Implementing smart energy systems: Integrating load and price forecasting for single parameter based demand response

This paper frames itself in the smart energy context where the power flow is controlled by price signals and elasticity models. In such a market, electricity prices dynamically vary and electricity consumers ought to respond with their electricity energy demand at specified time intervals. Initially load, and lately, price forecasting have been identified as essential technologies for market participants to design optimal demand response strategies. Thus, there are ongoing efforts in industry and academia to develop new methodologies that combine load and price forecasting tools. In this paper a methodology is presented for demand response in the smart energy context. The methodology couples price and load forecasting via an optimization based framework to enable automated demand response by smart grid participants. In particular, the methodology utilizes price forecasts to modify the initial forecasted load demand aiming at minimizing consumer's expenses. The proposed methodology minimizes human intervention in demand response by requiring only a single value to be entered by the consumer. We have evaluated the performance of the proposed single parameter demand response on a set of real world historical data taken from the New England area. Reported results promise a potential reduction of the consumption cost in all examined cases, while demonstrating validating the minimal human intervention in response decisions.