WO2023083235A1 - 一种分散式预测电网的优化方法及*** - Google Patents

一种分散式预测电网的优化方法及*** Download PDF

Info

Publication number
WO2023083235A1
WO2023083235A1 PCT/CN2022/131017 CN2022131017W WO2023083235A1 WO 2023083235 A1 WO2023083235 A1 WO 2023083235A1 CN 2022131017 W CN2022131017 W CN 2022131017W WO 2023083235 A1 WO2023083235 A1 WO 2023083235A1
Authority
WO
WIPO (PCT)
Prior art keywords
power
distributed power
distributed
value
distribution network
Prior art date
Application number
PCT/CN2022/131017
Other languages
English (en)
French (fr)
Inventor
尹稚玲
罗金满
高承芳
封祐钧
叶睿菁
张谊
李晓霞
刘飘
王海吉
Original Assignee
广东电网有限责任公司东莞供电局
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 广东电网有限责任公司东莞供电局 filed Critical 广东电网有限责任公司东莞供电局
Publication of WO2023083235A1 publication Critical patent/WO2023083235A1/zh

Links

Images

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
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G06N3/044—Recurrent networks, e.g. Hopfield networks
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • 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
    • G06Q10/067—Enterprise or organisation modelling
    • 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
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
    • Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
    • Y02E40/70—Smart grids as climate change mitigation technology in the energy generation sector
    • 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

