A Multi-Agent Shared Machine Learning Approach for Real-time Battery Operation Mode Prediction and Control

This paper introduces a machine learning approach for real-time battery operation mode prediction and control for residential PV applications. The novelty resides in the shared learning process among the devices. All the ESDs will share their historical data with a learning aggregator in order to train a ML algorithm for the mode prediction. The learning aggregator will then send the trained algorithm back to the agents. Its role will be to train and maintain the ML algorithm. First, from the historical data, the optimal battery operation mode for each operation time step is derived. Performances are tested with different number of houses in the training test and different training lengths. The month of August is reserved for testing, while the rest of year is used for training. In the first scenario, the same houses used in the training are used in the testing. In the second scenario, one set of houses is used for training and the other set for testing. Then, the shared-algorithm will be used to predict future operation mode for real-time operation. A comparison on bill savings is made with the model-predictive control approach using the residential load and PV data from the Pecan Street project website under a self-consumption case.