Effective bulk energy consumption control and management for power utilities using artificial intelligence techniques under conventional and renewable energy resources

Increasing sustainability demands initiate estimating various design and control opportunities for classifying energy-efficient plan ever more significant. These conditions demand simulation algorithms which are not only fast, but also accurate. Artificial intelligence (AI) enables efficient mimicry of bulk energy consumption control while producing results much faster than data-mining and machine learning models. This study proposes two AI based approaches for utilities bulk energy consumption prediction, control and management. Two different zones actual environmental and energy consumption data are obtained for input feature selection and modeling analysis. Each zone is categorized into five features parameter selection (PS) states. Each PS state is further divided into four different hidden neurons (HD) and hidden layers of the model's network. The forecasting duration is based on 1-month and 1-year ahead intervals for medium-term (MT) and long-term (LT) respectively. Further the current proposed model's performance is compared with three existing models. One of the promising findings in this research is that substantial improvement in prediction accuracy applying features extracted by PS-3 and PS-5. Results show that AI models are powerful in solving complex and nonlinear patterns of raw data. This study renders optimal decisions can be projected while utilities energy supply strategy & control, capacity expansion, capital investment research market management, revenue analysis and future load requirement forecasting.