Bayesian-based electrical load forecasting in three time-horizons

"Load forecasting is vitally important for the electric industry in the deregulated economy. It has many applications including energy purchasing and generation, load switching, contract evaluation, and infrastructure development. In addition, nowadays, exogenous variables also form an important part of load forecasting. Exogenous factors refer to weather condition, trees, vehicular accidents, construction accidents, animals, pollution, and operation and maintenance factors such as switching, faults, sustained overloading, and equipment condition.  Load forecasts can be divided into three categories: short-term forecasts which are usually from one hour to one week, medium forecasts which are usually from a week to a year, and long-term forecasts which are longer than a year. The forecasts for different time horizons are important for different operations within a utility company. In the past, a large variety of mathematical methods have been developed for load forecasting. Most forecasting methods use statistical techniques or artificial intelligence algorithms such as regression, neural networks, fuzzy logic, and expert systems. Two of the methods, so-called end-use and econometric approach are broadly used for medium- and long-term forecasting. A variety of methods, which include the so-called similar day approach, various regression models, time series, neural networks, statistical learning algorithms, fuzzy logic, and expert systems, have been developed for short-term forecasting. In my proposed study, Bayesian Network (BN) is planned to be considered. BN is one of the most efficient probabilistic graphical models to represent uncertain information and inferences thereof. Although BNs have been applied in reliability assessment, fault detection, prediction of weather-related failures of overhead lines and fault location finding, but little or no work is done in the area of load forecasting in different time-horizons. With my proposed approach, a platform will be constructed in which it would be feasible to forecast load in all time-horizons."