Domestic energy management and control method and system based on relation deep reinforcement learning

• Main Authors: GAO LINGYUE, SUN BO, LIU CHE
• Format: Patent
• Language: Chinese; English
• Published: 03.06.2022
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; DATA PROCESSING SYSTEMS OR METHODS, SPECIALLY ADAPTED FORADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORYOR FORECASTING PURPOSES; PHYSICS; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE,COMMERCIAL, FINANCIAL, MANAGERIAL, SUPERVISORY OR FORECASTINGPURPOSES, NOT OTHERWISE PROVIDED FOR

The invention provides a family energy management and control method and system based on relation deep reinforcement learning. The method comprises the following steps: acquiring an initial state of household electric equipment of a set user at an energy to-be-configured date; on the basis of the obtained initial state of the household electric equipment and the trained daily energy consumption type classification model, predicting the energy consumption type of the household electric equipment at the date to be configured; adding the predicted energy consumption type and the timestamp of the energy to-be-configured date as features into a state variable of the reinforcement learning household energy management model; and extracting the relevance between the actions of the household electric equipment and the relevance between the household electric equipment and the time from the reinforcement learning household energy management model by utilizing a relation deep reinforcement learning method, and further f