Wavelet Transform and Variants of SVR with Application in Wind Forecasting

Dhiman, Harsh S.; Anand, Pritam; Deb, Dipankar

doi:10.1007/978-981-13-1966-2_45

Cited by 22 publications

(16 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This advocates the high efficiency and appropriate search ability of the MDA. From the standard deviation point of view, the lower value of this index for the proposed method shows the high robustness of the optimization algorithm [54]. In order to make a clear picture of the convergence capability of the different algorithms, Figure 9 is provided here.…”

Section: Simulation Resultsmentioning

confidence: 99%

An Advanced Machine Learning Based Energy Management of Renewable Microgrids Considering Hybrid Electric Vehicles’ Charging Demand

et al. 2021

View full text Add to dashboard Cite

Renewable microgrids are new solutions for enhanced security, improved reliability and boosted power quality and operation in power systems. By deploying different sources of renewables such as solar panels and wind units, renewable microgrids can enhance reducing the greenhouse gasses and improve the efficiency. This paper proposes a machine learning based approach for energy management in renewable microgrids considering a reconfigurable structure based on remote switching of tie and sectionalizing. The suggested method considers the advanced support vector machine for modeling and estimating the charging demand of hybrid electric vehicles (HEVs). In order to mitigate the charging effects of HEVs on the system, two different scenarios are deployed; one coordinated and the other one intelligent charging. Due to the complex structure of the problem formulation, a new modified optimization method based on dragonfly is suggested. Moreover, a self-adaptive modification is suggested, which helps the solutions pick the modification method that best fits their situation. Simulation results on an IEEE microgrid test system show its appropriate and efficient quality in both scenarios. According to the prediction results for the total charging demand of the HEVs, the mean absolute percentage error is 0.978, which is very low. Moreover, the results show a 2.5% reduction in the total operation cost of the microgrid in the intelligent charging compared to the coordinated scheme.

show abstract

Section: Simulation Resultsmentioning

confidence: 99%

An Advanced Machine Learning Based Energy Management of Renewable Microgrids Considering Hybrid Electric Vehicles’ Charging Demand

et al. 2021

View full text Add to dashboard Cite

show abstract

“…For modelling, we used five different machine learning techniques-logistic regression (LR) [43,51], naive Bayes classifier (NB) [44], support vector machine (SVM) [45][46][47], random forest (RF) [48,54], and deep neural network (DNN) [49] to compare the results. The brief explanation of five machine learning techniques is provided in Appendix A.…”

Section: Modelling and Evaluationmentioning

confidence: 99%

“…3. Support vector machine (SVM) Support Vector approach use the simple idea to classify the data: construct a hyperplane to separate the two classes, so that the margin, which is defined as the distance between the hyperplane and the nearest point, is maximal [45][46][47]. Support vector regression (SVR) is similar to SVM in terms of theoretical background, but is employed for regression problems.…”

Section: Naive Bayes Classifier (Nb)mentioning

confidence: 99%

Predicting Patent Transactions Using Patent-Based Machine Learning Techniques

Kim

Geum

2020

IEEE Access

View full text Add to dashboard Cite

Technology transfer becomes imperative in recent business environment where technology changes rapidly and its complexity becomes sophisticated. Among various context of technology transfer, it is especially important to predict patent transactions in such fast-changing industries. Therefore, this study aims to suggest a predictive model for patent transaction considering a wide range of decision variables. For this purpose, this study highlighted two considerations-technological impact of technology donor and technological proximity in previous patent transactions. Six factors are employed for developing our predictive model-technological strength, knowledge accumulation, technological protection scope, technological jurisdiction, technological strength of companies, and previous history of patent transfers. Five machine learning techniques are employed. As a result, we find that technological strength of companies and previous transfer history significantly affect technology transfer. This study is expected to be used in practice where the technology buying decision is very complicated and comprehensive.

show abstract

“…Therefore, the signal to be analyzed is passed through several filters having different cutoff frequencies at different scales. Practically, the M th level DWT decomposition of a sampled signal This multiresolution analysis, illustrated in Figure 1 for three-level decomposition, may be expressed by:   (4) where, aM,n and dM,n are, respectively, the approximation and detail coefficients of the wavelet expansion. The functions m,n(t)=2 m/2 (2 m t-n) and m,n(t)=2 m/2 (2 m t-n), forming an orthogonal basis, are dilated and translated versions of the scaling and wavelet functions (t) and (t) respectively [26].…”

Section: Discrete Wavelet Decompositionmentioning

confidence: 99%

“…However, due to the irregular nature of wind energy production, its incorporation into the conventional electrical power system requires several technical and economic challenges [3][4][5]. To deal with the intermittency and randomness of wind energy conversion, forecasting techniques, over an extended period of time, are required [5].…”

Section: Introductionmentioning

confidence: 99%

Efficient Wind Speed Forecasting Using Discrete Wavelet Transform and Artificial Neural Networks

Berrezzek¹,

Khelil²,

Bouadjila³

2019

RIA

View full text Add to dashboard Cite

Electricity demand is globally increasing throughout the world, giving rise to many other renewable energy sources such as solar and wind energy. Therefore, to efficiently manage grid-connected wind power farms, precise wind forecast is very useful and necessary. This paper seeks to find out the most appropriate discrete wavelet transform (DWT), combined with artificial neural networks (ANN), for wind speed forecasting. Wavelet decomposition is applied to obtain a smoothed wind speed signal for more accurate prediction through neural networks. Wind speed data of three cities from the northern Africa region are employed, namely Annaba, Sidi Bouzid and Tetouan located in Algeria, Tunisia and Morocco respectively. The obtained simulation results show that the Daubechies wavelet db4 with 5level decomposition outperforms all other standard wavelets in terms of wind speed forecasting accuracy.

show abstract

Wavelet Transform and Variants of SVR with Application in Wind Forecasting

Cited by 22 publications

References 14 publications

An Advanced Machine Learning Based Energy Management of Renewable Microgrids Considering Hybrid Electric Vehicles’ Charging Demand

An Advanced Machine Learning Based Energy Management of Renewable Microgrids Considering Hybrid Electric Vehicles’ Charging Demand

Predicting Patent Transactions Using Patent-Based Machine Learning Techniques

Efficient Wind Speed Forecasting Using Discrete Wavelet Transform and Artificial Neural Networks

Contact Info

Product

Resources

About