Search

An accurate load forecast is always important for the power industry and energy players as it enables stakeholders to make critical decisions. In addition, its importance is further increased with growing uncertainties in the generation sector due to the high penetration of renewable energy and the introduction of demand side management strategies. An incremental improvement in grid-level demand forecast of anomalous days can potentially save millions of dollars. However, due to an increasing penetration of renewable energy resources and their dependency on several meteorological and exogenous variables, accurate load forecasting of anomalous days has now become very challenging. To improve the prediction accuracy of the load forecasting, an ensemble forecast framework (ENFF) is proposed with a systematic combination of three multiple predictors, namely Elman neural network (ELM), feedforward neural network (FNN) and radial basis function (RBF) neural network. These predictors are trained using global particle swarm optimization (GPSO) to improve their prediction capability in the ENFF. The outputs of individual predictors are combined using a trim aggregation technique by removing forecasting anomalies. Real recorded data of New England ISO grid is used for training and testing of the ENFF for anomalous days. The forecast results of the proposed ENFF indicate a significant improvement in prediction accuracy in comparison to autoregressive integrated moving average (ARIMA) and back-propagation neural networks (BPNN) based benchmark models.

The uncertainty associated with solar photo-voltaic (PV) power output is a big challenge to design, manage and implement effective demand response and management strategies. Therefore, an accurate PV power output forecast is an utmost importance to allow seamless integration and a higher level of penetration. In this research, a neural network ensemble (NNE) scheme is proposed, which is based on particle swarm optimization (PSO) trained feedforward neural network (FNN). Five different FFN structures with varying network complexities are used to achieve the diverse and accurate forecast results. These results are combined using trim aggregation after removing the upper and lower forecast error extremes. Correlated variables namely wavelet transformed historical power output of PV, solar irradiance, wind speed, temperature and humidity are applied as inputs to the multivariate NNE. Clearness index is used to classify days into clear, cloudy and partial cloudy days. Test case studies are designed to predict the solar output for these days selected from all seasons. The performance of the proposed framework is analyzed by applying training data set of different resolution, length and quality from seven solar PV sites of the University of Queensland, Australia. The forecast results demonstrate that the proposed framework improves the forecast accuracy significantly in comparison with individual and benchmark models.