Multi-Objective Residential Electricity Scheduling Based on Forecasting Generation and Demand via LSTM
This paper proposes a combined day-ahead forecasting and scheduling energy management system (EMS) with multiple complimentary objectives on household level. Our comparative case study, analyses, economical, ecological and grid independence aspects of our model include the utilization of renewable energy source (RES) with a controllable diesel generator and an energy storage system (ESS). The latter includes both stationary and electric vehicle batteries. The forecasting of RES and uncontrollable load of a single household is based on an LSTM approach, which is then used for day-ahead electricity scheduling. In order to be consistent with the forecasting horizon, day-ahead wholesale electricity market prices are used.
(Accepted) 2020 IEEE Power & Energy Society Innovative Smart Grid Technologies Europe (ISGT-Europe), The Hague, The Netherlands, 2020