WSEAS Transactions on Power Systems
Print ISSN: 1790-5060, E-ISSN: 2224-350X
Volume 13, 2018
Prediction of the Long-Term Electrical Energy Consumption in Greece Using Adaptive Algorithms
Authors: ,
Abstract: Planning the electricity grid is an ahead-looking process that requires long term prediction for a time interval greater than one year. The importance of accurate of long-term load forecasting cannot be overlooked, since it provides the future load demand; a crucial factor that is considered in scheduling the generation, transmission and distribution of the electrical energy, reliably and economically. In this study real data is used and the performance of the combination of the well-established multimodel partitioning filter (MMPF) implementing extended Kalman filters (EKF) with Support Vector Machines (SVM), is compared to the one of an artificial multilayer layer feed-forward neural network (ANN). The results indicate that both methods are reliable, however the combination of MMPF and SVM provides a more accurate long-term load forecasting. The proposed method is a useful tool since the electric system administrator based on its forecasts will able to use efficiently the current resources in order to meet the forecasted demand using a least-cost plan.
Search Articles
Keywords: Artificial neural networks, energy consumption, gross domestic product, extended kalman filters, multi model partitioning filter, support vector machines, installed capacity
Pages: 291-299
WSEAS Transactions on Power Systems, ISSN / E-ISSN: 1790-5060 / 2224-350X, Volume 13, 2018, Art. #29