One-Day-Ahead Hourly Load Forecasting of Smart Building Using a Hybrid Approach

摘要

This paper proposes a hybrid approach to solve the one-day-ahead hourly load forecasting of smart building. The electricity consumption of a smart building is inherently nonlinear and dynamic and heavily dependent on the habitual nature of power demand, activities of daily living and on holidays or weekends, so it is often difficult to construct an adequate forecasting model for this type of load. To address this problem, this paper proposes a hybrid approach combining self-organizing map (SOM), learning vector quantization (LVQ), and fuzzy inference method to offer more adequate forecasting model for smart building. The proposed model comprises classification stage, forecasting stage, and correction stage. The forecasting results show that the proposed approach provides a robust and appropriate forecasting model.