient is gradually increased (up to 0.3), so that the renewable energy consumption compensation is continuously increased, the electricity consumption cost is reduced, and the local load is finally guideddAt the position oftIncreasing the power consumption at the moment; when the actual electric power is +>The higher the optimal decision power generation +>Time->The coefficient is gradually increased (up to 0.3), so that the overload absorption penalty is continuously increased, the electricity consumption cost is increased, and the local load is finally guideddAt the position oftReducing the power consumption at the moment; />Representing local loaddAt the position oftGuidance of value drives at the moment, i.e. when +.>Representing local loaddAt the position oftThe value is driven to be a renewable energy consumption compensation coefficient under the moment when +.>Representing local loaddAt the position oftThe value driven under time is the overload absorbing penalty.
The information driving center scheduling node of the finite set of energy storage equipment carries out decision guiding on an energy storage equipment model through information driving based on energy storage guiding information of the energy storage equipment at the next moment, and assiststAnd the energy consumption of the renewable energy wind generating set and the renewable energy photovoltaic generating set at the time point of +1 reduces the consumption peak Gu Chashang in the time domain between the renewable energy generating set and the traditional thermal power generating set and the local load.
The information driving center dispatching node of the power grid power flow limited set carries out decision guiding on the power grid power flow model through information driving based on transmission power guiding information of the power grid power flow model at the next moment, and assiststAnd the energy consumption of the renewable energy wind generating set and the renewable energy photovoltaic generating set at the time of +1 compensates the information difference between the renewable energy generating set and the traditional thermal power generating set and between the renewable energy generating set and the local load on the space scheduling layer of physical equipment and a control system required by power grid tide power transmission, and the information difference is mobilized in advance, so that the execution time delay of the consumption decision is reduced.
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The above examples illustrate only a few embodiments of the application, which are described in detail and are not to be construed as limiting the scope of the claims. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the application, which are all within the scope of the application. Accordingly, the scope of protection of the present application is to be determined by the appended claims.

Claims (9)

