Finding suitable forecasting methods for an effective management of energy resources is of paramount importance for improving the efficiency in energy consumption and decreasing its impact on the environment. Natural gas is one of the main sources of electrical energy in Algeria and worldwide. To address this demand, this paper introduces a novel hybrid forecasting approach that resolves the two-stage method's deficiency, by designing a Multi Layered Perceptron (MLP) neural network as a nonlinear forecasting model. This model estimates the next day gas consumption profile and selects one of several local models to perform the forecast. The study focuses firstly on an analysis and clustering of natural gas daily consumption profiles, and secondly on building a comprehensive Long Short Term Memory (LSTM) recurrent models according to load behavior. The results are compared with four benchmark approaches: the MLP neural network approach, LSTM, seasonal time series with exogenous variables models and multiple linear regression models. Compared with these alternative approaches and their high dependence on historical loads, the proposed approach presents a new efficient functionality. It estimates the next day consumption profile, which leads to a significant improvement of the forecasting accuracy, especially for days with exceptional customers consumption behavior change.
Knowing that electrical load is a non storable resource; short term electric load forecasting becomes an important tool to optimise dispatching of electrical load in regular system planning. Several techniques have been used to accomplish this task, from traditional linear regression and Box-Jenkins to artificial intelligence approaches such as Artificial Neural Networks (ANN). This work presents a comparative study of serial and parallel ANN approaches for forecasting 168 hours ahead using a multiple linear regression model as a benchmark for comparison. The results obtained by the latter method, are compared with the ANN serial and parallel developed approaches. These models were trained solemnly on past load consumption data, given by the Algerian national electricity company. This results in Nonlinear Autoregressive Models (NAR), however once the approach validity is proven, the addition of exogenous inputs can only improve model results.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.