Definitions

  • the present application relates to the technical field of power grid optimization, in particular to a distributed forecasting power grid optimization method and system.
  • CN201910090554.8 discloses a distributed power supply coordinated optimization control method and system, based on distribution network operation state data, topology data, and electric vehicle charging state data to predict the power of the source and load, and obtain the prediction results.
  • the distributed power sources in the region are rationally configured and planned in an orderly manner, which ensures the safe and reliable operation of the power grid and at the same time makes full use of the coordinated control characteristics of charging equipment in the market environment, which can be more efficient. It economically and efficiently improves the utilization level of distributed power.
  • the above-mentioned related technologies can improve the utilization level of distributed power to a certain extent, but there are still some defects, such as: only qualitatively determine the power supply sequence, but it is difficult to quantitatively grasp the adjustment amount of distributed power, that is, it is impossible to control distributed power
  • the regulation accuracy is low, resulting in low planning reliability of distributed power generation.
  • the purpose of this application is to provide an optimization method and system for distributed forecasting power grids, so as to solve the problem that it is difficult to quantitatively grasp the adjustment amount of distributed power sources in related technologies, that is, it is impossible to control the adjustment accuracy of distributed power sources, which leads to the Planning technical issues with low reliability.
  • An optimization method for a distributed forecasting power grid comprising the following steps:
  • Step S1 real-time monitoring of the power supply parameters provided by each distributed power source in the distribution network for the distribution network load, and calculate the contribution of the distributed power source based on the power supply parameters, and the contribution degree is used as a contribution of the distributed power source to the distribution network load.
  • a measurement indicator of the supply degree of the total power supply parameter of the distribution network load, the power supply parameter is the electrical parameter data representing the input of the distributed power supply to the distribution network to the distribution network;
  • Step S2 Predict the contribution of the distributed power generation in the future, and build an allocation model for the contribution of the distributed power in the distribution network, and the distribution model is used to analyze the distribution of the distributed power in the distribution network. Coordinated distribution of the contribution of distributed power generation to meet the power demand of the distribution network load while reducing power costs and improving clean efficiency;
  • Step S3 Use the distribution value of the contribution degree obtained by the distribution model at a future time as an adjustment reference, and dynamically adjust the distributed power supply until the predicted value of the contribution degree obtained by the neural network at a future time is consistent with the adjustment reference , in order to realize the optimal scheduling of all distributed power sources in the distribution network so that the distribution network can meet the reliability requirements and meet the low-carbon requirements at the same time.
  • the calculation of the contribution of the distributed power supply based on the power supply parameters includes:
  • the electrical parameter is represented by the electrical parameter data that the load is connected to the distribution network and output from the distribution network to the load;
  • the ratio of the output power of each distributed power supply to the total input power is calculated in turn as the contribution of each distributed power supply, and the calculation formula of the contribution is:
  • h i,t represents the contribution of the i-th distributed generation at time t
  • P i,t represents the output power of the i-th distributed generation at time t
  • P j,t represents the The input power of the jth load at time t, N is characterized by the total number of loads, i, j are metering constants, which have no real meaning.
  • predicting the contribution of the distributed power generation at a future moment includes:
  • the training method of the LSTM long-short-term memory network is set to the reverse transfer method of seq2seq.
  • the construction of an allocation model for the contribution of distributed power sources in the distribution network includes:
  • the optimal power value is used to characterize the optimal value of output power for all loads to run at full load, and the lowest power value is used to characterize the output power for all loads to run at full capacity The minimum value of output power for load operation;
  • economic evaluation indicators are obtained based on the quantification of distributed power production costs, including:
  • X t is represented by the economic evaluation index value at time t
  • s i is represented by the unit price cost of the i-th distributed power generation
  • W i,t P i,t * ⁇ t
  • P i,t is represented by
  • the output power of the i-th distributed power generation, ⁇ t is characterized by the instantaneous duration at time t
  • W i,t is represented by the instantaneous power of the i-th distributed power generation at time t
  • M is represented by the distributed power the total number of
  • the cleanliness evaluation index is obtained based on the quantification of pollutant emissions from distributed power sources, including:
  • Y t represents the cleaning evaluation index value at time t
  • v k represents the pollutant treatment unit price of the kth pollutant
  • P i,t is characterized by the output power of the i-th distributed power generation at time t
  • ⁇ t is characterized by the instantaneous duration at time t
  • W i,t is represented by the i-th
  • u k is characterized by the correlation coefficient of the kth pollutant output when the instantaneous power W i,t is generated
  • Q i,t,k is represented by the i-th distributed power at time t
  • the output of the kth pollutant produced by the power supply, M is represented by the total number of distributed power sources
  • n is represented by the total number of pollutant types
  • k is a
  • the economic evaluation index and the cleaning evaluation index jointly constitute the evaluation value, including:
  • the economic evaluation index and the cleaning evaluation index are weighted and summed to obtain the evaluation value, and the calculation formula of the evaluation value is:
  • the weight coefficient of the indicator Y t is calculated by the distribution model, including:
  • the distribution value P i,t+1 (i ⁇ [1,M]) of the output power of the distributed power generation (i ⁇ [1,M]) is changed from the optimal power value to the lowest power Search within the value range to obtain the maximum evaluation value, and bring P i,t+1 (i ⁇ [1,M]) corresponding to the maximum evaluation value into the calculation formula of contribution
  • the distribution value h i,t+1 (i ⁇ [1,M]) of the contribution degree of distributed power generation (i ⁇ [1,M]) is calculated, and the distribution value h i,t+1 (i ⁇ [1,M]) as the adjustment benchmark, where P i,t+1 is characterized as the distribution value of the output power of the i-th distributed power generation at the future time t+1, and P j,t+1 is characterized as The rated power of the j-th load at the future time t+1, h i,t+1 is characterized by the distribution value of the contribution of the distribution model to the i-th distributed power supply at the future time
  • the search solution is solved by genetic algorithm.
  • the distributed power supply is dynamically adjusted until the predicted value of the contribution obtained by the neural network at a future moment is consistent with the adjustment benchmark, including:
  • the distributed power generation at the future time t+1 is calculated.
  • the present application provides an optimization system according to the optimization method of the decentralized forecasting power grid, including:
  • the data acquisition module is used for real-time monitoring of the power supply parameters provided by each distributed power source in the distribution network for the distribution network load, and the power consumption parameters of the distribution network load;
  • the data processing module is used to calculate the contribution degree of the distributed power supply based on the power supply parameters, and predict the contribution degree of the distributed power supply at a time in the future, and provide the contribution degree of the distributed power supply in the distribution network build distribution models;
  • the optimization adjustment module is used to use the distribution value of the contribution degree obtained by the distribution model at a future time as an adjustment reference, and dynamically adjust the distributed power supply until the neural network obtains the predicted value of the contribution degree at a future time.
  • the adjustment base is the same.
  • the distribution model of the contribution rate of the distributed power supply by constructing the distribution model of the contribution rate of the distributed power supply, the distribution value of the contribution degree obtained by the distribution model at the future time is used as the adjustment reference, and the distributed power supply is dynamically adjusted until the neural network obtains the distribution value at the future time.
  • the predicted value of the above contribution is consistent with the adjustment benchmark, so as to realize the optimal scheduling of all distributed power sources in the distribution network, so that the distribution network can meet the reliability requirements and low-carbon requirements at the same time, achieve the purpose of quantitative optimal scheduling, and improve the optimization efficiency. Scheduling accuracy and controllability.
