A review of wind speed and wind power forecasting with deep neural networks

A combined forecasting system based on statistical method, artificial neural networks, and deep learning methods for short-term wind speed forecasting

This article re-examines the finance-growth nexus in China using principal components analysis and ARDL bounds testing approach to cointegration. The results suggest that principal components have an effective role in examining the links between growth and financial development and, that financial development fosters economic growth.

Finance-growth nexus in China revisited: New evidence from principal components and ARDL bounds tests

De Vita and Trachanas's (hereafter DV-T, 2016) paper published in (Energy Economics, Volume 56, May 2016, pages, 150-160) criticizes Bal and Rath's paper (Energy Economics, Volume 51, September 2015, pages, 149-156) (hereafter, BR, 2015) by undertaking a â€˜pure replication' and a â€˜reanalysis' using (BR, 2015) data set. The aim of this paper is to reassess (BR, 2015) by providing comments and additional evidence. We revisit (BR, 2015) with the aim of applying additional unit root, cointegration and nonlinear causality tests. The results derived from these supplementary tests clearly reveal that the oil price series is non-stationary at level. The bivariate noisy Mackey-Glass model proposed by Kyrtsou and Terraza (2003) reveals bi-directional non-linear causality exists between real oil price and exchange rate in case of China, whereas for India, only unidirectional nonlinear causality running from oil price to exchange rate.

Nonlinear causality between crude oil price and exchange rate: A comparative study of China and India - A Reassessment

Wind energy has attracted considerable attention in the past decades as a low-carbon, environmentally friendly, and efficient renewable energy. However, the irregularity of wind speed makes it difficult to integrate wind energy into smart grids. Thus, achieving credible and effective wind speed forecasting results is crucial for the operation and management of wind energy. In this study, we propose an ensemble forecasting system that integrates data decomposition technology, sub-model selection, a novel multi-objective version of the Mayfly algorithm, and different predictors to better demonstrate the stochasticity and fluctuation of wind speed data. After decomposition using the data decomposition technology, each decomposed wind speed series is considered as the input to multiple predictors, from which the optimal forecasting model for each sub-series is determined based on sub-model selection. To obtain reliable forecasting results, a novel multi-objective version of the Mayfly algorithm is proposed to estimate the optimal weight coefficients for integrating the forecasting values of the sub-series. Based on three experiments and four analyses, the proposed ensemble system is verified as effective for obtaining accurate and stable point forecasting and interval forecasting performances, thus aiding in the planning and dispatching of power grids.

Ensemble forecasting system for short-term wind speed forecasting based on optimal sub-model selection and multi-objective version of mayfly optimization algorithm

Lifang Zhang

Papers

A combined forecasting model for time series: Application to short-term wind speed forecasting

A combined forecasting system based on statistical method, artificial neural networks, and deep learning methods for short-term wind speed forecasting

Hybrid system based on a multi-objective optimization and kernel approximation for multi-scale wind speed forecasting

Effects of PM2.5 on health and economic loss: Evidence from Beijing-Tianjin-Hebei region of China

Carbon price forecasting system based on error correction and divide-conquer strategies