Electric load forecasting has become crucial to the safe operation of power grids and cost reduction in production power. Although numerous electric models have been proposed, most them are still limited by poor effectiveness model training a sensitivity outliers. The limitations current methods may lead extra operational costs system or even disrupt its distribution network safety. To this end...

In energy demand forecasting, the objective function is often symmetric, implying that over-prediction errors and under-prediction have same consequences. practice, these two types of generally incur very different costs. To accommodate this, we propose a machine learning algorithm with cost-oriented asymmetric loss in training procedure. Specifically, develop new support vector regression inco...

Forecasting electric demand and its geographical distribution is a prerequisite to generate expansion planning scenarios for distribution planning. This paper presents a comprehensive methodology that uses a fuzzy inference model over a GIS support, to capture the behavior of influence factors on load growth patterns and map the potentia1 for development. The load growth is spread over maps wit...

Load forecasting (LF) is an essential factor in power system management. LF helps the utility maximize utilization of power-generating plants and schedule them both reliably economically. In this paper, a novel hybrid method proposed, combining long short-term memory network (LSTM) neural prophet (NP) through artificial network. The paper aims to predict electric load for different time horizon...

Paper aims This study analyzed the feasibility of BiGRU-CNN artificial neural network as a forecasting tool for short-term electric load. model can serve support related to decision-making by companies in energy sector. Originality Despite large amount scientific research this area, literature still searches more assertive models regarding Thus, model, based on layers BiGRU and CNN architecture...