  • Fig. 1 is the flow chart of the optimization method of the decentralized forecasting power grid provided by the embodiment of the present application;
  • FIG. 2 is a structural block diagram of the optimization system provided by the embodiment of the present application.
  • 1-data acquisition module 2-data processing module
  • 3-optimization adjustment module 3-optimization adjustment module.
  • the present application provides a method for optimizing a distributed forecasting power grid, including the following steps:
  • Step S1 real-time monitoring of the power supply parameters provided by each distributed power source in the distribution network for the distribution network load, and calculate the contribution degree of the distributed power source based on the power supply parameters, and the contribution degree is used as the contribution of the distributed power source to the distribution network load
  • the measurement index of the supply degree of the total power supply parameter, the power supply parameter is the electrical parameter data that characterizes the distributed power supply connected to the distribution network and input to the distribution network;
  • the power consumption parameters of the load are monitored at each load in the distribution network, and the input power of each load is calculated through the power consumption parameters of the load, and then the input power of all loads is summed to obtain the total input power of the distribution network load.
  • the electrical parameter is represented by the electrical parameter data output from the distribution network to the load when the load is connected to the distribution network;
  • h i,t represents the contribution of the i-th distributed generation at time t
  • P i,t represents the output power of the i-th distributed generation at time t
  • P j,t represents the The input power of the jth load at time t, N is characterized by the total number of loads, i, j are metering constants, which have no real meaning.
  • the power supply parameters include but not limited to the voltage and current transmitted to the distribution network lines, and the power consumption parameters include but not limited to the voltage and current transmitted from the distribution network to the load end.
  • the power consumption of the distribution network load comes from all The joint action of distributed power sources, so the power of the distribution network load is completely converted from the power of distributed power sources.
  • the output power of the distributed power source itself can be compared with the distribution power.
  • the ratio of the sum of the input power of all loads in the network is measured, that is, the proportion of the output power delivered by the distributed generation to the distribution network in the sum of the input power of all loads. The greater the degree, the higher the contribution, on the contrary, the smaller the proportion, the smaller the supply of distributed power to the load of the distribution network, and the lower the contribution.
  • Step S2. Predict the contribution of distributed generation in the future, and build an allocation model for the contribution of distributed generation in the distribution network.
  • the distribution model is used to determine the contribution of distributed generation in the distribution network to Coordinate distribution so that distributed power generation can reduce electricity cost and improve clean efficiency while meeting the load demand of distribution network;
  • the training method of the LSTM long short-term memory network is set to the reverse transfer method of seq2seq.
  • the optimal value of power is used to represent the optimal value of output power for all loads to operate at full load, and the minimum value of power is used to represent the minimum output power for all loads to operate at full load. value;
  • the economic evaluation index and clean evaluation index are set up to measure the cost and pollution of the distribution network.
  • the economic evaluation indicators are obtained, including:
  • X t is represented by the economic evaluation index value at time t
  • s i is represented by the unit price cost of the i-th distributed power generation
  • W i,t P i,t * ⁇ t
  • P i,t is represented by
  • the output power of the i-th distributed power generation, ⁇ t is characterized by the instantaneous duration at time t
  • W i,t is represented by the instantaneous power of the i-th distributed power generation at time t
  • M is represented by the distributed power the total number of
  • the cleaning evaluation indicators are obtained, including:
  • Y t represents the cleaning evaluation index value at time t
  • v k represents the pollutant treatment unit price of the kth pollutant
  • P i,t is characterized by the output power of the i-th distributed power generation at time t
  • ⁇ t is characterized by the instantaneous duration at time t
  • W i,t is represented by the i-th
  • u k is characterized by the correlation coefficient of the kth pollutant output when the instantaneous power W i,t is generated
  • Q i,t,k is represented by the i-th distributed power at time t
  • the output of the kth pollutant produced by the power supply, M is represented by the total number of distributed power sources
  • n is represented by the total number of pollutant types
  • k is a
  • the evaluation value is obtained by weighting and summing the economic evaluation index and the cleaning evaluation index.
  • the calculation formula of the evaluation value is:
  • the distribution value of the contribution degree obtained at the future moment is calculated by the distribution model, including:
  • the distribution value P i,t+1 (i ⁇ [1,M]) of the output power of the distributed power generation (i ⁇ [1,M]) is changed from the optimal power value to the lowest power Search within the value range to obtain the maximum evaluation value, and bring P i,t+1 (i ⁇ [1,M]) corresponding to the maximum evaluation value into the calculation formula of contribution
  • the distribution value h i,t+1 (i ⁇ [1,M]) of the contribution degree of distributed power generation (i ⁇ [1,M]) is calculated, and the distribution value h i,t+1 (i ⁇ [1,M]) as the adjustment benchmark, where P i,t+1 is characterized as the distribution value of the output power of the i-th distributed power generation at the future time t+1, and P j,t+1 is characterized as The rated power of the j-th load at the future time t+1, h i,t+1 is characterized by the distribution value of the contribution of the distribution model to the i-th distributed power supply at the future time
  • the search solution is solved by genetic algorithm.
  • Step S3 use the distribution value of the contribution degree obtained by the distribution model at the future time as the adjustment reference, and dynamically adjust the distributed power supply until the predicted value of the contribution degree obtained by the neural network at the future time is consistent with the adjustment reference, so as to realize the adjustment
  • the optimal scheduling of all distributed power sources in the distribution network enables the distribution network to meet the reliability requirements and meet the low-carbon requirements at the same time.
  • the distributed power generation at the future time t+1 is calculated.
  • the output power of the distributed generation needs to be P i,t+0 (i ⁇ [1,M]), but due to the absence of human intervention
  • the output power of the distributed generation at the future time t+1 can be predicted from the output power of the distributed generation at the time t, if the predicted output power of the distributed generation at the future time t+1 (this The predicted value in the embodiment) is inconsistent with the distribution value of the output power of the distributed power generation (i ⁇ [1,M]), then the distribution network will not be able to maintain the optimal operating state at the time t+1 in the future, and at this time It is necessary to carry out human intervention on the distributed power supply, adjust the distributed power supply so that the output power is the same as
  • an optimization system including:
  • the data acquisition module 1 is used to monitor in real time the power supply parameters provided by each distributed power source in the distribution network for the distribution network load, and the power consumption parameters of the distribution network load;
  • Data processing module 2 used to calculate the contribution of distributed power based on power supply parameters, predict the contribution of distributed power in the future, and build a distribution model for the contribution of distributed power in the distribution network ;
  • the optimization adjustment module 3 is used to use the distribution value of the contribution degree obtained by the distribution model at the future time as the adjustment reference, and dynamically adjust the distributed power supply until the predicted value of the contribution degree obtained by the neural network at the future time is consistent with the adjustment reference .
  • the distribution model of the contribution rate of the distributed power supply by constructing the distribution model of the contribution rate of the distributed power supply, the distribution value of the contribution degree obtained by the distribution model at the future moment is used as the adjustment benchmark, and the distributed power supply is dynamically adjusted until the neural network obtains the contribution degree at the future moment.
  • the predicted value is consistent with the adjustment benchmark to realize the optimal scheduling of all distributed power sources in the distribution network, so that the distribution network can meet the reliability requirements and meet the low-carbon requirements at the same time, achieve the purpose of quantitative optimal scheduling, and improve the accuracy of optimal scheduling and controllability.

