Electric utilities require short-term forecasts of electricity demand (load) in order to schedule generating plant up to several days ahead on an hourly basis. Errors in the forecasts may lead to generation plant operation that is not required or sub-optimal scheduling of generation plants. In addition, with the introduction of the Electricity Regulation Act 1999, a deregulated market structure has been introduced, adding increased impetus to reducing forecast error and the associated costs. This thesis presents a strategy for reducing costs from electrical demand forecast error using models designed specifically for the Irish system. The differences in short-term load forecasting models are examined under three independent categories: how the data is segmented prior to modelling, the modelling technique and the approach taken to minimise the effect of weather forecast errors present in weather inputs to the load forecasting models. A novel approach is presented to determine whether the data should be segmented by hour of the day prior to modelling. Several segmentation strategies are analysed and the one appropriate for Irish data identified. Furthermore, both linear and nonlinear techniques are compared with a view to evaluating the optimal model type. The effect of weather forecast errors on load forecasting models, though significant, has largely been ignored in the literature. Thus, the underlying issues are examined and a novel method is presented which minimises the effect of weather forecast errors.