Renewable Power Output Forecasting Using Least-Squares Support Vector Regression and Google Data

Abstract

Sustainable and green technologies include renewable energy sources such as solar power, wind power, and hydroelectric power. Renewable power output forecasting is an essential contributor to energy technology and strategy analysis. This study attempts to develop a novel least-squares support vector regression with a Google (LSSVR-G) model to accurately forecast power output with renewable power, thermal power, and nuclear power outputs in Taiwan. This study integrates a Google application programming interface (API), least-squares support vector regression (LSSVR), and a genetic algorithm (GA) to develop a novel LSSVR-G model for accurately forecasting power output from various power outputs in Taiwan. Material price and the search volume via Google's search engine for keywords, which is used for various power outputs and is collected by Google APIs, are used as input data. The forecasting model uses LSSVR. Furthermore, the LSSVR employs a GA to find the optimal parameters for the LSSVR. Real-world annual power output datasets collected from Taiwan were used to demonstrate the forecasting performance of the model. The empirical results reveal that the proposed LSSVR-G model is superior to all other considered models both in terms of accuracy and stability, and, thus, can be a useful tool for renewable power forecasting. Moreover, the accuracy forecasting thermal power and nuclear power could effectively assist in understanding the future trend of renewable power output in Taiwan. The accurately forecasting result could effectively provide basic information for renewable power, thermal power, and nuclear power planning and policy making in Taiwan.

Hybrid and Ensemble Methods of Two Days Ahead Forecasts of Electric Energy Production in a Small Wind Turbine

“…Recent papers addressing wind power forecasts could be broadly classified into 5 categories: papers focused on how to increase NWP accuracy [4][5][6][7][8], good-practice prediction guidelines [9][10][11], comparisons of accuracy across prediction models [12][13][14][15], hybrid and ensemble methods [16][17][18][19][20][21][22][23][24][25][26][27], and conventional methods improved by, among other things, preprocessing [28][29][30][31][32][33][34][35]. At this point, clear distinction should be made between hybrid, ensemble and improved models.…”

“…Hybridization [16][17][18][19][20][21] and parallelization [22][23][24][25][26][27] of prediction models use datarefining and error compensation, respectively, as an approach to maximize prediction accuracy. The most common bases for hybrid models in recent literature are ANNs [17][18][19]21] due to their generalization ability, while the most common hybrid add ons would be single optimization methods [16,18,20,21]. With varying implementation, error reduction can be achieved in different ways.…”

“…This hybrid combination of PSO and MLP has been implemented in an original computer program by one of the authors. The following tuning hyperparameters were investigated in our research: number of neurons in hidden layers (5,8,10,20), number of particles in the swarm (20, 50, 100, 150), number of algorithm iterations (100, 1000), coefficients in the formula for particles movements (0.7, 1.0, 1.4), number of iterations between subsequent disturbances in the swarm (50, 100, 400), neighborhood width (2,5,10). The optimization concept is presented in Figures 7 and 8.…”

A Forecasting Model for Economic Growth and CO2 Emission Based on Industry 4.0 Political Policy under the Government Power: Adapting a Second-Order Autoregressive-SEM

“…Hyndman and Fan [20] forecasted the density of long-term peak electricity demand by proposing a new and systematic methodology, and the model outperforms others, as shown by the results of the study. In other research, Chen et al [29] developed a novel least-squares support vector regression with a Google (LSSVR-G) model to predict the power output from various sources in Taiwan, including renewable power, thermal power and nuclear power. The discussion of this study indicated that the proposed LSSVR-G model performs better than any previously studied models with respect to accuracy and stability.…”

Multi-Power Joint Peak-Shaving Optimization for Power System Considering Coordinated Dispatching of Nuclear Power and Wind Power

“…Large-scale, random, intermittent wind power and large-capacity nuclear power plants are connected to the power grid, which puts higher requirements on the climbing rate of units such as thermal power [9,10]. With the continuous increase of peak-valley difference of load in coastal areas and the construction and development of wind and nuclear power units, the pressure of peak shaving in coastal areas will be seriously aggravated and the demand for wind and nuclear power to participate in daily peak shaving is becoming stronger [11][12][13].…”