Short‐term load forecasting in smart grids using artificial intelligence methods: A survey

Electrical load forecasting is crucial to achieving better efficiency, reliability, and power quality in modern systems. Applying short-term forecasting, a balance can be preserved between supply demand; the cost of electricity production will also decreased. Several methods are proposed for smart grids recent years each them has its own advantages weaknesses. Among these methods, popularity increasing machine learning techniques. This study review three common artificial intelligence including long memory, group method data handling, adaptive neuro-fuzzy inference system that have been used forecast grid consisting photovoltaic, wind turbine, battery energy storage system, electric vehicle charging stations. The performance evaluated given accuracy system's hardware requirements. noisy condition investigated when forecasting. results show memory model more accurate than handling models. However, this requires much