Artificial Combined Model Based on Hybrid Nonlinear Neural Network Models and Statistics Linear Models—Research and Application for Wind Speed Forecasting

Yuewei Liu,Jianzhou Wang,Shenghui Zhang,Xuejun Chen

doi:10.3390/su10124601

Abstract

The use of wind power is rapidly increasing as an important part of power systems, but because of the intermittent and random nature of wind speed, system operators and researchers urgently need to find more reliable methods to forecast wind speed. Through research, it is found that the time series of wind speed demonstrate not only linear features but also nonlinear features. Hence, a combined forecasting model based on an improved cuckoo search algorithm optimizes weight, and several single models—linear model, hybrid nonlinear neural network, and fuzzy forecasting model—are developed in this paper to provide more trend change for time series of wind speed forecasting besides improving the forecasting accuracy. Furthermore, the effectiveness of the proposed model is proved by wind speed data from four wind farm sites and the results are more reliable and accurate than comparison models.

Highlights

In the past few decades, due to policy-driven environmental and energy security issues, the development of renewable energy sources (RESs), which play an indispensable role in the global power sector, has received much attention, and these energy sources play an indispensable role in the global power sector [1].Wind energy is a very rich resource on the earth, according to a report of the World Meteorological Organization (WMO)
The output weights are calculated through an inverse operation on the hidden layer output matrix, which is randomly determined according to Equation (10)
Accurate and reliable forecasting results have a significant impact on wind farms, which in turn have an influence on the economy

Summary

Introduction

In the past few decades, due to policy-driven environmental and energy security issues, the development of renewable energy sources (RESs), which play an indispensable role in the global power sector, has received much attention, and these energy sources play an indispensable role in the global power sector [1].Wind energy is a very rich resource on the earth, according to a report of the World Meteorological Organization (WMO). Global wind energy reserves total about 2.74 × 109 MW, which amounts to wind energy development and utilization of approximately 2 × 107 MW, greater than hydrogen energy, and can be developed and utilized all around the world. It is estimated that the amount of wind energy is 10 times larger than hydrogen energy, and Earth’s daily wind power is equivalent to the current world energy consumption. Forecasting short-term wind speed is key to improving the reliability of wind power generation systems and integrating wind energy into the power grid [3,4,5,6,7]. In order to reduce the operational cost of a wind farm, it is very important to improve short-term wind speed forecasting accuracy

Methods

Results

Conclusion