1. A high-proportion renewable energy consumption optimization method, characterized by comprising:
s1: establishing a network model of a renewable energy consumption system of a block chain micro-grid; the operation of the device is divided into a day-ahead stage and a day-middle stage;
the network model of the renewable energy consumption system of the blockchain micro-grid comprises a consumption decision optimization computing center node set;
the consumption decision optimization computing center node set is recorded as follows:
；
wherein,target optimization calculation center node representing day-ahead stage multi-target model>Representing a multi-objective deep reinforcement learning optimization computation center node, < ->Representing a crowd algorithm optimizing computation center node, ++>Representing a multi-target deep reinforcement learning optimization calculation center node of the roller in the sun;
in the early stage of the day,
s2: collecting equipment history information, and generating an objective function based on the equipment history information; solving the objective function to obtain pre-decision information;
generating an objective function by the nodes in the consumption decision optimization computing center node set based on the equipment history information comprises:
step 1: collecting constraint information through the day-ahead stage multi-target model target optimization computing center node; the constraint information comprises wind generating set constraint, photovoltaic generating set constraint, traditional thermal power generating set constraint, local load constraint, energy storage equipment constraint and power grid tide constraint;
Step 2: determining a lowest running cost objective function of the micro-grid, a lowest waste wind and light rate objective function in the micro-grid and a lowest exchange power frequency objective function of the micro-grid and the main network piece based on the constraint information and the equipment history information;
step 3: combining the lowest objective function of the running cost of the micro-grid, the lowest objective function of the wind and light rejection rate in the micro-grid and the lowest objective function of the exchange power frequency of the micro-grid-main network element, and minimizing the functions to generate the objective function;
solving the objective function to obtain pre-decision information comprises:
step 1: the crowd-sourcing algorithm optimizing calculation center node adopts the crowd-sourcing algorithm to carry out iterative solution on the objective function to obtain a first solving result;
step 2: the multi-objective deep reinforcement learning optimization computing center node takes the first solving result as experience guidance, and carries out secondary solving on the objective function through multi-objective deep reinforcement learning to obtain pre-decision information;
in the middle of the day period, the time of day,
s3: collecting real-time information of equipment; updating the pre-decision information at the current moment based on the real-time information of the equipment; solving the compensation decision information at the next moment;
The daily roller multi-target deep reinforcement learning optimization computation center node comprises a daily stage multi-target model construction intelligent contract, a multi-target deep reinforcement learning optimization computation intelligent contract and a daily roller guide information optimization computation intelligent contract; automatically collecting real-time information of the equipment at the current moment by constructing an intelligent contract through the multi-objective model at the mid-day stage, updating the pre-decision information at the current moment by using the real-time information of the equipment at the current moment, and taking the time range from [t,24]Modified to [t+1,24]；
Automatically solving the compensation decision information at the next moment through a multi-target deep reinforcement learning algorithm on the multi-target deep reinforcement learning optimization calculation intelligent contract;
s4: calculating real-time decision information of the next moment in real time based on the updated pre-decision information and the compensation decision information;
s5: and carrying out digestion decision guidance on the equipment at the next moment based on the real-time decision information at the next moment.
2. The high-proportion renewable energy consumption optimization method according to claim 1, wherein in S1, the blockchain microgrid renewable energy consumption system network model further comprises a consumption decision information acquisition center node set and a consumption decision guide center scheduling node set;
The consumption decision information acquisition center node set comprises a consumption decision day-ahead information acquisition center node set and a consumption decision real-time information acquisition center node set;
the node set of the information acquisition center before the consumption decision is recorded as follows:
；
wherein,representing a day-ahead information acquisition node of a wind generating set, < >>Representing solar information acquisition node of photovoltaic generator set, < ->Representing the limited set of information acquisition nodes before the day of the traditional thermal power generating unit, and +.>Limited set of information acquisition nodes before daily representing local load>Representing a limited set of day-ahead information collection nodes of the energy storage device, < >>Representing a limited set of information acquisition nodes before the day of the power grid tide, < ->Representing the finite element set of the traditional thermal power generating unit, < ->Representing a finite element set of the energy storage device model, +.>Representing a local load model finite element set, < ->Representing a finite element set of the power grid tide model,crepresent the firstcA traditional thermal power generating unit is arranged;drepresent the firstdA local load model;srepresent the firstsA plurality of energy storage device models;lrepresenting a first power grid tide model;
the consumption decision real-time information acquisition center node set is recorded as follows:
；
wherein,representing real-time information acquisition node of wind generating set, < >>Representing real-time information acquisition node of photovoltaic generator set, < > >Representing the limited set of real-time information acquisition nodes of the traditional thermal power generating unit>Representing local load real-time information acquisition node finite set, < ->For the finite set of energy storage equipment real-time information acquisition nodes, < >>Representing a limited set of real-time information acquisition nodes of the power grid tide;
the consumption decision guiding center scheduling node set is recorded as:
；
wherein,value driving center dispatching node representing limited set of traditional thermal power generating unit>Value driven hub dispatch node representing local load finite set,/a value driven hub dispatch node representing local load finite set>Information driven central dispatch node representing a finite set of energy storage devices,>information driven central dispatch node representing a limited set of grid flows +.>An information driven central dispatch node for a limited set of renewable energy sources, denoted +.>，/>Information driven central dispatch node representing a wind park,/->Information representing the photovoltaic generator set drives the central dispatch node.
3. The high-proportion renewable energy consumption optimization method according to claim 2, wherein in S2, the equipment history information comprises wind generating set output history data, photovoltaic generating set output history data, traditional thermal power generating set output history data, local load absorption capacity history data, energy storage capacity history data of an energy storage device and power grid trend history data;
The output historical data of the wind generating set is automatically acquired by a wind generating set historical data acquisition intelligent contract in a wind generating set day-ahead information acquisition node;
the photovoltaic generator set output historical data is automatically acquired by a photovoltaic generator set historical data acquisition intelligent contract in a photovoltaic generator set day-ahead information acquisition node;
the traditional thermal power generating unit output historical data is automatically acquired by traditional thermal power generating unit historical data acquisition intelligent contracts with limited and concentrated traditional thermal power generating unit day-ahead information acquisition nodes;
the local load absorption capacity historical data is automatically acquired by a local load historical data acquisition intelligent contract in a limited set of local load day-ahead information acquisition nodes;
the energy storage capacity historical data of the energy storage equipment are automatically acquired by an intelligent contract for acquiring the historical data of the energy storage equipment, wherein the historical data of the energy storage equipment is collected in a limited set of information acquisition nodes before the date of the energy storage equipment;
