A Line Loss Management Method Based on Improved Random Forest Algorithm in Distributed Generation System

  • Wang Zongbao State Grid Baiyin Power Supply Company, Gansu Baiyin 730900, China
Keywords: Distributed power generation, 35kV, Line Loss, Random Forest Algorithm;

Abstract

The distributed power generation in Gansu Province is dominated by wind power and photovoltaic power. Most of these distributed power plants are located in underdeveloped areas. Due to the weak local consumption capacity, the distributed electricity is mainly sent and consumed outside. A key indicator that affects ultra-long-distance power transmission is line loss. This is an important indicator of the economic operation of the power system, and it also comprehensively reflects the planning, design, production and operation level of power companies. However, most of the current research on line loss is focused on ultra-high voltage (≧110 KV), and there is less involved in distributed power generation lines below 110 KV. In this study, 35 kV and 110 kV lines are taken as examples, combined with existing weather, equipment, operation, power outages and other data, we summarize and integrate an analysis table of line loss impact factors. Secondly, from the perspective of feature relevance and feature importance, we analyze the factors that affect line loss, and obtain data with higher feature relevance and feature importance ranking. In the experiment, these two factors are determined as the final line loss influence factor. Then, based on the conclusion of the line loss influencing factor, the optimized random forest regression algorithm is used to construct the line loss prediction model. The prediction verification results show that the training set error is 0.021 and the test set error is 0.026. The prediction error of the training set and test set is only 0.005. The experimental results show that the optimized random forest algorithm can indeed analyze the line loss of 35 kV and 110 kV lines well, and can also explain the performance of 110-EaR1120 reasonably.

Downloads

Download data is not yet available.

Author Biography

Wang Zongbao, State Grid Baiyin Power Supply Company, Gansu Baiyin 730900, China

Wang Zongbao, born in June 1991, graduated from Northeast Dianli University, majoring in electrical engineering. The current deputy dispatcher of the Power Dispatching Control Center of State Grid Gansu Electric Power Company State Grid Baiyin Power Supply Company, mainly engaged in power grid economic dispatch, power grid security and stability analysis, and big data applications.Successively presided over the compilation of “Baiyin Power Grid Monitoring Information Management System” and “Concurrent Line Loss Offline Auxiliary Calculation and Management System”. In 2018, the QC project “Research and Development and Application of Auxiliary Calculation and Management System for Line Losses in the Same Period” won the second prize of Excellent QC Achievement of Baiyin Power Supply Company. In 2018, he presided over the “Big Data-Based Diagnosis and Decision-making of Abnormal Line Losses in the Same Time” project, which won the gold prize of the Gansu Provincial Company Data Value Mining Innovation Competition. In 2019, he hosted the “Big Data-based Line Loss Line Abnormal Diagnosis and Decision-making in the Same Time”, and obtained the software copyright of “35 kV and above Line Line Loss Analysis Tool Software”.

References

F. Wang, W. Liu, X. Chen, W. Wang, Z. Xing. Evaluation Model of Synchronous Line Loss Data Quality Based on Penalty Variable Weight RDA. Electric Power, 2020, 53(12): 223–231.

J. Wang, Y. Wang, Y. Yang, Y. Wang. Analysis the Impact of Photovoltaic Power Station’s Integration into Rural Distribution Network. Electric Power, 2018, 51(6): 150–154.

L. Liu, C. Zhu. Application of Data Mining Technology to Build the Anti-Stealing Management System. Electric Power, 2017, 50(10): 181–184.

Z. Li, H. Hou, Y. Jiang, C. Wan, R. Zheng. Line Loss Calculation and Electricity Theft Analysis Based on Artificial Neural Network. Southern Power System Technology, 2019, 13(2): 7–12.

Y. Xu, H. Shi. Research on Diagnosis Method of Line Loss Abnormality in Power Grid Based on Machine Learning. Electric Power, 2020, 11(1): 236–237.

W. He, Y. Sun, J. Jiang, L. Jin. Reference Test of Daily Line Loss Rate in Low Voltage Transformer Area based on RNN. Computer Measurement & Control, 2020, 28(9): 58–64.

B. Jin, M. Zhang, H. Wu, Y. Shi. A prediction method of anti-electricity stealing based on big data of electric power. Journal of Light Industry, 2020, 95(4): 81–87.

L. Tao, S. Liu, X. Ceng. Theoretical calculation and analysis of line loss based on power grid. Technology Innovation and Application, 2018, 23(4): 132–133.

X. Chen, M. Liu. Prediction of protein-protein interactions using random decision forest framework. Bioinformatics, 2005, 21(24): 4394–4400.

Smith A, Sterba-Boatwright B, Mott J. Novel application of a statistical technique, Random Forests, in a bacterial source tracking study. Water Research, 2010, 44(14): 4067–4076.

Y. Cheng, H. Zou. Random Forest RFM Model and Its Evaluation in Bank Credit Risk. Journal of Anqing Teachers College (Natural Science Edition), 2018, 3(1): 34–37.

T. Sun, X. Xu. Medical Big Data Analysis and Clinical Application Based on Machine Learning. Software Guide, 2019, 11(1): 10–14.

R. Lu, L. Li. Model of Crime Prediction Based on the Random Forest. Journal of Criminal Investigation Police University of China, 2019, (3): 108–112.

Y. Huang, W. Cha. Comparison on Classification Performance Between Random Forests and Support Vector Machine. Software, 2012, 33(6): 107–110.

J. Zhao, X. Zhang, F. Di, S. Guo, X. Li. Exploring the Optimum Proactive Defense Strategy for the Power Systems from an Attack Perspective. Security and Communication Networks, 2021, 2021(1): 1–14.

Y. Tao, T. Huang, M. Li, et al. Research on Log Audit Analysis Model of Cyberspace Security Classified Protection Driven by Knowledge Map[J]. Netinfo Security, 2020, 20(1): 46–51.

W. Dong, Y. Li. Research on Analysis of Attacks on Smart Grid Network Based on Complex Network[J]. Netinfo Security, 2020, 20(1): 52–60.

W. Luo, C. Xu. Network Intrusion Detection Based on Improved MajorClust Clustering[J]. Netinfo Security, 2020, 20(2): 14–21.

C. Peng, Y. Zhao, M. Fan. A Differential Private Data Publishing Algorithm via Principal Component Analysis Based on Maximum Information Coefficient[J]. Netinfo Security, 2020, 20(2): 37–48.

R. Wang, C. Ma, P. Wu. An Intrusion Detection Method Based on Federated Learning and Convolutional Neural Network[J]. Netinfo Security, 2020, 20(4): 47–54.

J. Xiong, R. Bi, M. Zhao, J. Guo, Q. Yang. Edge-assisted privacy-preserving raw data sharing framework for connected autonomous vehicles, IEEE Wireless Communications, 2020, 27(3): 24–30.

Y. Tian, Z. Wang, J. Xiong, J. Ma. A blockchain-based secure key management scheme with trustworthiness in DWSNs, IEEE Transactions on Industrial Informatics, 2020, 16(9): 6193–6202.

J. Xiong, X. Chen, Q. Yang, L. Chen, Z. Yao. A task-oriented user selection incentive mechanism in edge-aided mobile crowdsensing, IEEE Transactions on Network Science and Engineering, 2020, 7(4): 2347–2360.

J. Xiong, R. Ma, L. Chen, Y. Tian, Q. Li, X. Liu, Z. Yao. A personalized privacy protection framework for mobile crowdsensing in IIoT, IEEE Transactions on Industrial Informatics, 2020, 16(6): 4231–4241.

Published
2021-08-30
Section
Renewable Power and Energy Systems