Integration of Demand Response and Short-Term Forecasting for the Management of Prosumers’ Demand and Generation

Abstract

The development of Short-Term Forecasting Techniques has a great importance for power system scheduling and managing. Therefore, many recent research papers have dealt with the proposal of new forecasting models searching for higher efficiency and accuracy. Several kinds of artificial intelligence (AI) techniques have provided good performance at predicting and their efficiency mainly depends on the characteristics of the time series data under study. Load forecasting has been widely studied in recent decades and models providing mean absolute percentage errors (MAPEs) below 5% have been proposed. On the other hand, short-term generation forecasting models for photovoltaic plants have been more recently developed and the MAPEs are in general still far from those achieved from load forecasting models. The aim of this paper is to propose a methodology that could help power systems or aggregators to make up for the lack of accuracy of the current forecasting methods when predicting renewable energy generation. The proposed methodology is carried out in three consecutive steps: (1) short-term forecasting of energy consumption and renewable generation; (2) classification of daily pattern for the renewable generation data using Dynamic Time Warping; (3) application of Demand Response strategies using Physically Based Load Models. Real data from a small town in Spain were used to illustrate the performance and efficiency of the proposed procedure.

A Metaheuristic Algorithm for Flexible Energy Storage Management in Residential Electricity Distribution Grids

“…The uncertainty of renewable generation patterns is also a factor requiring attention. In [10], this issue is studied by comparing the efficiency of several short-term forecasting methods. Based on such data, the prosumer-network interaction is modelled in [11] as a profit model of DNO concurrent with a utility model of the PV prosumers, where the operator wants to maximize its profit and the prosumers adjust their energy consumption and sharing according to the feed-in time-varying prices.…”

“…Another approach, developed in [14], considers the possibility of optimally managing prosumers that are acting independently, only in their self-interest, to maintain the voltage stability in the network within acceptable limits. The uncertainty of PV generation is managed in [10] by using a combination of load profiling and demand response techniques, and in [15] by creating energy hubs of prosumer communities. Prosumer management is more challenging for the network operator in islanded networks, a problem that is approached in [16].…”

“…It follows that, if the prosumer management is formulated as an optimization problem, the computational-intensive classical algorithms could be successfully replaced with other methods, with marginal performance decrease. The literature survey from above lists several methods used for prosumer management problems: game theory [11,14,19,20], clustering [13], neural networks, random forest [10], mixed integer linear optimization [15,22,31], genetic algorithm [23], linear programming [21], alternating direction method of multipliers [18,30], dynamic programming [24], optimal power flow [26], proof-of-stake blockchain trading algorithm [29].…”

Interpretable Modeling for Short- and Medium-Term Electricity Demand Forecasting

“…From a suppliers' point of view, it is crucial to produce an interpretable model to investigate the impact of weather on the demand. For example, estimating the fluctuations of electric power caused by weather would help develop strategies for energy-saving interventions [e.g., (Guo et al, 2018a;Wang et al, 2018)] and demand response [e.g., (Ruiz-Abellón et al, 2020)]. To produce an interpretable model, one can directly add weather forecast information to the exploratory variables in the regression model (Hong et al, 2010) and investigate the estimator of regression coefficients.…”

Interpretable modeling for short- and medium-term electricity load forecasting

“…From a suppliers' point of view, it is crucial to produce an interpretable model to investigate the impact of weather on the loads. For example, estimating the fluctuations of electric power caused by weather would help develop strategies for energy-saving interventions (e.g., Guo et al, 2018a;Wang et al, 2018) and demand response (e.g., Ruiz-Abellón et al, 2020). To produce an interpretable model, one can directly add weather forecast information to the exploratory variables in the regression model (Hong et al, 2010) and investigate the estimator of regression coefficients.…”