and the power grid power flow historical data is automatically acquired by a power grid power flow historical data acquisition intelligent contract in a limited set of power grid power flow daily information acquisition nodes.
4. The high-proportion renewable energy consumption optimization method according to claim 3, wherein in S2, the iterative solution calculation formula is:
；
；
；
Wherein min represents minimization;represent the firstτ+1 iterative microgrid operation cost minimum objective function;represent the firstτ+1 iterative minimum objective function of wind and light rejection rate in the micro-grid; />Represent the firstτ+1 iterative microgrid-main network element exchange power frequency minimum objective function; />Represent the firstτThe micro-grid operation cost of the iteration is the lowest objective function; />Represent the firstτThe lowest objective function of the wind and light rejection rate in the micro-grid of the secondary iteration;represent the firstτThe micro-grid-main network element exchange power frequency of the secondary iteration is the lowest objective function; />Representing an objective function;
the pre-decision information includes: the method comprises the steps of outputting pre-decision information of each time period of a wind generating set, outputting pre-decision information of each time period of a photovoltaic generating set, pre-state information of each time period of a traditional thermal power generating set, outputting pre-decision information, pre-energy storage information of each time period of an energy storage device model, pre-load information of each time period of a local load model and pre-transmission information of each time period of a power grid tide model.
5. The high-proportion renewable energy consumption optimization method according to claim 4, wherein in S2, the wind turbine generator set day-ahead information collection node comprises a wind turbine generator set generation reactive network intelligent contract for training a first generation reactive network model; inputting the output history data of the wind generating set into the trained first generation reactance network model to obtain predicted output information of the wind generating set; the wind generating set predicted force information is used for expanding the force history data of the wind generating set;
The photovoltaic generator set day-ahead information acquisition node comprises a photovoltaic generator set generation antagonism network intelligent contract, wherein the photovoltaic generator set generation antagonism network intelligent contract is used for training a second generation antagonism network model; inputting the output history data of the photovoltaic generator set into the trained second generation countermeasure network model to obtain predicted output information of the photovoltaic generator set; and the photovoltaic generator set predicted output information is used for expanding the photovoltaic generator set output historical data.
6. The high-proportion renewable energy consumption optimization method according to claim 4, wherein in S3, the device real-time information includes: real-time output data of a wind generating set, real-time output data of a photovoltaic generating set, real-time output data of a traditional thermal power generating set, real-time local load capacity consumption data, real-time storage capacity data of energy storage equipment and real-time power flow data of a power grid;
the real-time output data of the wind generating set is automatically acquired by a real-time data acquisition intelligent contract of the wind generating set in a real-time information acquisition node of the wind generating set;
the output real-time data of the photovoltaic generator set is automatically acquired by a photovoltaic generator set real-time data acquisition intelligent contract in a photovoltaic generator set real-time information acquisition node;
The real-time output data of the traditional thermal power generating set is automatically acquired by a traditional thermal power generating set real-time data acquisition intelligent contract with limited and concentrated real-time information acquisition nodes of the traditional thermal power generating set;
the local load absorption capacity real-time data is automatically acquired by a local load real-time data acquisition intelligent contract in a limited set of local load real-time information acquisition nodes;
the energy storage capacity real-time data of the energy storage device are automatically acquired by an energy storage device real-time data acquisition intelligent contract in a limited set of energy storage device real-time information acquisition nodes;
the power grid power flow real-time data is automatically acquired by a power grid power flow real-time data acquisition intelligent contract in a limited and concentrated mode of a power grid power flow real-time information acquisition node.
7. The high-proportion renewable energy consumption optimization method according to claim 6, wherein in S3, the compensation decision information of the next time includes: the method comprises the steps of outputting compensation decision information of a wind generating set at the next moment, outputting compensation decision information of a photovoltaic generating set at the next moment, compensating state information of a traditional thermal power generating set at the next moment, outputting compensation decision information, compensating energy storage information of energy storage equipment at the next moment, compensating load information of a local load model at the next moment and compensating transmission information of a power grid tide model at the next moment.
8. The high-proportion renewable energy consumption optimization method according to claim 7, wherein in S4, based on the updated pre-decision information and the compensation decision information, the on-day roller guide information optimization calculation intelligent contract automatically calculates real-time decision information at the next moment in real time; the real-time decision information of the next moment comprises: the method comprises the steps of outputting decision guiding information of a wind generating set at the next moment, outputting decision guiding information of a photovoltaic generating set at the next moment, real-time state information of a traditional thermal power generating set at the next moment, outputting decision guiding information, energy storage guiding information of energy storage equipment at the next moment, load guiding information of a local load model at the next moment and transmission power guiding information of a power grid tide model at the next moment.
9. The high-proportion renewable energy consumption optimization method according to claim 8, wherein in S5, based on the real-time decision information of the next moment, performing consumption decision guidance on the device of the next moment comprises:
the information driving center dispatching node of the wind generating set guides the maximum output power of each period of the wind generating set based on the output decision guiding information of the next moment of the wind generating set;
The information driving center dispatching node of the photovoltaic generator set guides the maximum output power of each period of the photovoltaic generator set based on the output decision guiding information of the next moment of the photovoltaic generator set;
the value driving center dispatching node of the limited set of the traditional thermal power generating unit carries out renewable energy source assisted digestion guide and load bottom guide on the traditional thermal power generating unit through value driving based on real-time state information and output decision guide information of the traditional thermal power generating unit at the next moment;
the value driving center dispatching node of the local load finite set carries out renewable energy source consumption compensation guidance and overload consumption punishment guidance on the local load model through value driving based on load guiding information of the local load model at the next moment;
the information driving center scheduling node of the limited set of energy storage equipment carries out reduction absorption peak Gu Chashang guiding on an energy storage equipment model through information driving based on energy storage guiding information of the energy storage equipment at the next moment;
and the information driving center dispatching node of the power grid power flow limited set carries out compensation power transmission information difference guiding on the power grid power flow model through information driving based on transmission power guiding information of the power grid power flow model at the next moment.
CN202310643050.0A 2023-06-01 2023-06-01 High-proportion renewable energy source consumption optimization method Active CN116365606B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202310643050.0A CN116365606B (en) 2023-06-01 2023-06-01 High-proportion renewable energy source consumption optimization method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202310643050.0A CN116365606B (en) 2023-06-01 2023-06-01 High-proportion renewable energy source consumption optimization method

