Load forecasting for diurnal management of community battery systems

Abstract

This paper compares three methods of load forecasting for the optimum management of community battery storages. These are distributed within the low voltage (LV) distribution network for voltage management, energy arbitrage or peak load reduction. The methods compared include: a neural network (NN) based prediction scheme that utilizes the load history and the current metrological conditions; a wavelet neural network (WNN) model which aims to separate the low and high frequency components of the consumer load and an artificial neural network and fuzzy inference system (ANFIS) approach. The batteries have limited capacity and have a significant operational cost. The load forecasts are used within a receding horizon optimization system that determines the state of charge (SOC) profile for a battery that minimizes a cost function based on energy supply and battery wear costs. Within the optimization system, the SOC daily profile is represented by a compact vector of Fourier series coefficients. The study is based upon data recorded within the Perth Solar City high penetration photovoltaic (PV) field trials. The trial studied 77 consumers with 29 rooftop solar systems that were connected in one LV network. Data were available from consumer smart meters and a data logger connected to the LV network supply transformer.