Short-Term Load Forecast of Microgrids by a New Bilevel Prediction Strategy

Abstract

Microgrids are a rapidly growing sector of smart grids, which will be an essential component in the trend toward distributed electricity generation. In the operation of a microgrid, forecasting the short-term load is an important task. With a more accurate short-term loaf forecast (STLF), the microgrid can enhance the management of its renewable and conventional resources and improve the economics of energy trade with electricity markets. However, STLF for microgrids is a complex forecast process, mainly because of the highly nonsmooth and nonlinear behavior of the load time series. In this paper, characteristics of the load time series of a typical microgrid are discussed and the differences with the load time series of traditional power systems are described. In addition, a new bilevel prediction strategy is proposed for STLF of microgrids. The proposed strategy is composed of a feature selection technique and a forecast engine (including neural network and evolutionary algorithm) in the lower level as the forecaster and an enhanced differential evolution algorithm in the upper level for optimizing the performance of the forecaster. The effectiveness of the proposed prediction strategy is evaluated by the real-life data of a university campus in Canada.