A Short-Term Distributed Load Forecasting Algorithm Based on Spark and IPPSO_LSSVM

Bao Yi Wang; Dong Yang Wang; Shao Min Zhang

doi:10.4028/www.scientific.net/AMM.713-715.1385

Paper Titles

A Distribution Network Fault Location Method Based on Reverse Wave and Wavelet Analysis
p.1369

High Precision GPS Clock Synchronization Method Based on Time Different Compensation
p.1373

Research of Modeling Method of Transmission Line Information Based on IEC61850
p.1377

Application and Development of MCGS Configuration Software in Wind/Solar Hybrid System
p.1381

A Short-Term Distributed Load Forecasting Algorithm Based on Spark and IPPSO_LSSVM
p.1385

A Backoff Algorithm for LOWPAN Based on the Dynamically Backoff Exponent
p.1389

3-Dimensional Localization Algorithm Research Based on Weighted Fusion with Projected Coordinate
p.1394

Harmonic Analyzing and Filtering of Motor Discrete Variable Frequency Soft Starter
p.1401

A Simulation Study of Nakagami-m Distribution
p.1405

HomeApplied Mechanics and MaterialsApplied Mechanics and Materials Vols. 713-715A Short-Term Distributed Load Forecasting...

A Short-Term Distributed Load Forecasting Algorithm Based on Spark and IPPSO_LSSVM

Abstract:

To improve the accuracy of load forecasting and cope with the challenge of single computer’s insufficient computing resource, a short-term distributed load forecasting model based on LSSVM optimized by IPPSO is proposed. Uncertain parameters are optimized by improved parallel particle swarm algorithm which runs on the Spark on Yarn memory computing platform. The real load data provided by EUNITE is used, and experiments and analysis are conducted on an 8-node cloud computing platform. The results show that the accuracy of the algorithm proposed by our paper is better than the traditional functional networks algorithm, the efficiency of the algorithm is better than MR-OSELM-WA, and the algorithm has good ability of parallelization.

You might also be interested in these eBooks

View Preview

Info:

Periodical:

Applied Mechanics and Materials (Volumes 713-715)

Pages:

1385-1388

DOI:

https://doi.org/10.4028/www.scientific.net/AMM.713-715.1385

Citation:

Cite this paper

Online since:

January 2015

Authors:

Bao Yi Wang*, Dong Yang Wang, Shao Min Zhang

Keywords:

IPPSO, Load Forecasting, LSSVM, Spark

Export:

RIS, BibTeX

Price:

Permissions CCC:

Request Permissions

Permissions PLS:

Request Permissions

Сopyright:

Citation:

* - Corresponding Author

References

[1] Wan Kun, Liu Ruiyu. Application of Interval Time-Series Vector Autoregressive Model in Short-Term Load Forecasting[J]. Power System Technology, 2012, 36(11): 77-81.

Google Scholar

[2] Zhou Huaxin. Research on Medium and Long Term Power Load Forecasting Based on PSOEM-LSSVM and Its Application[D]. Chongqing: College of Automation of Chongqing University, (2013).

Google Scholar

[3] Cheng Xingguo. Research on Dynamic Feedback Mechanism for the Bionical Algorithms and Parallel Implementation[D]. Guangzhou: South China University of Technology, (2013).

Google Scholar

[4] Dai Xinbo, Cui Yong, Zhou Dexiang, etc. LS-SVM Short-term Load Forecasting Based on and Improved Particle Swarm Principal Component Analysis Optimization[J]. Electrical Measurement & Instrumentation, 2012, 49(558): 5-9.

Google Scholar

[5] Wang Gang, Jiang Jie, Tang Kunming, etc. Ultra-short-term load forecasting based on adaptive bidirectional weighted least squares support vector machines[J]. Power System Protection and Control, 2010, 38(19): 142-146.

Google Scholar

[6] Castillo E, Guijarro B, Alonso A. Electricity load forecast using functional networks[R]. Report for EUNITE 2001 Competition, (2001).

Google Scholar

[7] Wang Baoyi, Zhao Shuo, Zhang Shaomin. A Distributed Load Forecasting Algorithm Based on Cloud Computing and Extreme Learning Machine[J]. Power System Technology, 2014, 38(2): 526-531.

Google Scholar