AN ADAPTIVE NEURAL-NETWORK APPROACH TO ONE-WEEK AHEAD LOAD FORECASTING

A new neural network approach is applied to one-week ahead load foreca sting. This approach uses a linear adaptive neuron or adaptive linear combiner called ''Adaline''. An energy spectrum is used to analyze the periodic components in a load sequence. The load sequence mainly cons ists of three components: base load component, and low and high freque ncy load components. Each load component has a unique frequency range. Load decomposition is made for the load sequence using digital filter s with different passband frequencies After load decomposition, each l oad component can be forecasted by an Adaline. Each Adaline has an inp ut sequence, an output sequence, and a desired response-signal sequenc e. It also has a set of adjustable parameters called the weight vector . In load forecasting. the weight vector is designed to make the outpu t sequence, the forecasted load, follow the actual load sequence; it a lso has a minimized Least Mean Square error. This approach is useful i n forecasting unit scheduling commitments. Mean absolute percentage er rors of less than 3.4 percent are derived from five months of utility data, thus demonstrating the high degree of accuracy that can be obtai ned without dependence on weather forecasts.