Storage of large-scale and multivariate power data faces challenges such as low efficiency and insufficient memory capacity. Traditional data storage optimization methods like data index and data compress methods have their own advantages and disadvantages. How to effectively apply these methods to power data storage is a core problem in current research. To solve the problem, a storage optimization decision method for multivariate power data that integrates random forest algorithm and Q-learning algorithm was proposed. Key technologies of this method were these as follows. Firstly, a storage optimization strategy decision model based on an improved random forest algorithm was developed. By the introduction of information gain method, the model could evaluate the data access frequency, query time, storage speed and data redundancy rate during database data storage, and made choice on storage optimization strategies like direct data storage, data index storage, and data compress storage. Secondly, a data storage algorithm decision model based on the improved Q-learning algorithm was proposed. By the introduction of multi-scale learning mechanism, prioritized experience replay mechanism and positive/negative reward mechanism, the model could determine the suitable index algorithm for data index storage and the compress algorithm for data compress storage. The proposed method effectively integrates the technological advantages of data index and data compress storage, can improve data storage efficiency and save storage space significantly, and thus provide a new solution for the management of large-scale and multivariate power data.
YE Xue-shun, JIA Dong-li, ZHOU Jun, TANG Ying, JIA Zi-hao.
Storage Optimization Decision Method for Multivariate Power Data Based on the Integration of Random Forest and Q-learning[J].
Science Technology and Engineering, 2026, 26(3): 1065-1074 DOI:10.12404/j.issn.1671-1815.2501706
LiGaoyang, WangNing, GaoRuotian, et al. Research on multi-source heterogeneous data fusion technology for intelligent efficiency improvement of new power systems[J]. Electrical Measurement & Instrumentation, 2024, 61(11): 116-121.
SunYingtao, ZhangFengming, ChenShuibiao, et al. Power data anomaly detection algorithm based on multi-domain feature extraction[J]. Proceedings of the CSU-EPSA, 2022, 34(6): 105-113.
ZengFei, YangXiong, SuWei, et al. Power data storage and sharing method based on blockchain and data lake[J]. Power Engineering Technology, 2022, 41(3): 48-54.
LiYueyi, ZhangFeng, DuZhenhong, et al. Spatio-temporal flow distributed scheduling and storage scheme based on LSM-OCTree[J]. Journal of Zhejiang University (Science Edition), 2023, 50(2): 204-212.
XiaXiufeng, SunXiangtian, SunYao, et al. Regular path query algorithm based on inverted index[J]. Computer Engineering and Design, 2024, 45(8): 2343-2349.
GengQingtian, DiJing, ChangLiang, et al. Data indexing and storage based on B+ tree[J]. Journal of Jilin University (Science Edition), 2013, 51(6): 1133-1136.
YuHao, YangJiahui, XiWei, et al. Research progress and prospects of smart distribution and power consumption data compression methods[J]. Power Supply and Consumption, 2024, 41(8): 2-14.
ZhouHang, PanXiaohui, SunJiawei, et al. Application of the CZ-BWT improved LZW compression algorithm in power messages[J]. Computer Integrated Manufacturing Systems, 2024, 30(8): 2947-2953.
XuXiaofei, ChenLiang. LZ77 power data compression algorithm using integer wavelet transform[J]. Journal of Xi’an University of Engineering, 2018, 32(3): 337-342.
HongDehua, LiuCuiling, ZhaoLinyan, et al. Power data recognition method based on multi-domain feature analysis and selection[J]. Hydropower and Energy Science, 2023, 41(9): 211-215.
LiQiang, ZhangLimei, BaiMuke. Intelligent distribution network anomaly data identification based on multivariate data features and improved random forest[J]. Science Technology and Engineering, 2023, 23(5): 2007-2015.
ZhangYushan, ZhouYatong. Short-term power load forecasting model optimization based on VMD-SSA-RF algorithm[J]. Electrical Engineering and New Technology, 2024, 43(12): 30-39.
TuQian, ZhanYabo, ChenDongliang, et al. Research on power grid engineering data processing and analysis method based on Q-Learning[J]. Electronic Design Engineering, 2023, 31(12): 124-127, 132.
GuanCheng, LiuMingyue, ManWeidong, et al. Estimation of chlorophyll content in leaves of Spartina alterniflora by continuous wavelet combined with random forest algorithm[J]. Spectroscopy and Spectral Analysis, 2024, 44(10): 2993-3000.
WangPeng, DengZhi, FanYuyang. Finite state machine anti single particle flipping design for single hot encoding[J]. Telecommunications Technology2022, 62(8): 1178-1183..
XiangZheng, HeYuyang, QuanZhiwei. A rerouting path planning based on Q-Learning algorithm in congested airspace[J]. Science Technology and Engineering, 2022, 22(32): 14494-14501.