Landscapes

  • Engineering & Computer Science (AREA)
  • Business, Economics & Management (AREA)
  • Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Strategic Management (AREA)
  • Human Resources & Organizations (AREA)
  • Economics (AREA)
  • General Physics & Mathematics (AREA)
  • Health & Medical Sciences (AREA)
  • Tourism & Hospitality (AREA)
  • Marketing (AREA)
  • General Health & Medical Sciences (AREA)
  • General Business, Economics & Management (AREA)
  • Entrepreneurship & Innovation (AREA)
  • Software Systems (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • General Engineering & Computer Science (AREA)
  • Computing Systems (AREA)
  • Molecular Biology (AREA)
  • Evolutionary Computation (AREA)
  • Quality & Reliability (AREA)
  • Operations Research (AREA)
  • Data Mining & Analysis (AREA)
  • Computational Linguistics (AREA)
  • Mathematical Physics (AREA)
  • Biophysics (AREA)
  • Biomedical Technology (AREA)
  • Artificial Intelligence (AREA)
  • Development Economics (AREA)
  • Game Theory and Decision Science (AREA)
  • Primary Health Care (AREA)
  • Water Supply & Treatment (AREA)
  • Public Health (AREA)
  • Educational Administration (AREA)
  • Supply And Distribution Of Alternating Current (AREA)

Abstract

本申请公开了一种分散式预测电网的优化方法及***，包括以下步骤：步骤S1、实时监测配电网中每个分布式电源为配电网负载提供的供电参量，并基于所述供电参量计算出分布式电源的贡献度；步骤S2、对分布式电源在未来时刻上的所述贡献度进行预测，并在配电网中为分布式电源的贡献度构建分配模型，所述分配模型用于对配电网中分布式电源的贡献度对进行协调分配以使得分布式电源在满足配电网负载用电需求的同时降低用电成本和提高清洁效益。本申请对分布式电源进行动态调整直至神经网络在未来时刻上得到所述贡献度的预测值与调节基准一致，以实现对配电网中所有分布式电源的优化调度使得配电网满足可靠性需求的同时满足低碳性需求。