Publications (2)

Publication Number Publication Date
CN116365606A CN116365606A (en) 2023-06-30
CN116365606B true CN116365606B (en) 2023-08-18

Family

ID=86913462

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202310643050.0A Active CN116365606B (en) 2023-06-01 2023-06-01 High-proportion renewable energy source consumption optimization method

Country Status (1)

Country Link
CN (1) CN116365606B (en)

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018059096A1 (en) * 2016-09-30 2018-04-05 国电南瑞科技股份有限公司 Combined decision method for power generation plans of multiple power sources, and storage medium
CN109149567A (en) * 2018-09-10 2019-01-04 华南理工大学 The Multiple Time Scales control method for coordinating of self micro-capacitance sensor containing hybrid energy-storing
CN109962499A (en) * 2019-03-25 2019-07-02 国家电网公司华中分部 A kind of power grid Multiple Time Scales dispatching method
AU2019101104A4 (en) * 2019-09-25 2019-10-31 Southeast University An optimal dispatching method of multi-region power and gas coupled integrated energy system using tiered gas tariff
CN115498624A (en) * 2022-08-09 2022-12-20 国网湖北省电力有限公司电力科学研究院 Low-carbon economic dispatching method for power distribution network containing flexible interactive resources based on two-stage robust optimization
CN115912351A (en) * 2022-11-30 2023-04-04 国网北京市电力公司 Photovoltaic day-ahead model prediction method, system, equipment and medium

