Evaluation Method for Microgrid Cluster State Based on Fuzzy Least Squares Support Vector Machine

被引：0
|
作者：
Chen W. [1 ]
Liang S. [1 ]
Xiao Y. [1 ]
Guo M. [1 ]
机构：
[1] Electric Power Research Institute of Guangxi Power Grid Company Limited, Nanning
来源：
Dianli Xitong Zidonghua/Automation of Electric Power Systems | 2019年 / 43卷 / 02期
关键词：
Least squares support vector machine; Microgrid cluster; Operation state evaluation; Real-time evaluation;
D O I：
10.7500/AEPS20180311001
中图分类号：
学科分类号：
摘要：
Aiming at energy management system (EMS) and coordination control system (CCS) for adapting to flexible adjustment of microgrid cluster control strategy at variable operation states, a real-time operation state evaluation model of low-voltage microgrid cluster based on fuzzy least squares support vector machine (FLS-SVM) is proposed. With traditional power system operation state description method, the proposed model builds constraints in secure and normal operation of microgrid cluster and microgrid. Microgrid states are classified in view of multi-dimensional eigenvector including voltage deviation rate, energy storage state of charge, energy storage charge and discharge time, power generation and load. The real-time operation states of microgrids are evaluated with FLS-SVM, and then the operation states of microgrid cluster can be determined. Case study shows that the method can conduct the real-time evaluation within the sampling period of the system, and classify the operation states of microgrids accurately and effectively under the conditions of both off-grid and on-grid. It can provide the basis for microgrid cluster to quickly determine the operation state and flexibly adjust control strategy. © 2019 Automation of Electric Power Systems Press.
引用
收藏
页码：76 / 82
页数：6
相关论文
共 20 条
  • [1] Lasseter R., Akhil A., Marnay C., Integration of distributed energy resources: the CERTS microgrid concept
  • [2] Zhao M., Chen Y., Shen C., Et al., Characteristic analysis of multi-microgrids and a pilot project design, Power System Technology, 39, 6, pp. 1469-1476, (2015)
  • [3] Liu T., Theory and Method of Modern Power System Analysis, (2016)
  • [4] Zhao J., Zhang G., Huang Y., Status and prospect of state estimation of power system with new energy, Electric Power Automation Equipment, 34, 5, pp. 7-20, (2014)
  • [5] Wu Z., Xu J., Yu X., Et al., Review on state estimation technique of active distribution network, Automation of Electric Power Systems, 41, 13, pp. 182-191, (2017)
  • [6] Liu Y., Zhang B., Li J., Et al., Probabilistic load flow algorithm considering static security risk of the power system, Proceedings of the CSEE, 31, 1, pp. 59-64, (2011)
  • [7] Fu Y., Liao J., Li Z., Et al., Static security analysis of active distribution network considering time sequence character, Automation of Electric Power Systems, 40, 24, pp. 64-70, (2016)
  • [8] Peng H., Cao Y., Huang X., Et al., Static security risk assessment of islanded microgrids under peer-peer control, Proceedings of the CSEE, 36, 18, pp. 4837-4846, (2016)
  • [9] Wang H., Hu Z., Zhang M., A combined forecasting model for range of wind power fluctuation based on fuzzy information granulation and least squares support vector machine, Transactions of China Electrotechnical Society, 29, 12, pp. 218-224, (2014)
  • [10] Fan B., Lu X., Li H., Probabilistic inference-based least squares support vector machine for modeling under noisy environment, IEEE Transactions on Systems Man Cybernetics: Systems, 46, 12, pp. 1703-1710, (2016)
12