Description

一种分散式预测电网的优化方法及***
本申请要求在2021年11月10日提交中国专利局、申请号为202111323378.1的中国专利申请的优先权，该申请的全部内容通过引用结合在本申请中。
技术领域
本申请涉及电网优化技术领域，具体涉及一种分散式预测电网的优化方法及***。
背景技术
随着世界各国对能源危机、环境保护、全球气候变化等问题日益重视，开发利用可再生能源已成为全球的普遍共识和一致行动。近年来，可再生能源发电技术日益成熟，可再生能源发电并网迅猛发展。同时，电动汽车因其节能环保、防治大气污染的优势被广泛研究与利用。分布式电源与电动汽车规模接入与应用是智能配电网可持续发展的必然趋势和未来重要特征。分布式电源出力的间歇性、随机性、波动性特征，是制约分布式电源消纳与高效利用的瓶颈之一。大规模电动汽车的随机并网与无序充电，会产生尖峰负荷，增加网络损耗。强波动电源-强随机负荷使配电网呈现常态化的不确定性和波动性，对智能配电网的安全可靠运行提出巨大了挑战，对智能配电网的协调优化控制也提出了更高的要求。
相关技术CN201910090554.8公开了一种分布式电源协调优化控制方法及***，基于配电网运行状态数据、拓扑数据、与电动汽车充电状态数据对源荷功率进行预测，得到预测结果，在配电网运行状态和拓扑结构不变的情况下，对区域内分布式电源进行合理配置和有序规划，保证了电网安全可靠运行的同时，充分利用了市场环境下充电设备的协调控制特性，可以更经济、高效地提升了对分布式电源的利用水平。
上述相关技术能够一定程度的提升分布式电源的利用水平，但仍存在一定的缺陷，比如：只是定性的确定了供电顺序，却难以定量的掌握分布式电源的调节量，即无法控制分布式电源的调节准确度，导致分布式电源的规划可靠性低。
发明内容
本申请的目的在于提供一种分散式预测电网的优化方法及***，以解决相关技术中难以定量的掌握分布式电源的调节量，即无法控制分布式电源的调节 准确度，导致分布式电源的规划可靠性低的技术问题。
为解决上述技术问题，本申请具体提供下述技术方案：
一种分散式预测电网的优化方法，包括以下步骤：
步骤S1、实时监测配电网中每个分布式电源为配电网负载提供的供电参量，并基于所述供电参量计算出分布式电源的贡献度，所述贡献度用于作为分布式电源对配电网负载总供电参量的供给程度的衡量指标，所述供电参量是表征分布式电源接入至配电网向配电网输入的电参数据；
步骤S2、对分布式电源在未来时刻上的所述贡献度进行预测，并在配电网中为分布式电源的贡献度构建分配模型，所述分配模型用于对配电网中分布式电源的贡献度对进行协调分配以使得分布式电源在满足配电网负载用电需求的同时降低用电成本和提高清洁效益；
步骤S3、将由分配模型在未来时刻上得到的所述贡献度的分配值作为调节基准，并对分布式电源进行动态调整直至神经网络在未来时刻上得到所述贡献度的预测值与调节基准一致，以实现对配电网中所有分布式电源的优化调度使得配电网满足可靠性需求的同时满足低碳性需求。
作为本申请的一种方案，所述基于所述供电参量计算出分布式电源的贡献度，包括：
根据分布式电源的供电参量依次计算出每个分布式电源的输出功率；
在配电网各负载处监测负载的用电参量，并通过所述负载的用电参量计算出每个负载的输入功率，再将所有负载的输入功率求和得到配电网负载的总输入功率，所述用电参量表征为负载接入至配电网由配电网向负载输出的电参数据；
依次计算每个分布式电源的输出功率与所述总输入功率的比值作为每个分布式电源的贡献度，所述贡献度的计算公式为：
Figure PCTCN2022131017-appb-000001
式中，h i,t表征为在时刻t处第i个分布式电源的贡献度，P i,t表征为在时刻t处第i个分布式电源的输出功率，P j,t表征为在时刻t处第j个负载的输入功率，N表征为负载总数目，i，j为计量常数，无实质含义。
作为本申请的一种方案，对分布式电源在未来时刻上的所述贡献度进行预测，包括：
将所述分布式电源在时刻t处的贡献度h i,t(i∈[1,M])输入至LSTM长短期记忆网络中，输出得到分布式电源在未来时刻t+1处的贡献度的预测值 h i,t+1′(i∈[1,M])，以实现对分布式电源在未来时刻上的所述贡献度进行预测；
所述LSTM长短期记忆网络的训练方式设置为seq2seq的反向传递方式。
作为本申请的一种方案，所述在配电网中为分布式电源的贡献度构建分配模型，包括：
为所述分布式电源设置功率最优值和功率最低值，所述功率最优值用于表征供所有负载满负荷运行的输出功率最优值，所述功率最低值用于表征供所有负载满负荷运行的输出功率最低值；
基于分布式电源的产电成本量化配电网运行的用电成本得到经济评价指标；
基于分布式电源的污染物排放量量化配电网运行的环境成本得到清洁评价指标；
在功率最优值到功率最低值范围内进行搜索求解，以获得评优值，所述评优值表征为利用经济评价指标和清洁评价指标共同表示配电网运行优劣状态的评价指标。
作为本申请的一种方案，基于分布式电源的产电成本量化得到经济评价指标，包括：
获取每个分布式电源的产电成本，并将所有分布式电源的产电成本进行求和得到经济评价指标，所述经济评价指标的计算公式为：
Figure PCTCN2022131017-appb-000002
式中，X t表征为时刻t处的经济评价指标值，s i表征为第i个分布式电源的产电单价成本，W i,t＝P i,t*Δt，P i,t表征为在时刻t处第i个分布式电源的输出功率，Δt表征为时刻t处的瞬时时长，W i,t表征为在时刻t处第i个分布式电源的瞬时电能，M表征为分布式电源的总数目；
将时刻t处的瞬时时长Δt量化为1个单位时间，则将经济评价指标的计算公式更新为：
Figure PCTCN2022131017-appb-000003
作为本申请的一种方案，基于分布式电源的污染物排放量量化得到清洁评价指标，包括：
获取每个分布式电源产生的污染物、污染物产量以及污染物处理单价成本，并根据污染物、污染物产量以及污染物处理单价成本计算出所述清洁评价指标，所述清洁评价指标的计算公式为：
Figure PCTCN2022131017-appb-000004
式中，Y t表征为时刻t处的清洁评价指标值，v k表征为第k个污染物的污染物处理单价，Q i,t,k＝u k*W i,t，W i,t＝P i,t*Δt，P i,t表征为在时刻t处第i个分布式电源的输出功率，Δt表征为时刻t处的瞬时时长，W i,t表征为在时刻t处第i个分布式电源的瞬时电能，u k表征为在产生瞬时电能W i,t时会产生第k个污染物产量的关联系数，Q i,t,k表征为在时刻t处第i个分布式电源产生的第k个污染物产量，M表征为分布式电源的总数目，n表征为污染物种类总数目，k为计量常数，无实质含义；
将时刻t处的瞬时时长Δt量化为1个单位时间，则将经济评价指标的计算公式更新为：
Figure PCTCN2022131017-appb-000005
作为本申请的一种方案，所述利用经济评价指标和清洁评价指标共同组成评优值，包括：
将经济评价指标和清洁评价指标进行加权求和得到评优值，所述评优值的计算公式为：
F t＝αX t+βY t；
式中，F t表征为时刻t处的评优值，α+β＝1，α∈[0,1]，β∈[0,1]，α、β分别为经济评价指标X t和清洁评价指标Y t的权重系数。作为本申请的一种方案，由分配模型计算出在未来时刻上得到的所述贡献度的分配值，包括：
在未来时刻t+1处，将分布式电源(i∈[1,M])的输出功率的分配值P i,t+1(i∈[1,M])在功率最优值到功率最低值范围内进行取值搜索得到处最大评优值，并将最大评优值对应的P i,t+1(i∈[1,M])带入至贡献度的计算公式
Figure PCTCN2022131017-appb-000006
中计算得到分布式电源(i∈[1,M])贡献度的分配值h i,t+1(i∈[1,M])，将贡献度的分配值h i,t+1(i∈[1,M])作为调节基准，其中，P i,t+1表征为在未来时刻t+1处第i个分布式电源的输出功率的分配值，P j,t+1表征为在未来时刻t+1处第j个负载的额定功率，h i,t+1表征为由分配模型在未来时刻t+1处对第i个分布式电源的贡献度的分配值；
所述搜索求解采用遗传算法进行求解。
作为本申请的一种方案，对分布式电源进行动态调整直至神经网络在未来时刻上得到所述贡献度的预测值与调节基准一致，包括：
根据分布式电源在未来时刻t+1处的贡献度的预测值h i,t+1′(i∈[1,M])以及贡献度的计算公式计算得到分布式电源在未来时刻t+1处输出功率的预测值P i,t+1′(i∈[1,M])；
将分布式电源在未来时刻t+1处输出功率的预测值P i,t+1′(i∈[1,M])通过供 电参量进行调整直至预测值P i,t+1′(i∈[1,M])与分布式电源输出功率的分配值P i,t+1(i∈[1,M])相等，以实现所述贡献度的预测值与调节基准一致。
作为本申请的一种方案，本申请提供了一种根据所述的分散式预测电网的优化方法的优化***，包括：
数据采集模块，用于实时监测配电网中每个分布式电源为配电网负载提供的供电参量，以及配电网负载的用电参量；
数据处理模块，用于基于所述供电参量计算出分布式电源的贡献度，以及对分布式电源在未来时刻上的所述贡献度进行预测，并在配电网中为分布式电源的贡献度构建分配模型；
优化调节模块，用于将由分配模型在未来时刻上得到的所述贡献度的分配值作为调节基准，并对分布式电源进行动态调整直至神经网络在未来时刻上得到所述贡献度的预测值与调节基准一致。
本申请与相关技术相比较具有如下效果：
本申请通过构建分布式电源贡献率的分配模型，将由分配模型在未来时刻上得到的所述贡献度的分配值作为调节基准，并对分布式电源进行动态调整直至神经网络在未来时刻上得到所述贡献度的预测值与调节基准一致，以实现对配电网中所有分布式电源的优化调度使得配电网满足可靠性需求的同时满足低碳性需求，达到定量优化调度的目的，提高优化调度的准确度和可控性。
