Short-term load forecasting is crucial for the operations planning of an electrical grid. Forecasting the next 24 h of electrical load in a grid allows operators to plan and optimize their resources. The purpose of this study is to develop a more accurate short-term load forecasting method utilizing non-linear autoregressive artificial neural networks (ANN) with exogenous multi-variable input (NARX). The proposed implementation of the network is new: the neural network is trained in open-loop using actual load and weather data, and then, the network is placed in closed-loop to generate a forecast using the predicted load as the feedback input. Unlike the existing short-term load forecasting methods using ANNs, the proposed method uses its own output as the input in order to improve the accuracy, thus effectively implementing a feedback loop for the load, making it less dependent on external data. Using the proposed framework, mean absolute percent errors in the forecast in the order of 1% have been achieved, which is a 30% improvement on the average error using feedforward ANNs, ARMAX and state space methods, which can result in large savings by avoiding commissioning of unnecessary power plants. The New England electrical load data are used to train and validate the forecast prediction.

No abstract

Smart Grids require a clear understanding of consumer demand patterns. Classification of consumers according to their demand pattern is required for the effective planning of tariffs, eligibility for demand-side management (DSM) programs, energy production and transmission, as well as for security purposes. We propose a framework for classification of consumer load patterns using a hybrid system with a parameter estimation model, a clustering model and an artificial neural network (ANN). The proposed model provides an effective unbiased classification method. The process starts with generating a training data set from existing consumers without a priori classification. The raw load data is processed through a parameter estimation model and a clustering algorithm to generate a training data set with distinct impartial classification clusters. The training data is fed to an ANN for learning. Once the load patterns are learned, the model can be used to further classify new consumers into a demand pattern. The ANN provides fast and accurate clustering performance without underlying assumptions about shape or class. An analysis of the optimal number of clusters is presented. Results indicate that clusters with distinguishable characteristics are achieved and we demonstrate how regulators can make use of this method in demand curtailment planning.