Multi-objective predictive maintenance optimization of electric energy meters based on LSTM-XGBoost and modified firefly algorithm
-
,
Abstract
Due to the rapid development of modern smart grid and Internet of Things technology, the operational and maintenance demands on smart meters, the core metering equipment of the power system, are becoming increasingly significant. Traditional maintenance methods waste resources and are inefficient. Therefore, a new maintenance paradigm combining stable, efficient prediction technology and intelligent, decision-making optimization is urgently needed. This paper proposes a multi-objective predictive maintenance optimization framework based on a long short-term memory (LSTM)-extreme gradient boosting (XGBoost) hybrid model and an improved firefly algorithm (IFA). The framework addresses three core challenges in smart meter operation and maintenance: complex failure modes, limited resources, and conflicting objectives. The main innovations of this study are: 1. A spatiotemporal hybrid prediction model for meter failures is proposed for the first time. This model combines bidirectional LSTMs to capture long-term parameter dependencies, such as voltage and current, and introduces an enhanced XGBoost with a dynamic threshold Huber loss function (DTHL). This reduces error by 25 % in voltage mutation scenarios. 2. A maintenance decision optimization model is designed based on an improved firefly algorithm. The model suggests a maintenance-specific brightness index and a cosine annealing step strategy. The convergence speed is 3.2 times faster than NSGA-II. 3. Support edge-cloud collaborative computing with a prediction response time of less than 200 ms. Using real data from the Gansu Electric Power Company from 2020 to 2024 covering 9,823 devices, the LSTM-XGBoost model performs well in predicting faults. Under budget and manpower constraints, IFA’s cost savings and risk reduction rates are 8.2 % and 9.5 % higher than NSGA-II, respectively, and resource utilization is 89.7 %. SHAP analysis shows that temperature, voltage fluctuations and communication packet loss rate are key fault characteristics.
-
Research ethics: This study does not involve any experiments on humans or animals and therefore does not require ethical approval.
-
Informed consent: Not applicable, as no human subjects were involved.
-
Author contributions: All authors have accepted responsibility for the entire content of this manuscript and approved its submission.
-
Use of Large Language Models, AI and Machine Learning Tools: None declared.
-
Conflict of interest: The authors declare that there are no conflicts of interest regarding the publication of this paper.
-
Research funding: None declared.
-
Data availability: The dataset used in this study was provided by Gansu Electric Power Company under formal collaboration and used strictly for research purposes with proper authorization.
References
1. Nassereddine, M, Alex, K. Applications of internet of things (IoT) in smart cities. In: Advanced IoT technologies and applications in the industry 4.0 digital economy. New York: CRC Press; 2024:109–36 pp.10.1201/9781003434269-6Search in Google Scholar
2. Saied, M, Guirguis, S, Madbouly, M. Review of artificial intelligence for enhancing intrusion detection in the internet of things. Eng Appl Artif Intell 2024;127:107231. https://doi.org/10.1016/j.engappai.2023.107231.Search in Google Scholar
3. Mu, X, Antwi-Afari, MF. The applications of internet of things (IoT) in industrial management: a science mapping review. Int J Prod Res 2024;62:1928–52. https://doi.org/10.1080/00207543.2023.2290229.Search in Google Scholar
4. Aouedi, O, Vu, Thai-H, Sacco, A, Nguyen, DC, Piamrat, K, Marchetto, G, et al.. A survey on intelligent internet of things: applications, security, privacy, and future directions. IEEE Commun Surv Tutorials 2024;27:1238–92. https://doi.org/10.1109/comst.2024.3430368.Search in Google Scholar
5. Meng, F, Li, J, Li, Z, Li, X, Li, Y, Xiang, S. Research on the automatic recheck system and maintenance technology for dismantled electric energy meters. In: IEEE 3rd international conference on electrical engineering, big data and algorithms (EEBDA). London: IEEE; 2024. 905–9. pp.10.1109/EEBDA60612.2024.10485916Search in Google Scholar
