Short-term wind speed prediction using an unscented Kalman filter based state-space support vector regression approach

Chen, Kuilin; Yu, Jie

doi:10.1016/j.apenergy.2013.08.025

Cited by 266 publications

(112 citation statements)

References 40 publications

Supporting

Mentioning

102

Contrasting

Order By: Relevance

“…It is evident that prediction performance degrades as sample size increases. Furthermore, the recent studies [16,17] lacked turbulence intensity estimations. The main advantage of the proposed methodology is that it can forecast wind speed and turbulence intensity simultaneously, which may have important implications for the performance and safety of wind turbines, especially during a storm.…”

Section: Discussionmentioning

confidence: 99%

Adaptive decision fusion based framework for short-term wind speed and turbulence intensity forecasting: case study for North West of Turkey

Dinçkal¹,

Töreyi̇n²,

Küçükali³

2017

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

Abstract:In this paper, an online learning framework called adaptive decision fusion (ADF) is employed for short-term wind speed and turbulence intensity forecasting by use of wind speed data for each season for the city ofİzmit, located in the northwest of Turkey. Fixed-weight (FW) linear combination is derived and used for comparison with ADF. Wind speeds and turbulence intensities are predicted from the existing wind speed data and computed turbulence intensities, respectively, using the ADF and FW methods. Simulations are carried out for each season and the results are tested on mean absolute percentage error criterion. It is shown that the proposed model captured the system dynamic behavior and made accurate predictions based on the seasonal wind speed characteristics of the site. The procedure described here can be used to estimate the local velocity and turbulence intensity in a wind power plant during a storm.

show abstract

Section: Discussionmentioning

confidence: 99%

Adaptive decision fusion based framework for short-term wind speed and turbulence intensity forecasting: case study for North West of Turkey

Dinçkal¹,

Töreyi̇n²,

Küçükali³

2017

Turk J Elec Eng & Comp Sci

View full text Add to dashboard Cite

show abstract

“…[25] for very short-term prediction (up to 4-6 hours). In addition, other authors [26] proposed Kalman integrated support vector machine (SVM) method to achieve a 10% accuracy improvement by comparing with artificial neural networks or autoregressive (AR) methods. Also a consistent approach is given by the use of ANNs for short-term generation forecast in case of wind turbines and photovoltaic (PV) panels.…”

Section: Consumption and Micro-generation Short-term Forecastingmentioning

confidence: 99%

Electricity Consumption and Generation Forecasting with Artificial Neural Networks

Bârã¹,

Oprea²

2018

Advanced Applications for Artificial Neural Networks

View full text Add to dashboard Cite

Nowadays, smart meters, sensors and advanced electricity tariff mechanisms such as timeof-use tariff (ToUT), critical peak pricing tariff and real time tariff enable the electricity consumption optimization for residential consumers. Therefore, consumers will play an active role by shifting their peak consumption and change dynamically their behavior by scheduling home appliances, invest in small generation or storage devices (such as small wind turbines, photovoltaic (PV) panels and electrical vehicles). Thus, the current load profile curves for household consumers will become obsolete and electricity suppliers will require dynamical load profiles calculation and new advanced methods for consumption forecast. In this chapter, we aim to present some developments of artificial neural networks for energy demand side management system that determines consumers' profiles and patterns, consumption forecasting and also small generation estimations.

show abstract

“…For instance, in the case of short-term prediction, stochastic methods (persistence, autoregressive models [12] and generalized equivalent Markov model [13]) are recommended. Furthermore, other research [14] has used the Kalman filter integrated with support vector regression (SVR) to obtain a 10% prediction improvement, comparing the obtained data with Artificial Neural Network (ANN) and autoregressive (AR).…”

Section: State Of the Artmentioning

confidence: 99%

A Two-step Forecasting Solution and Upscaling Technique for Small Size Wind Farms Located in Hilly Areas of Romania

Lungu¹,

Căruţaşu²,

Pîrjan³

et al. 2016

SIC

View full text Add to dashboard Cite

Short-term wind speed prediction using an unscented Kalman filter based state-space support vector regression approach

Cited by 266 publications

References 40 publications

Adaptive decision fusion based framework for short-term wind speed and turbulence intensity forecasting: case study for North West of Turkey

Adaptive decision fusion based framework for short-term wind speed and turbulence intensity forecasting: case study for North West of Turkey

Electricity Consumption and Generation Forecasting with Artificial Neural Networks

A Two-step Forecasting Solution and Upscaling Technique for Small Size Wind Farms Located in Hilly Areas of Romania

Contact Info

Product

Resources

About