Utilizing Device-level Demand Forecasting for Flexibility Markets

Abstract

e uncertainty in the power supply due to uctuating Renewable Energy Sources (RES) has severe ( nancial and other) implications for energy market players. In this paper, we present a device-level Demand Response (DR) scheme that captures the atomic (all available) exibilities in energy demand and provides the largest possible solution space to generate demand/supply schedules that minimize market imbalances. We evaluate the e ectiveness and feasibility of widely used forecasting models for device-level exibility analysis. In a typical device-level exibility forecast, a market player is more concerned with the utility that the demand exibility brings to the market, rather than the intrinsic forecast accuracy. In this regard, we provide comprehensive predictive modeling and scheduling of demand exibility from household appliances to demonstrate the ( nancial and otherwise) viability of introducing exibility-based DR in the Danish/Nordic market. Further, we investigate the correlation between the potential utility and the accuracy of the demand forecast model. Furthermore, we perform a number of experiments to determine the data granularity that provides the best nancial reward to market players for adopting the proposed DR scheme. A cost-bene t analysis of forecast results shows that even with somewhat low forecast accuracy, market players can achieve regulation cost savings of 54% of the theoretically optimal.

Modeling and Managing Energy Flexibility Using FlexOffers

“…Nevertheless, even with a very low traditional accuracy measure, the proposed FO generation model can still give a good utility, i.e., positive financial benefits to a market. Hence, the achieved accuracy is sufficient to increase market confidence in utilizing FOs for balancing the deviations in the portfolio [10], [11].…”

“…The regularity in energy consumption pattern for EVs resulted in higher accuracy for extracted flexibilities. On the other hand, uncertainty in usage pattern for wet-devices lowers the accuracy, which has been investigated in [10]. Nevertheless, even with a very low traditional accuracy measure, the proposed FO generation model can still give a good utility, i.e., positive financial benefits to a market.…”

Flexibility Modeling, Management, and Trading in Bottom-up Cellular Energy Systems

“…(2) Predictive model building and demand prognosis: An FO is essentially an estimation of a load's future behavior and its flexibility, which requires forecasting of the future energy demand and the associated flexibility. Thus, we need to develop models to analyze user behavior and predict future energy demand [13,26]. The predicted energy demand and the associated flexibility data is used to generate FOs [27].…”

Prescriptive analytics: a survey of emerging trends and technologies

“…As a result, the different tools required for PSA have to be inter-connected manually in an ad-hoc fashion, resulting in less structured and more time-consuming and error-prone specifications of PSA workflows. Furthermore, if new algorithms or specialized models (e.g., energy flexibility models [79,78]) need to be used in the application, the closed structure of the architectures might completely prevent this, or lead to the ad-hoc integration of new tools, e.g., by the connection of external programs, to which the data has to be transferred via an API. -Third, the analytics computations are still performed on a single node machine, and often far away from where the data is stored.…”