Power load forecasting is an essential tool for energy management systems. Accurate load forecasting supports power companies to make unit commitment decisions and schedule maintenance plans appropriately. In addition to minimizing the power generation costs, it is also important for the reliability of energy systems. This research study presents the implementation of a novel fuzzy wavelet neural network model on an hourly basis, and validates its performance on the prediction of electricity consumption of the power system of the Greek Island of Crete. In the proposed framework, a multiplication wavelet neural network has replaced the classic linear model, which usually appears in the consequent part of a neurofuzzy scheme, while subtractive clustering with the aid of the Expectation–Maximization algorithm is being utilized in the definition of fuzzy rules. The results related to the minimum and maximum load using metered data obtained from the power system of the Greek Island of Crete indicate that the proposed forecasting model provides significantly better forecasts, compared to conventional neural networks models applied on the same dataset.