Browsing by Author "AL-ANI, BARQ RAAD KHASHEI"
Now showing 1 - 1 of 1
Results Per Page
Sort Options
Item LOAD DEMAND FORECASTING USING ARTIFICIAL NEURAL NETWORKS AND FUZZY LOGIC METHODS(2022-05-12) AL-ANI, BARQ RAAD KHASHEI; ERKAN, Turan ErmanThis study proposes using artificial neural networks (ANNs) and fuzzy logic (FL) to estimate load demand data to forecast hourly electricity loads in Turkey or 2017 and 2018. We used Real Time Consumption as hourly electric load based on EPİAŞ data for 2017 to 2018. The load forecast was actualized using two machine learning techniques: ANN and fuzzy logic FL. The predicted data was compared to the actual data by plotting on a graph. This study used the ANN and FL methods to optimise the demand for load forecast in Turkey's power systems. The first and last 200 hours were plotted on ANN to get a better visualisation pattern, and the overall estimated hourly load for Turkey was calculated by adding the hourly estimations from each area. The minimum and maximum readings for the year 2017 are 18851.35 MWh and 47062.40 MWh whereas the mean and standard deviation readings are 33102.19 Mwh and 4968.67 MWh. As a result, the comparison of these models was used to forecast the load, all of which have different load patterns and origins. The series are stationary across the year and it peaks during the month of August. The MAPE values for FL for 2017 and 2018 are 3.7986094 and 5.28635983 respectively which is very good and falls in high accurate forecasting results. It can be concluded that the FL gives a better prediction than the ANN for both years. Electrical peak reduction is a vital component of any plan for managing energy demand, and forecasting electric load assists in planning peak load demand reductions to meet energy demand management targets. It can be concluded that the FL gives us a better prediction than the ANN for both years. Home, energy management research will benefit from the new load forecasting models proposed in this study.