附图说明
图1为本申请实施例提供的分散式预测电网的优化方法流程图；
图2为本申请实施例提供的优化***结构框图。
图中的标号分别表示如下：
1-数据采集模块；2-数据处理模块；3-优化调节模块。
具体实施方式
下面将结合本申请实施例中的附图，对本申请实施例中的技术方案进行清楚、完整地描述，所描述的实施例仅仅是本申请一部分实施例，而不是全部的实施例。
如图1所示，本申请提供了一种分散式预测电网的优化方法，包括以下步骤：
步骤S1、实时监测配电网中每个分布式电源为配电网负载提供的供电参量， 并基于供电参量计算出分布式电源的贡献度，贡献度用于作为分布式电源对配电网负载总供电参量的供给程度的衡量指标，供电参量是表征分布式电源接入至配电网向配电网输入的电参数据；
基于供电参量计算出分布式电源的贡献度，包括：
根据分布式电源的供电参量依次计算出每个分布式电源的输出功率；
在配电网各负载处监测负载的用电参量，并通过负载的用电参量计算出每个负载的输入功率，再将所有负载的输入功率求和得到配电网负载的总输入功率，用电参量表征为负载接入至配电网由配电网向负载输出的电参数据；
依次计算每个分布式电源的输出功率与总输入功率的比值作为每个分布式电源的贡献度，贡献度的计算公式为：
Figure PCTCN2022131017-appb-000007
式中，h i,t表征为在时刻t处第i个分布式电源的贡献度，P i,t表征为在时刻t处第i个分布式电源的输出功率，P j,t表征为在时刻t处第j个负载的输入功率，N表征为负载总数目，i，j为计量常数，无实质含义。
供电参量包括但不仅限于向配电网线路中输送的电压、电流等，用电参量包括但不仅限于由配电网向负载端输送的电压、电流，配电网负载的用电均来自于所有分布式电源的共同作用，因此配电网负载的功率完全由分布式电源的功率转换而来，衡量单个分布式电源对配电网的贡献度，可以通过分布式电源自身的输出功率与配电网中所有负载的输入功率总和的比值进行衡量，即分布式电源向配电网输送的输出功率占所有负载的输入功率总和的比重，比重越大，则分布式电源对配电网负载的供给程度越大，则贡献度越高，反之，比重越小，则分布式电源对配电网负载的供给程度越小，则贡献度越低。
步骤S2、对分布式电源在未来时刻上的贡献度进行预测，并在配电网中为分布式电源的贡献度构建分配模型，分配模型用于对配电网中分布式电源的贡献度对进行协调分配以使得分布式电源在满足配电网负载用电需求的同时降低用电成本和提高清洁效益；
对分布式电源在未来时刻上的贡献度进行预测，包括：
将分布式电源在时刻t处的贡献度h i,t(i∈[1,M])输入至LSTM长短期记忆网络中，输出得到分布式电源在未来时刻t+1处的贡献度的预测值h i,t+1′(i∈[1,M])，以实现对分布式电源在未来时刻上的贡献度进行预测；
LSTM长短期记忆网络的训练方式设置为seq2seq的反向传递方式。
在配电网中为分布式电源的贡献度构建分配模型，包括：
为分布式电源设置功率最优值和功率最低值，功率最优值用于表征供所有负载满负荷运行的输出功率最优值，功率最低值用于表征供所有负载满负荷运行的输出功率最低值；
基于分布式电源的产电成本量化配电网运行的用电成本得到经济评价指标；
基于分布式电源的污染物排放量量化配电网运行的环境成本得到清洁评价指标；
在功率最优值到功率最低值范围内进行搜索求解，以获得评优值，评优值表征为利用经济评价指标和清洁评价指标共同表示配电网运行优劣状态的评价指标。
设立经济评价指标和清洁评价指标是为了衡量配电网的成本和污染情况，经济评价指标越高，则配电网的运行状态越差，经济评价指标越低，则配电网的运行状态越好，清洁评价指标越高，则配电网的运行状态越差，清洁评价指标越低，则配电网的运行状态越好，而配电网的运行目标是保持较好的运行状态，即追求更低的经济评价指标和清洁评价指标，因此对通过经济评价指标和清洁评价指标构成的评优值进行搜索，得到对应最大评优值的分布式电源的输出功率作为配电网期望分布式电源调度状态，从而实时保持配电网的最佳运行状态。
基于分布式电源的产电成本量化得到经济评价指标，包括：
获取每个分布式电源的产电成本，并将所有分布式电源的产电成本进行求和得到经济评价指标，经济评价指标的计算公式为：
Figure PCTCN2022131017-appb-000008
式中，X t表征为时刻t处的经济评价指标值，s i表征为第i个分布式电源的产电单价成本，W i,t＝P i,t*Δt，P i,t表征为在时刻t处第i个分布式电源的输出功率，Δt表征为时刻t处的瞬时时长，W i,t表征为在时刻t处第i个分布式电源的瞬时电能，M表征为分布式电源的总数目；
将时刻t处的瞬时时长Δt量化为1个单位时间，则将经济评价指标的计算公式更新为：
Figure PCTCN2022131017-appb-000009
基于分布式电源的污染物排放量量化得到清洁评价指标，包括：
获取每个分布式电源产生的污染物、污染物产量以及污染物处理单价成本，并根据污染物、污染物产量以及污染物处理单价成本计算出清洁评价指标，清洁评价指标的计算公式为：
Figure PCTCN2022131017-appb-000010
式中，Y t表征为时刻t处的清洁评价指标值，v k表征为第k个污染物的污染物处理单价，Q i,t,k＝u k*W i,t，W i,t＝P i,t*Δt，P i,t表征为在时刻t处第i个分布式电源的输出功率，Δt表征为时刻t处的瞬时时长，W i,t表征为在时刻t处第i个分布式电源的瞬时电能，u k表征为在产生瞬时电能W i,t时会产生第k个污染物产量的关联系数，Q i,t,k表征为在时刻t处第i个分布式电源产生的第k个污染物产量，M表征为分布式电源的总数目，n表征为污染物种类总数目，k为计量常数，无实质含义；
将时刻t处的瞬时时长Δt量化为1个单位时间，则将经济评价指标的计算公式更新为：
Figure PCTCN2022131017-appb-000011
利用经济评价指标和清洁评价指标共同组成评优值，包括：
将经济评价指标和清洁评价指标进行加权求和得到评优值，评优值的计算公式为：
F t＝αX t+βY t；
式中，F t表征为时刻t处的评优值，α+β＝1，α∈[0,1]，β∈[0,1]，α、β分别为经济评价指标X t和清洁评价指标Y t的权重系数。
由分配模型计算出在未来时刻上得到的贡献度的分配值，包括：
在未来时刻t+1处，将分布式电源(i∈[1,M])的输出功率的分配值P i,t+1(i∈[1,M])在功率最优值到功率最低值范围内进行取值搜索得到处最大评优值，并将最大评优值对应的P i,t+1(i∈[1,M])带入至贡献度的计算公式
Figure PCTCN2022131017-appb-000012
中计算得到分布式电源(i∈[1,M])贡献度的分配值h i,t+1(i∈[1,M])，将贡献度的分配值h i,t+1(i∈[1,M])作为调节基准，其中，P i,t+1表征为在未来时刻t+1处第i个分布式电源的输出功率的分配值，P j,t+1表征为在未来时刻t+1处第j个负载的额定功率，h i,t+1表征为由分配模型在未来时刻t+1处对第i个分布式电源的贡献度的分配值；
搜索求解采用遗传算法进行求解。
步骤S3、将由分配模型在未来时刻上得到的贡献度的分配值作为调节基准，并对分布式电源进行动态调整直至神经网络在未来时刻上得到贡献度的预测值与调节基准一致，以实现对配电网中所有分布式电源的优化调度使得配电网满足可靠性需求的同时满足低碳性需求。
对分布式电源进行动态调整直至神经网络在未来时刻上得到贡献度的预测 值与调节基准一致，包括：
根据分布式电源在未来时刻t+1处的贡献度的预测值h i,t+1′(i∈[1,M])以及贡献度的计算公式计算得到分布式电源在未来时刻t+1处输出功率的预测值P i,t+1′(i∈[1,M])；
将分布式电源在未来时刻t+1处输出功率的预测值P i,t+1′(i∈[1,M])通过供电参量进行调整直至预测值P i,t+1′(i∈[1,M])与分布式电源输出功率的分配值P i,t+1(i∈[1,M])相等，以实现贡献度的预测值与调节基准一致。
通过评优值计算公式计算出未来时刻t+1处的分布式电源(i∈[1,M])的输出功率的分配值P i,t+1(i∈[1,M])，从而可知要想配电网在未来时刻t+1处保持最佳的运行状态，需要使得分布式电源的输出功率为P i,t+0(i∈[1,M])，但是由于不在人为干预的情况下，分布式电源在未来时刻t+1处的输出功率可由分布式电源在时刻t处的输出功率预测得到，如果预测得到的分布式电源在未来时刻t+1处的输出功率(本实施例中的预测值)与分布式电源(i∈[1,M])的输出功率的分配值不一致，那么在未来时刻t+1处配电网将无法保持最佳运行状态，此时就需要对分布式电源进行人为干预，将分布式电源进行调整使得输出功率与分配值相同，重新实现将在未来时刻t+1处配电网调整至最佳运行状态。
如图2所示，基于上述分散式预测电网的优化方法，本申请提供了一种优化***，包括：
数据采集模块1，用于实时监测配电网中每个分布式电源为配电网负载提供的供电参量，以及配电网负载的用电参量；
数据处理模块2，用于基于供电参量计算出分布式电源的贡献度，以及对分布式电源在未来时刻上的贡献度进行预测，并在配电网中为分布式电源的贡献度构建分配模型；
优化调节模块3，用于将由分配模型在未来时刻上得到的贡献度的分配值作为调节基准，并对分布式电源进行动态调整直至神经网络在未来时刻上得到贡献度的预测值与调节基准一致。
本申请通过构建分布式电源贡献率的分配模型，将由分配模型在未来时刻上得到的贡献度的分配值作为调节基准，并对分布式电源进行动态调整直至神经网络在未来时刻上得到贡献度的预测值与调节基准一致，以实现对配电网中所有分布式电源的优化调度使得配电网满足可靠性需求的同时满足低碳性需求，达到定量优化调度的目的，提高优化调度的准确度和可控性。

