Short Term Load Demand Forecasting for Transnet Port Terminal (TPT) in East London Using Artificial Neural Network
Mncedisi Figlan (CUT, South Africa); Elisha Markus (Central University of Technology & Free State South Africa, South Africa)
The stochastic nature of energy consumption patterns in the port varies by day and week. The ongoing supply of electricity to port consumers requires an accurate and adequate Short-Term Load Forecast (STLF) for quality, quantity and efficiency. Most researchers have recently proposed Artificial Neural Networks (ANNs) for short-term load forecasting. This research is aimed at creating a more exact method of short-term load forecasting using the non-linear, autoregressive, multi-variable exogenous input (NARX) ANNs. The suggested network architecture is new: the neural network is open-loop training with real load and weather information, and then a closed-loop network is used to produce a prediction with the predicted load as its feedback data. In comparison to the current ANN short-term load forecasting models, the proposed method utilizes its own performance to improve precision, essentially implementing a load feedback loop that is less dependent on external data. With the suggested system, mean absolute percentage errors were reached in the forecast range of 1%, an improvement of 30% on the average error by feedforward ANNs. This model is tested using actual reticulation network load data from Transnet Port Terminal in East London and climate statistics to predict port terminal load for a week in advance.
Conference: UKSim-AMSS 22nd International Conference on Computer Modelling and Simulation, UKSim2020
Published: Mar 25, 2020