Computational Models Development and Demand Response Application for Smart Grids

Abstract

Abstract. This paper focuses on computational models development and its applications on demand response, within smart grid scope. A prosumer model is presented and the corresponding economic dispatch problem solution is analyzed. The prosumer solar radiation production and energy consumption are forecasted by artificial neural networks. The existing demand response models are studied and a computational tool based on fuzzy clustering algorithm is developed and the results discussed. Consumer energy management applications within the InovGrid pilot project are presented. Computation systems are developed for the acquisition, monitoring, control and supervision of consumption data provided by smart meters, allowing the incorporation of consumer actions on their electrical energy management. An energy management system with integration of smart meters for energy consumers in a smart grid is developed.

Artificial Intelligence Enabled Demand Response: Prospects and Challenges in Smart Grid Environment

“…There are a number of publications in the literature that attempt to predict demand, some of which account for potential changes in demand brought about by DR. Most of the studies [77], [78], [79], [80], [81], [82], [83], [84], [85], [86] focus on estimating demand for the next day or two, while others [87] look forward a week. Also, load forecasting has been done at many other aggregation levels, including for single-family homes [78], [88], [89], [90], commercial buildings [80], [83], [91] and individual appliances [92], [93] such as chillers, ice banks, and lights.…”

“…Most of the studies [77], [78], [79], [80], [81], [82], [83], [84], [85], [86] focus on estimating demand for the next day or two, while others [87] look forward a week. Also, load forecasting has been done at many other aggregation levels, including for single-family homes [78], [88], [89], [90], commercial buildings [80], [83], [91] and individual appliances [92], [93] such as chillers, ice banks, and lights. The load forecasting for single consumer or a group of consumers for day ahead prediction depends on previous load profile and weather conditions as presented in [92] using ANN-based method for home load forecasting.…”

“…A DR program's ability to recruit new members and keep current ones engaged depends in part on the quality of its reward system. When it comes to pricing mechanisms, the vast majority of papers utilize AI methods to determine the best interactive scheme a day in a meritocratic electricity market [66], [80], [107], [108], [138], [139], all while maximizing the profit of the service provider within the bounds of realistic market constraints and the discomfort of consumers for load reduction/shifting. Further, [164] use the numerical model relationship between real-time total cost and energy expenditure in a DR scenario for real-time pricing, and [110], [165] have constructed a model based on the cost elasticity matrix which is proposed for dynamic pricing.…”