Multi-agent reinforcement learning power distribution network optimization method taking distributed photovoltaic absorption as target

Multi-agent reinforcement learning power distribution network optimization method taking distributed photovoltaic absorption as target

The invention relates to a multi-agent reinforcement learning power distribution network optimization method with distributed photovoltaic consumption as a target. The method comprises the following steps: step 1, constructing a power distribution network optimization model with distributed photovol...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: ZHAO CHUNLI, SHANG XINGMING, WU YIXUAN, GAO ZIWEI, LI BEN, CHONG FEI, LEE CHANG-WON, WANG YUE, ZHANG HAO, LI DEQIANG, YE JU, LIU KAI, WU TONG, KONG LINGYU, DONG HANG, PENG YIZHOU, WEI GUOHUA, BAI JIE, GE LEIJIAO, LI BOZHEN, LIU ZHANGE, QIAN XIN
Format: Patent
Sprache:chi ; eng
Schlagworte:
CALCULATING
CIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTINGELECTRIC POWER
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
COUNTING
DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES
ELECTRICITY
GENERATION
PHYSICS
SYSTEMS FOR STORING ELECTRIC ENERGY
SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:The invention relates to a multi-agent reinforcement learning power distribution network optimization method with distributed photovoltaic consumption as a target. The method comprises the following steps: step 1, constructing a power distribution network optimization model with distributed photovoltaic consumption as a target; 2, modeling the power distribution network optimization system model in the step 1 into a Markov decision process, and constructing a body solving framework of the power distribution network optimization model based on the multi-agent Markov decision process; step 3, based on the power distribution network optimization model solving framework in the step 2, solving the power distribution network optimization model by using a multi-agent soft-act-critic algorithm; and 4, optimizing the power distribution network by using the strategy neural network trained in the step 3. According to the invention, voltage violation and photovoltaic power reduction can be reduced to the greatest extent.