Load Forecasting and ESS Scheduling Considering the Load Pattern of Building

Abstract

-This study presents the electrical load forecasting and error correction method using a real building load pattern, and the way to manage the energy storage system with forecasting results for economical load operation. To make a unique pattern of target load, we performed the Hierarchical clustering that is one of the data mining techniques, defined load pattern(group) and forecasted the demand load according to the clustering result of electrical load through the previous study. In this paper, we propose the new reference demand for improving a predictive accuracy of load demand forecasting. In addition we study an error correction method for response of load events in demand load forecasting, and verify the effects of proposed correction method through EMS scheduling simulation with load forecasting correction.

Investment Decision for Long-Term Battery Energy Storage System Using Least Squares Monte Carlo

“…Yoon utilized a Genetic Algorithm, and M. M. Alam planned the charging and discharging schedules of an ESS through LSTM [29,30]. Research was also conducted using Dynamic Programming, a Mixed-Logit model, and Mixed-Integer Linear Programming [31][32][33][34][35]. Mauricio B. C. Salles studied the potential arbitrage of ESSs by choosing parameter values anticipated for future mature flow battery technology but did not consider actual installed costs [36].…”