A Hybrid Nonlinear Combination System for Monthly Wind Speed Forecasting

Paulo S G De Mattos Neto,Hugo Valadares Siqueira,Joao Fausto Lorenzato De Oliveira,Domingos Savio De Oliveira Santos Junior,Manoel Henrique Da Nobrega Marinho,Francisco Madeiro

doi:10.1109/access.2020.3032070

Abstract

Wind speed is one of the primary renewable sources for clean power. However, it is intermittent, presents nonlinear patterns, and has nonstationary behavior. Thus, the development of accurate approaches for its forecasting is a challenge in wind power generation engineering. Hybrid systems that combine linear statistical and Artificial Intelligence (AI) forecasters have been highlighted in the literature due to their accuracy. Those systems aim to overcome the limitations of the single linear and AI models. In the literature about wind speed, these hybrid systems combine linear and nonlinear forecasts using a simple sum. However, the most suitable function for combining linear and nonlinear forecasts is unknown and the linear relationship assumption can degenerate or underestimate the performance of the whole system. Thus, properly combining the forecasts of linear and nonlinear models is an open question and its determination is a challenge. This article proposes a hybrid system for monthly wind speed forecasting that uses a nonlinear combination of the linear and nonlinear models. A data-driven intelligent model is used to search for the most suitable combination, aiming to maximize the performance of the system. An evaluation has been carried out using the monthly data from three wind speed stations in northeast Brazil, evaluated with two traditional metrics. The assessment is performed for two scenarios: with and without exogenous variables. The results show that the proposed hybrid system attains an accuracy superior to other hybrid systems and single linear and AI models.

Highlights

I N the last decades, there has been much research on power systems in order to develop energy systems that work using clean and renewable sources [1]
Taking into consideration higher error metrics and the correlation analysis in Table 1, the results suggest that the set of exogenous variables under consideration present the smallest significance for wind speed forecasting for Natal city
Wind power generation has become an important research field due to the appeal for the development of new technologies to generate electric energy based on renewable sources

Summary

Introduction

I N the last decades, there has been much research on power systems in order to develop energy systems that work using clean and renewable sources [1]. Governments and societies have seen the harm of using fossil fuels due to their economic cost and environmental impact [2], [3]. For this reason, wind power has gained much attention. It is clean and inexhaustible, in clear contrast to fossil fuels. According to the Global Wind Energy Council, the cumulative installed wind capacity was around 651 GW in 2019. The last year was outstanding, because new wind power installations increased by 60.4 GW (10.1%) globally over 2018. China and the United States (US) led this growth and are the most significant onshore markets, followed by Europe [5]

Methods

Findings

Discussion

Conclusion