Adaptive Fuzzy Logic Controller Based Energy Management for a Stand-alone PV Hybrid System with Battery and Hydrogen Storage Path

Abstract

The paper describes a novel adaptive fuzzy logic controller based energy management concept (A-FLC-EM) for a stand-alone photovoltaic (PV) hybrid system with battery and hydrogen storage path. The reference application is a single family home. The basic idea is to switch and optimally adjust the energy management parameters according to identified changes of distinct longterm energy supply and/or demand situations. Key elements of the offline learning phase are the analysis of the energy time series and the automatic determination of distinct energy situations on the basis of a segmentation algorithm and a vector of suitable statistical features calculated for a short-term, sliding observation window. A bottom-up approach is used, ranking and selecting statistical features that are particularly good at distinguishing certain long-term energy situations. The selected features form the basis for a clustering algorithm to detect and describe distinct energy situations. For each energy situation, the calculation of optimal energy management parameters is performed for a training data set employing particle swarm optimization (PSO). The performance of the novel A-FLC-EM is demonstrated compared to a conventional fuzzy logic controller based energy management (FLC-EM) with an all-year fixed parameter setting. Qualitative and quantitative improvements as well as further challenges are discussed.