Yang, W, Wang, J, Lu, H, Niu, T & Du, P 2019, 'Hybrid wind energy forecasting and analysis system based on divide and conquer scheme: A case study in China', Journal of Cleaner Production, vol. 222, pp. 942-959.View/Download from: UTS OPUS or Publisher's site
© 2019 Elsevier Ltd Wind energy, acknowledged as a promising form of renewable energy and the fastest-growing clean method for electricity generation, has attracted considerable attention from many scientists and researchers in recent decades. However, wind energy forecasting is still a challenging task owing to its inherent features of non-linearity and randomness. Therefore, this study develops a hybrid wind energy forecasting and analysis system including a deterministic forecasting module and an uncertainty analysis module to mitigate the challenges in existing studies. In particular, these challenges are as follows: (1) It is difficult to guarantee that the data characteristics underlying the time series are effectively extracted; (2) in the modeling of each subseries, i.e., when the original data is decomposed into some time series, forecasting accuracy and stability are not simultaneously considered, and thus, they are not properly modeled; and (3) the best function to perform a deterministic forecasting and uncertainty analysis based on the forecaster of each subseries is unknown. The developed hybrid system consists of three steps: First, data preprocessing is conducted to capture and mine the main feature of the wind energy time series and weaken the noises' negative effects; second, multi-objective optimization is proposed to achieve the forecasting of each subseries with improvements in accuracy and stability; finally, search for the best function, which obtains the deterministic forecasting and uncertainty analysis results using an optimized extreme learning machine based on different modeling objectives, is conducted. Experimental simulations are performed using data from three sites in a real wind farm, which indicate that the developed system has a better performance in engineering applications than that of other methods. Furthermore, this system could not only be used as an effective tool for wind energy deterministic forecasting and uncertainty ...
Niu, T, Wang, J, Lu, H & Du, P 2018, 'Uncertainty modeling for chaotic time series based on optimal multi-input multi-output architecture: Application to offshore wind speed', Energy Conversion and Management, vol. 156, pp. 597-617.View/Download from: UTS OPUS or Publisher's site
© 2017 Elsevier Ltd Wind energy is attracting more attention with the growing demand for energy. However, the efficient development and utilization of wind energy are restricted due to the intermittency and randomness of wind speed. Although abundant investigations concerning wind speed forecasting have been conducted by numerous researchers, most of the studies merely attach importance to point forecasts, which cannot quantitatively characterize the uncertainties as developing intervals. In this study, a novel interval prediction architecture has been designed, aiming at constructing effective prediction intervals for a wind speed series, composed of a preprocessing module, a feature selection module, an optimization module, a forecast module and an evaluation module. The feature selection module, in cooperation with the preprocessing module, is developed to determine the optimal model input. Furthermore, the forecast module optimized by the optimization module is considered a predictor for giving prediction intervals. The experimental results shed light on the architecture that not only outperforms the benchmark models considered, but also has great potential for application to wind power systems.
Niu, T, Wang, J, Zhang, K & Du, P 2018, 'Multi-step-ahead wind speed forecasting based on optimal feature selection and a modified bat algorithm with the cognition strategy', RENEWABLE ENERGY, vol. 118, pp. 213-229.View/Download from: UTS OPUS or Publisher's site
Wang, J, Du, P, Lu, H, Yang, W & Niu, T 2018, 'An improved grey model optimized by multi-objective ant lion optimization algorithm for annual electricity consumption forecasting', Applied Soft Computing Journal, vol. 72, pp. 321-337.View/Download from: UTS OPUS or Publisher's site
© 2018 Elsevier B.V. Accurate and stable annual electricity consumption forecasting play vital role in modern social and economic development through providing effective planning and guaranteeing a reliable supply of sustainable electricity. However, establishing a robust method to improve prediction accuracy and stability simultaneously of electricity consumption forecasting has been proven to be a highly challenging task. Most previous researches only pay more attention to enhance prediction accuracy, which usually ignore the significant of forecasting stability, despite its importance to the effectiveness of forecasting models. Considering the characteristics of annual power consumption data as well as one criterion i.e. accuracy or stability is insufficient, in this study a novel hybrid forecasting model based on an improved grey forecasting mode optimized by multi-objective ant lion optimization algorithm is successfully developed, which can not only be utilized to dynamic choose the best input training sets, but also obtain satisfactory forecasting results with high accuracy and strong ability. Case studies of annual power consumption datasets from several regions in China are utilized as illustrative examples to estimate the effectiveness and efficiency of the proposed hybrid forecasting model. Finally, experimental results indicated that the proposed forecasting model is superior to the comparison models.
Wang, J, Niu, T, Lu, H, Guo, Z, Yang, W & Du, P 2018, 'An analysis-forecast system for uncertainty modeling of wind speed: A case study of large-scale wind farms', Applied Energy, vol. 211, pp. 492-512.View/Download from: UTS OPUS or Publisher's site
© 2017 Elsevier Ltd The uncertainty analysis and modeling of wind speed, which has an essential influence on wind power systems, is consistently considered a challenging task. However, most investigations thus far were focused mainly on point forecasts, which in reality cannot facilitate quantitative characterization of the endogenous uncertainty involved. An analysis-forecast system that includes an analysis module and a forecast module and can provide appropriate scenarios for the dispatching and scheduling of a power system is devised in this study; this system superior to those presented in previous studies. In order to qualitatively and quantitatively investigate the uncertainty of wind speed, recurrence analysis techniques are effectively developed for application in the analysis module. Furthermore, in order to quantify the uncertainty accurately, a novel architecture aimed at uncertainty mining is devised for the forecast module, where a non-parametric model optimized by an improved multi-objective water cycle algorithm is considered a predictor for producing intervals for each mode component after feature selection. The results of extensive in-depth experiments show that the devised system is not only superior to the considered benchmark models, but also has good potential practical applications in wind power systems.