Claims (10)

  1. 一种分散式预测电网的优化方法，包括：
    步骤S1、实时监测配电网中每个分布式电源为配电网负载提供的供电参量，并基于所述供电参量计算出分布式电源的贡献度，所述贡献度用于作为分布式电源对配电网负载总供电参量的供给程度的衡量指标，所述供电参量是表征分布式电源接入至配电网向配电网输入的电参数据；
    步骤S2、对分布式电源在未来时刻上的所述贡献度进行预测，并在配电网中为分布式电源的贡献度构建分配模型，所述分配模型用于对配电网中分布式电源的贡献度对进行协调分配以使得分布式电源在满足配电网负载用电需求的同时降低用电成本和提高清洁效益；
    步骤S3、将由分配模型在未来时刻上得到的所述贡献度的分配值作为调节基准，并对分布式电源进行动态调整直至神经网络在未来时刻上得到所述贡献度的预测值与调节基准一致，以实现对配电网中所有分布式电源的优化调度使得配电网满足可靠性需求的同时满足低碳性需求。
  2. 根据权利要求1所述的一种分散式预测电网的优化方法，其中，所述基于所述供电参量计算出分布式电源的贡献度，包括：
    根据分布式电源的供电参量依次计算出每个分布式电源的输出功率；
    在配电网各负载处监测负载的用电参量，并通过所述负载的用电参量计算出每个负载的输入功率，再将所有负载的输入功率求和得到配电网负载的总输入功率，所述用电参量表征为负载接入至配电网由配电网向负载输出的电参数据；
    依次计算每个分布式电源的输出功率与所述总输入功率的比值作为每个分布式电源的贡献度，所述贡献度的计算公式为：
    Figure PCTCN2022131017-appb-100001
    式中，h i,t表征为在时刻t处第i个分布式电源的贡献度，P i,t表征为在时刻t处第i个分布式电源的输出功率，P j,t表征为在时刻t处第j个负载的输入功率，N表征为负载总数目，i，j为计量常数，无实质含义。
  3. 根据权利要求2所述的一种分散式预测电网的优化方法，其中，对分布式电源在未来时刻上的所述贡献度进行预测，包括：
    将所述分布式电源在时刻t处的贡献度h i,t(i∈[1,M])输入至LSTM长短期记忆网络中，输出得到分布式电源在未来时刻t+1处的贡献度的预测值h i,t+1′(i∈[1,M])，以实现对分布式电源在未来时刻上的所述贡献度进行预测；
    所述LSTM长短期记忆网络的训练方式设置为seq2seq的反向传递方式。
  4. 根据权利要求3所述的一种分散式预测电网的优化方法，其中，所述在配电网中为分布式电源的贡献度构建分配模型，包括：
    为所述分布式电源设置功率最优值和功率最低值，所述功率最优值用于表征供所有负载满负荷运行的输出功率最优值，所述功率最低值用于表征供所有负载满负荷运行的输出功率最低值；
    基于分布式电源的产电成本量化配电网运行的用电成本得到经济评价指标；
    基于分布式电源的污染物排放量量化配电网运行的环境成本得到清洁评价指标；
    在功率最优值到功率最低值范围内进行搜索求解，以获得评优值，所述评优值表征为利用经济评价指标和清洁评价指标共同表示配电网运行优劣状态的评价指标。
  5. 根据权利要求4所述的一种分散式预测电网的优化方法，其中，基于分布式电源的产电成本量化得到经济评价指标，包括：
    获取每个分布式电源的产电成本，并将所有分布式电源的产电成本进行求和得到经济评价指标，所述经济评价指标的计算公式为：
    Figure PCTCN2022131017-appb-100002
    式中，X t表征为时刻t处的经济评价指标值，s i表征为第i个分布式电源的产电单价成本，W i,t＝P i,t*Δt，P i,t表征为在时刻t处第i个分布式电源的输出功率，Δt表征为时刻t处的瞬时时长，W i,t表征为在时刻t处第i个分布式电源的瞬时电能，M表征为分布式电源的总数目；
    将时刻t处的瞬时时长Δt量化为1个单位时间，则将经济评价指标的计算公式更新为：
    Figure PCTCN2022131017-appb-100003
  6. 根据权利要求5所述的一种分散式预测电网的优化方法，其中，基于分布式电源的污染物排放量量化得到清洁评价指标，包括：
    获取每个分布式电源产生的污染物、污染物产量以及污染物处理单价成本，并根据污染物、污染物产量以及污染物处理单价成本计算出所述清洁评价指标，所述清洁评价指标的计算公式为：
    Figure PCTCN2022131017-appb-100004
    式中，Y t表征为时刻t处的清洁评价指标值，v k表征为第k个污染物的污染物处理单价，Q i,t,k＝u k*W i,t，W i,t＝P i,t*Δt，P i,t表征为在时刻t处第i个分布式电源的输出功率，Δt表征为时刻t处的瞬时时长，W i,t表征为在时刻t处第 i个分布式电源的瞬时电能，u k表征为在产生瞬时电能W i,t时会产生第k个污染物产量的关联系数，Q i,t,k表征为在时刻t处第i个分布式电源产生的第k个污染物产量，M表征为分布式电源的总数目，n表征为污染物种类总数目，k为计量常数，无实质含义；
    将时刻t处的瞬时时长Δt量化为1个单位时间，则将经济评价指标的计算公式更新为：
    Figure PCTCN2022131017-appb-100005
  7. 根据权利要求6所述的一种分散式预测电网的优化方法，其中，所述利用经济评价指标和清洁评价指标共同组成评优值，包括：
    将经济评价指标和清洁评价指标进行加权求和得到评优值，所述评优值的计算公式为：
    F t＝αX t+βY t；
    式中，F t表征为时刻t处的评优值，α+β＝1，α∈[0,1]，β∈[0,1]，α、β分别为经济评价指标X t和清洁评价指标Y t的权重系数。
  8. 根据权利要求7所述的一种分散式预测电网的优化方法，其中，由分配模型计算出在未来时刻上得到的所述贡献度的分配值，包括：
    在未来时刻t+1处，将分布式电源(i∈[1,M])的输出功率的分配值P i,t+1(i∈[1,M])在功率最优值到功率最低值范围内进行取值搜索得到处最大评优值，并将最大评优值对应的P i,t+1(i∈[1,M])带入至贡献度的计算公式
    Figure PCTCN2022131017-appb-100006
    中计算得到分布式电源(i∈[1,M])贡献度的分配值h i,t+1(i∈[1,M])，将贡献度的分配值h i,t+1(i∈[1,M])作为调节基准，其中，P i,t+1表征为在未来时刻t+1处第i个分布式电源的输出功率的分配值，P j,t+1表征为在未来时刻t+1处第j个负载的额定功率，h i,t+1表征为由分配模型在未来时刻t+1处对第i个分布式电源的贡献度的分配值；
    所述搜索求解采用遗传算法进行求解。
  9. 根据权利要求8所述的一种分散式预测电网的优化方法，其中，对分布式电源进行动态调整直至神经网络在未来时刻上得到所述贡献度的预测值与调节基准一致，包括：
    根据分布式电源在未来时刻t+1处的贡献度的预测值h i,t+1′(i∈[1,M])以及贡献度的计算公式计算得到分布式电源在未来时刻t+1处输出功率的预测值P i,t+1′(i∈[1,M])；
    将分布式电源在未来时刻t+1处输出功率的预测值P i,t+1′(i∈[1,M])通过供 电参量进行调整直至预测值P i,t+1′(i∈[1,M])与分布式电源输出功率的分配值P i,t+1(i∈[1,M])相等，以实现所述贡献度的预测值与调节基准一致。
  10. 一种根据权利要求1-9任一项所述的分散式预测电网的优化方法的优化***，包括：
    数据采集模块，用于实时监测配电网中每个分布式电源为配电网负载提供的供电参量，以及配电网负载的用电参量；
    数据处理模块，用于基于所述供电参量计算出分布式电源的贡献度，以及对分布式电源在未来时刻上的所述贡献度进行预测，并在配电网中为分布式电源的贡献度构建分配模型；
    优化调节模块，用于将由分配模型在未来时刻上得到的所述贡献度的分配值作为调节基准，并对分布式电源进行动态调整直至神经网络在未来时刻上得到所述贡献度的预测值与调节基准一致。
PCT/CN2022/131017 2021-11-10 2022-11-10 一种分散式预测电网的优化方法及*** WO2023083235A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202111323378.1A CN113762650B (zh) 2021-11-10 2021-11-10 一种分散式预测电网的优化方法及***
CN202111323378.1 2021-11-10

