Data-Driven Load Forecasting of Air Conditioners for Demand Response Using Levenberg–Marquardt Algorithm-Based ANN

摘要

Air Conditioners (AC) impact in overall electricity consumption in buildings is very high.Therefore, controlling ACs power consumption is a significant factor for demand response. With theadvancement in the area of demand side management techniques implementation and smart grid,precise AC load forecasting for electrical utilities and end-users is required. In this paper, big dataanalysis and its applications in power systems is introduced. After this, various load forecastingcategories and various techniques applied for load forecasting in context of big data analysis inpower systems have been explored. Then, Levenberg–Marquardt Algorithm (LMA)-based ArtificialNeural Network (ANN) for residential AC short-term load forecasting is presented. This forecastingapproach utilizes past hourly temperature observations and AC load as input variables for assessment.Different performance assessment indices have also been investigated. Error formulations haveshown that LMA-based ANN presents better results in comparison to Scaled Conjugate Gradient(SCG) and statistical regression approach. Furthermore, information of AC load is obtainable fordifferent time horizons like weekly, hourly, and monthly bases due to better prediction accuracy ofLMA-based ANN, which is helpful for efficient demand response (DR) implementation.