Short-Term Power Forecasting Framework for Microgrids Using Combined Baseline and Regression Models

Antonio Parejo,Federico Delfino,Stefano Bracco,Carlos León,Diego Francisco Larios,Enrique Personal

doi:10.3390/app11146420

Antonio Parejo, Federico Delfino + Show 4 more

Open Access

https://doi.org/10.3390/app11146420

Copy DOI

Abstract

Short-term electric power forecasting is a tool of great interest for power systems, where the presence of renewable and distributed generation sources is constantly growing. Specifically, this type of forecasting is essential for energy management systems in buildings, industries and microgrids for optimizing the operation of their distributed energy resources under different criteria based on their expected daily energy balance (the consumption–generation relationship). Under this situation, this paper proposes a complete framework for the short-term multistep forecasting of electric power consumption and generation in smart grids and microgrids. One advantage of the proposed framework is its capability of evaluating numerous combinations of inputs, making it possible to identify the best technique and the best set of inputs in each case. Therefore, even in cases with insufficient input information, the framework can always provide good forecasting results. Particularly, in this paper, the developed framework is used to compare a whole set of rule-based and machine learning techniques (artificial neural networks and random forests) to perform day-ahead forecasting. Moreover, the paper presents and a new approach consisting of the use of baseline models as inputs for machine learning models, and compares it with others. Our results show that this approach can significantly improve upon the compared techniques, achieving an accuracy improvement of up to 62% over that of a persistence model, which is the best of the compared algorithms across all application cases. These results are obtained from the application of the proposed methodology to forecasting five different load and generation power variables for the Savona Campus at the University of Genova in Italy.

Highlights

During the last few years, the presence of renewable energy generation has increased significantly within power systems [1]
For both types of aggregations, the weather data were directly used as inputs for the models in a row of 48 points for each weather variable, with no averaging being applied to these numbers
It must be remembered that the best forecast corresponds to the lowest absolute values

Summary

Introduction

During the last few years, the presence of renewable energy generation has increased significantly within power systems [1]. The increasing presence of renewables marks a large change from a traditional centralized generation system to a distributed system This trend is based on the distributed generation (DG) paradigm [2]. In the DG paradigm, active sources are connected directly to the distribution network, permitting them to be nearer to consumption points [8] These elements are usually called distributed energy resources (DERs). The DER concept is associated with generation systems [9] and with the coverage of storage [10,11] and even controllable loads [12,13] In this sense, electric vehicles (EVs) can be considered DERs, adding to the difficulty of being a mobile load [14,15,16]. All these DERs have been coordinated by energy management systems (EMSs)

Objectives

Results

Discussion

Conclusion