A hierarchical hybrid neural model in short-term load forecasting

This paper proposes a novel neural model to the problem of short-term load forecasting. The neural model is made up of two self-organizing map nets — one on top of the other —, and a single-layer per-ceptron. It has application into domains in which the context information given by former events plays a pri-mary role. The model was trained and assessed on load data extracted from a Brazilian electric utility. It was required to predict once every hour the electric load dur-ing the next six hours. The paper presents the results, and evaluates them.