Artificial Neural Network Based Short-term Load Forecasting For The Ethiopian Electric And Power Corpora Tion-(eepco)

Load forecasting has become, in recent years, one of the major areas of research.rnMost traditional forecasting and artificial intelligence researches have tried out thisrntask. Artificial neural networks (ANNs) have lately received much attention, andrnsuccessful experiments and practical tests have been reported. This work studies thernapplicability of this kind of model procrastinating.The multi-layered feed-forward neural network, that are capable of representing nonlinearrnfictional mappings between inputs and outputs was used to model the short termrnload to recast for the Ethiopian electric and power corporation (EEPCO). Thernnetwork was trained with the error back-propagation method. Two models werernstudied in this whole process. The first one is forecasting the load one hour aheadrnand secondly the daily peak load forecast.The test results, based on historical demand, indicates that this methodology isrncapable of providing accurate forecasts with 1.1 % and 1.3 % average absoluternforecast errors for the hourly and daily peak load forecasts respectively.

Get Full Work

Report copyright infringement or plagiarism