A Study of Load Demand Forecasting Models in Electricity Using Artificial Neural Networks and Fuzzy Logic Model

Since load time series are very changeable, demand forecasting of the short-term load is challenging based on hourly, daily, weekly, and monthly load forecast demand. as a result, the turkish electricity transmission company (tea) load forecasting is proposed in this paper using artificial neural networks (ann) and fuzzy logic (fl). load forecasting enables utilities to purchase and generate electricity, load shift, and build infrastructure. a load forecast was classified into three sorts (hourly, weekly and monthly). over time, forecasting power loads with artificial neural networks and fuzzy logic reveals a massive decrease in ann and a progressive increase in fl from 24 to 168 hours. as illustrated, fuzzy logic and artificial neural networks outperform regression algorithms. this study has the highest growth and means absolute percentage error (mape) rates compared to fl and ann. although regression has the highest prediction growth rate, it is less precise than fl and ann due to their lower mape percentage. artificial neural networks and fuzzy logic are emerging technologies capable of forecasting and mitigating demand volatility. future research can forecast various turkish states using the same approach.