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.
Highlights
There is a large literature related to short-term forecasting in the context of electric energy and this topic has a great interest in many other fields
We provide 24-h-ahead predictions for the electricity consumption of the Spanish town in order to apply them to the context of Demand Response
We describe the short-term PV power forecasting model able to offer 24-h-ahead predictions for the PV plant placed in the town under study in the context of Demand Response
Summary
There is a large literature related to short-term forecasting in the context of electric energy and this topic has a great interest in many other fields. The proposal of new forecasting methods is daily increasing because of their applicability to dispatch unit commitment or market operations [1]. In this sense, short-term load forecasting models have always been a key instrument for carrying out such operations, in recent years, with the increasing integration of power plants based on renewable energy with high variability (mainly wind and solar), forecasting models for these kinds of power plants has gained the attention of researchers and utilities. In the field of short-term load forecasting there are some examples of classical time-series approaches with auto-regressive integrated moving average (ARIMA), seasonal ARIMA (SARIMA) The search for more accurate and faster forecasting methods, both in load and in PV power generation, has resulted in a set of efficient techniques that can be divided into three different categories: time-series approaches, regression based, and artificial intelligence methods (see [2,3]).
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
