Artificial Neural Network Based Short-Term Load Forecasting of Nuwakot Distribution Center Using Smart Meter AMI Data

Load forecasting facilitates the distribution system operator for accurate estimation of resource requirements and necessary action plans to maintain their electricity supply-demand balance. With recent advancements in smart meter and Advanced Metering Infrastructure (AMI) technologies, an immense amount of fine-grained end-use data is being collected enabling utilities to analyze accurate energy consumption patterns and future demand projections. This paper proposes a Neural Network (NN) based short-term electric demand forecasting on the aggregate level for a distribution network at Nepal Electricity Authority (NEA), Nuwakot Distribution Center (NDC). The relationship between present and historical energy consumption patterns along with temperature data is used to train the NN model and the applicability of the model is tested using the real load data from the Nepalese utility, Nepal Electricity Authority. A day ahead demand forecasting of Nuwakot Distribution Center for different time series with reasonable load forecasting error is obtained.