Accurate metering and billing of actual energy consumed by consumers is integral to commercial management of an electric utility. An aggregate technical and commercial loss in India is around 27% and this is very high in spite of various reforms and measures by electricity boards across country. One of the significant components of these losses is Theft. Electricity theft is a grave problem across the globe. Improvement in aggregate technical and commercial losses in phased manner is very important for financial and technical viability of distribution companies in deregulated environment. The major challenge is to identify the location of the theft and estimate the amount of energy being stolen. Research to identify power pilferages and remedial measures to overcome them in electricity sector has been going on in recent years. The Paper proposes a conceptual approach to get both the approximate location and estimate of energy theft at that location. With both information available in real time, it will completely change the landscape of electrical sector across the nation.

Accurate models for electric power load forecasting are essential for the operation and planning of power system from technical as well as financial perspective. Paper proposes an approach for short term electric load forecasting based on parameters which have been arrived from past load data using artificial neural network based Non linear autoregressive network exogenous technique. Novel approach for obtaining the seasonality factor, weekly trend and load increase pattern from past electricity consumption data are also proposed. Proposed methodology requires lesser real time inputs such as weather information. The real time active power load consumption data in MW for two and half years of Goa Electricity Board of Goa state from India is used for predicting future load demand. The results obtained from the model successfully predicts the future load data for week days with mean square error less than 1.67% and mean absolute deviation of 3.6%, which proves suitability of our proposed technique for forecasting.

No abstract