Medium Term Electric Load Forecasting Using TLFN Neural Networks

This paper develops medium term electric load forecasting using neu- ral networks, based on historical series of electric load, economic and demographic variables. The neural network chosen for this work is the Time Lagged Feedfor- ward Network (TLFN), which combines conventional network topology (multilayer perceptron) with good handling of time dependencies by means of gamma memory. This is a versatile mechanism that generalizes the short term structures of memory, based on delays and recurrences. This scheme allows smaller adjustments without re- quiring changes in the general network structure. The neural model gave satisfactory results exceeding those obtained by classical statistical models like multiple linear regression.