Short term load forecast of Kano zone using artificial intelligent techniques

Huzaimu Lawal Imam (Bayero University, Kano)
M.S Gaya (Kano University of Science and Technology)
G. S. M Galadanci (Bayero University, Kano)

Indonesian Journal of Electrical Engineering and Computer Science
Vol 16, No 2: November 2019

Load forecast provides useful information for effective electricity dispatch, planning for future expansion and significantly enhances operational efficiency. Conventional techniques yield unsatisfactory forecast which results in high energy losses and in turn leads to high operational cost and suppressed electricity demand. This paper presents hybrid neuro fuzzy (HNF) and Nonlinear Auto-Regressive with eXogeneous input (NARX) neural network for the short term load prediction of Kano region Nigeria.  Simulation results obtained demonstrated the generalization capabilities of the models in predicting the load accurately well by achieving MAPE of 0.025% and 0.6551% for the HNF model and NARX network model respectively. The models could serve as promising tool for predicting Kano Zone load demand.