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2018059096A1 (en) * 2016-09-30 2018-04-05 国电南瑞科技股份有限公司 Combined decision method for power generation plans of multiple power sources, and storage medium
CN109149567A (en) * 2018-09-10 2019-01-04 华南理工大学 The Multiple Time Scales control method for coordinating of self micro-capacitance sensor containing hybrid energy-storing
CN109962499A (en) * 2019-03-25 2019-07-02 国家电网公司华中分部 A kind of power grid Multiple Time Scales dispatching method
AU2019101104A4 (en) * 2019-09-25 2019-10-31 Southeast University An optimal dispatching method of multi-region power and gas coupled integrated energy system using tiered gas tariff
CN115498624A (en) * 2022-08-09 2022-12-20 国网湖北省电力有限公司电力科学研究院 Low-carbon economic dispatching method for power distribution network containing flexible interactive resources based on two-stage robust optimization
CN115912351A (en) * 2022-11-30 2023-04-04 国网北京市电力公司 Photovoltaic day-ahead model prediction method, system, equipment and medium

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
陈晓红.数字技术助推我国能源行业碳中和目标实现的路径探析.《中国科学院院刊》.2021,全文. *

Also Published As

Publication number Publication date
CN116365606A (en) 2023-06-30

Similar Documents

Publication Publication Date Title
Zhang et al. Lifelong learning for complementary generation control of interconnected power grids with high-penetration renewables and EVs
Hong et al. Hour-ahead wind power and speed forecasting using simultaneous perturbation stochastic approximation (SPSA) algorithm and neural network with fuzzy inputs
CN102930358B (en) A kind of neural net prediction method of photovoltaic power station power generation power
Rajkumar et al. Techno-economical optimization of hybrid pv/wind/battery system using Neuro-Fuzzy
Li et al. Probabilistic charging power forecast of EVCS: Reinforcement learning assisted deep learning approach
CN111555356B (en) Random variable analysis method for regional comprehensive energy system based on coupled Markov model
CN107256436A (en) The prediction and matching and control method of dissolving of thermal storage electric boiler and clean energy resource
CN107590607A (en) A kind of micro-capacitance sensor Optimal Scheduling and method based on photovoltaic prediction
CN114069687B (en) Distributed photovoltaic planning method considering reactive power regulation effect of inverter
CN115036914A (en) Power grid energy storage double-layer optimization method and system considering flexibility and new energy consumption
CN112883630B (en) Multi-microgrid system day-ahead optimization economic dispatching method for wind power consumption
Pan et al. Dual-layer optimal dispatching strategy for microgrid energy management systems considering demand response
CN116365606B (en) High-proportion renewable energy source consumption optimization method
CN113158547A (en) Regional comprehensive energy system optimal configuration method considering economy and reliability
CN116914821A (en) Micro-grid low-carbon optimal scheduling method based on improved particle swarm optimization
Hong et al. Short-term real-power scheduling considering fuzzy factors in an autonomous system using genetic algorithms
CN116683530A (en) Wind-light-containing hybrid type pumping and storing station cascade reservoir random optimization scheduling method
CN116418001A (en) Reservoir group multi-energy complementary scheduling method and system for coping with uncertainty of new energy
CN116629421A (en) Comprehensive energy system multi-target distribution robust optimization scheduling method considering comprehensive energy efficiency
CN115545429A (en) Multi-scene low-voltage renewable resource load prediction method based on CPSS framework
CN111311032B (en) Micro-grid system capacity optimal configuration method based on sector radar map model
CN115764855A (en) Real-time adjustable capacity and available electric quantity prediction method for electric vehicle quick charging station
CN108171384A (en) One kind is based on composite particle swarm optimization algorithm microgrid energy management method
CN103326387B (en) Source network coordinated dispatching method reducing wind electricity dispatching risks by means of stored energy
Masoumi et al. Wind speed forecasting using back propagation artificial neural networks in North of Iran

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