Publications (1)

Publication Number Publication Date
WO2023083235A1 true WO2023083235A1 (zh) 2023-05-19

Family

ID=78784848

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/131017 WO2023083235A1 (zh) 2021-11-10 2022-11-10 一种分散式预测电网的优化方法及***

Country Status (2)

Country Link
CN (1) CN113762650B (zh)
WO (1) WO2023083235A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116629455A (zh) * 2023-07-19 2023-08-22 山西阳风新能售电有限公司 一种基于电力供电的智能定向预测方法
CN117557009A (zh) * 2024-01-12 2024-02-13 东莞市华灏技术有限公司 一种电源效率监测方法及***

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113762650B (zh) * 2021-11-10 2022-02-15 广东电网有限责任公司东莞供电局 一种分散式预测电网的优化方法及***

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150356213A1 (en) * 2014-06-06 2015-12-10 General Electric Company Method and system for generating electric load models
CN106981030A (zh) * 2017-03-22 2017-07-25 华中科技大学 一种对含dg的配电网的dg并网特性、接纳能力进行量化评估的方法
CN111509781A (zh) * 2019-01-30 2020-08-07 中国电力科学研究院有限公司 一种分布式电源协调优化控制方法及***
CN113378100A (zh) * 2021-05-25 2021-09-10 国网福建省电力有限公司 考虑碳排放的配电网源网荷储协同优化调度模型和方法
CN113762650A (zh) * 2021-11-10 2021-12-07 广东电网有限责任公司东莞供电局 一种分散式预测电网的优化方法及***

Family Cites Families (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104993522B (zh) * 2015-06-30 2018-01-19 中国电力科学研究院 一种基于mpc的主动配电网多时间尺度协调优化调度方法
CN105262129B (zh) * 2015-10-22 2018-01-16 华南理工大学 一种含复合储能微电网的多目标优化***及方法

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20150356213A1 (en) * 2014-06-06 2015-12-10 General Electric Company Method and system for generating electric load models
CN106981030A (zh) * 2017-03-22 2017-07-25 华中科技大学 一种对含dg的配电网的dg并网特性、接纳能力进行量化评估的方法
CN111509781A (zh) * 2019-01-30 2020-08-07 中国电力科学研究院有限公司 一种分布式电源协调优化控制方法及***
CN113378100A (zh) * 2021-05-25 2021-09-10 国网福建省电力有限公司 考虑碳排放的配电网源网荷储协同优化调度模型和方法
CN113762650A (zh) * 2021-11-10 2021-12-07 广东电网有限责任公司东莞供电局 一种分散式预测电网的优化方法及***

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116629455A (zh) * 2023-07-19 2023-08-22 山西阳风新能售电有限公司 一种基于电力供电的智能定向预测方法
CN116629455B (zh) * 2023-07-19 2023-10-31 山西阳风新能售电有限公司 一种基于电力供电的智能定向预测方法
CN117557009A (zh) * 2024-01-12 2024-02-13 东莞市华灏技术有限公司 一种电源效率监测方法及***
CN117557009B (zh) * 2024-01-12 2024-05-07 东莞市华灏技术有限公司 一种电源效率监测方法及***

Also Published As

Publication number Publication date
CN113762650B (zh) 2022-02-15
CN113762650A (zh) 2021-12-07

Similar Documents

Publication Publication Date Title
WO2023083235A1 (zh) 一种分散式预测电网的优化方法及***
CN113746144B (zh) 一种源网荷实时交互的电碳控制方法及其智能管理***
Fu et al. Planning of distributed renewable energy systems under uncertainty based on statistical machine learning
CN112510703B (zh) 一种考虑煤耗曲线修正的多能源接入电网优化调度方法
Gao et al. An iterative optimization and learning-based IoT system for energy management of connected buildings
CN110880055A (zh) 楼宇智能电表***
Liu et al. Multi-objective optimization strategy of integrated electric-heat system based on energy storage situation division
Zou et al. Hierarchical evaluation framework for coupling effect enhancement of renewable energy and thermal power coupling generation system
CN105162129A (zh) 计及分布式电源最优配置的配网无功电压控制方法
Li et al. Control method of multi-energy system based on layered control architecture
Fan et al. Study on load monitoring and demand side management strategy based on Elman neural network optimized by sparrow search algorithm
Gao et al. Thermoelectric optimization of integrated energy system considering wind-photovoltaic uncertainty, two-stage power-to-gas and ladder-type carbon trading
Liu et al. Research on peak load shifting for hybrid energy system with wind power and energy storage based on situation awareness
CN116468302A (zh) 建筑园区能源结构评估方法、***、电子设备及存储介质
Cai et al. Intra-day Tie-line Scheduling Model Considering New Energy Fluctuation
Sha et al. New Energy Limit Consumption Capacity Evaluation based on Single station-partition-whole network
Jie et al. Power grid two-level dispatch strategy with participation of electric heating load
Xuan et al. Research on short-term load forecasting model of integral energy system considering demand side response
Ye et al. Design of Multi-Objective Optimal Control Algorithm for Flexible Load of Urban Electric Warehouse Based on Model Prediction
Yang et al. Dual-layer flexibility dispatching of distributed integrated energy systems incorporating resilient heating schemes based on the standardized thermal resistance method
Ren et al. Research on Aggregate Load Prediction Methods
Wang et al. A Collaborative Planning Model of Power Source Considering the Uncertainty of The New Energy and The Power Market
Chen et al. Power Grid Dispatch with High Proportion of New Energy Integration
Du et al. The heating load control method of load aggregators based on cluster analysis
Huimin Flexible Adjustment Resource Allocation Method for High Proportion of New Energy Areas based on K-means Clustering

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22892029

Country of ref document: EP

Kind code of ref document: A1