Abstract
Accurate wind speed forecasting plays a significant role for grid operators and the use of wind energy, which helps meet increasing energy needs and improve the energy structure. However, choosing an accurate forecasting system is a challenging task. Many studies have been carried out in recent years, but unfortunately, these studies ignore the importance of data preprocessing and the influence of numerous missing values, leading to poor forecasting performance. In this paper, a hybrid forecasting system based on data preprocessing and an Extreme Learning Machine optimized by the cuckoo algorithm is proposed, which can overcome the limitations of the single ELM model. In the system, the standard genetic algorithm is added to reduce the dimensions of the input and utilize the time series model for error correction by focusing on the optimized extreme learning machine model. And according to screened results, the 5% fractile and 95% fractile are applied to compose the upper and lower bounds of the confidence interval, respectively. The assessment results indicate that the hybrid system successfully overcomes some limitations of the single Extreme Learning Machine model and traditional BP and Mycielski models and can be an effective tool compared to traditional forecasting models.
Highlights
At present, the increasing energy demand, security of the energy supply and reduction of emissions are the most difficult challenges that need to be address urgently for the whole world [1].Energy consumption, which accounts for 60% of global greenhouse gas emissions, has already contributed to climate change [2]
BP neural net, Mycielski and non-optimized extreme learning machine (ELM) are used as contrast models to analyze the predictable performance of the ELM model optimized by the Cuckoo algorithm proposed in the previous section
When building the SGA-CSELM model, we set the number of hidden layer nodes at the Apply GAOT toolbox to build SGA, and the specific parameters are set as follows: the number of iterations is 100, the species number is 20, the crossover probability is 0.09, and the mutation probability is 0.05
Summary
Landberg [10] studied the performance of different models for wind speed forecasting, including the NWP and an artificial neural network (ANN), and so on. Integrated Moving Average, fractional ARIMA, exponential smoothing and grey prediction They are built based on the relationship between each variable by mathematical statistics to describe the potential correlations from history data sampling for wind speed forecasting [12]. A wind speed forecasting method based on improved empirical mode decomposition (EMD) and GA-BP neural network is proposed by Wang et al [28]. The evaluation system contains the performance of the whole research process including data preprocessing, optimized algorithm and empirical forecasting results. Attempting to overcome the low forecasting accuracy of the single ELM method, this article proposes a prediction model that optimizes the initial weight of ELM by using Cuckoo Search.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
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