6. Zhu, Y, Jin, Y, Lin, T, Gong, G, Yao, Z. Analysis and adoption of the internet of things in life cycle management of electric energy meters. Academic J Bus Manag 2022;4:129–35.10.25236/AJBM.2022.041119Search in Google Scholar
7. Bermeo-Ayerbe, MA, Ocampo-Martinez, C, Diaz-Rozo, J. Data-driven energy prediction modeling for both energy efficiency and maintenance in smart manufacturing systems. Energy 2022;238:121691. https://doi.org/10.1016/j.energy.2021.121691.Search in Google Scholar
8. Kumar, LA, Indragandhi, V, Selvamathi, R, Vijayakumar, V, Ravi, L, Subramaniyaswamy, V. Design, power quality analysis, and implementation of smart energy meter using internet of things. Comput Electr Eng 2021;93:107203. https://doi.org/10.1016/j.compeleceng.2021.107203.Search in Google Scholar
9. Salunkhe, AS, Kanse, YK, Patil, SS. Internet of things based smart energy meter with esp 32 real time data monitoring. In: 2022 international conference on electronics and renewable systems (ICEARS). Berlin: IEEE; 2022:446–51 pp.10.1109/ICEARS53579.2022.9752144Search in Google Scholar
10. Vashist, PC, Tripathi, A. Design and implementation of smart energy meter with real-time pricing. In: Computational and experimental methods in mechanical engineering: proceedings of ICCEMME 2021. Springer Singapore, Singapore; 2021:499–507 pp.10.1007/978-981-16-2857-3_49Search in Google Scholar
11. Rind, YM, Haseeb Raza, M, Zubair, M, Mehmood, MQ, Massoud, Y. Smart energy meters for smart grids, an internet of things perspective. Energ 2023;16:1974. https://doi.org/10.3390/en16041974.Search in Google Scholar
12. Jabbar, WA, Annathurai, S, Rahim, TAA, Fitri Mohd Fauzi, M. Smart energy meter based on a long-range wide-area network for a stand-alone photovoltaic system. Expert Syst Appl 2022;197:116703. https://doi.org/10.1016/j.eswa.2022.116703.Search in Google Scholar
13. Yu, SONG, Yongzhong, YU, Xuchang, LIANG, Yi, WANG, Tiexin, HOU. Calibration method of line transformer relationship in distribution network based on data analysis of electric energy metering management system. High Volt Eng 2021;47:4461–70.Search in Google Scholar
14. Gerasopoulos, SI, Manousakis, NM, Psomopoulos, CS. Smart metering in EU and the energy theft problem. Energy Effic 2022;15:12. https://doi.org/10.1007/s12053-021-10011-y.Search in Google Scholar
15. Ma, L, Meng, Z, Teng, Z, Tang, Q. A measurement error prediction framework for smart meters under extreme natural environment stresses. Elec Power Syst Res 2023;218:109192. https://doi.org/10.1016/j.epsr.2023.109192.Search in Google Scholar
16. Ray, S, Lama, A, Mishra, P, Biswas, T, Das, SS, Gurung, B. An ARIMA-LSTM model for predicting volatile agricultural price series with random forest technique. Appl Soft Comput 2023;149:110939. https://doi.org/10.1016/j.asoc.2023.110939.Search in Google Scholar
17. Gülmez, B. Stock price prediction with optimized deep LSTM network with artificial rabbits optimization algorithm. Expert Syst Appl 2023;227:120346. https://doi.org/10.1016/j.eswa.2023.120346.Search in Google Scholar
18. Dao, F, Zeng, Y, Qian, J. Fault diagnosis of hydro-turbine via the incorporation of bayesian algorithm optimized CNN-LSTM neural network. Energy 2024;290:130326. https://doi.org/10.1016/j.energy.2024.130326.Search in Google Scholar
19. Pan, S, Yang, B, Wang, S, Guo, Z, Wang, L, Liu, J, et al.. Oil well production prediction based on CNN-LSTM model with self-attention mechanism. Energy 2023;284:128701. https://doi.org/10.1016/j.energy.2023.128701.Search in Google Scholar
20. Zaheer, S, Anjum, N, Hussain, S, Algarni, AD, Iqbal, J, Bourouis, S, et al.. A multi parameter forecasting for stock time series data using LSTM and deep learning model. Math 2023;11:590. https://doi.org/10.3390/math11030590.Search in Google Scholar
21. Zaini, N’atiah, Ali, NA, Ean, LW, Chow, MF, Abdul Malek, M. Forecasting of fine particulate matter based on LSTM and optimization algorithm. J Clean Prod 2023;427:139233. https://doi.org/10.1016/j.jclepro.2023.139233.Search in Google Scholar
22. Fan, D, Sun, H, Yao, J, Zhang, K, Yan, X, Sun, Z. Well production forecasting based on ARIMA-LSTM model considering manual operations. Energy 2021;220:119708. https://doi.org/10.1016/j.energy.2020.119708.Search in Google Scholar
23. Behera, RK, Jena, M, Kumar Rath, S, Misra, S. Co-LSTM: convolutional LSTM model for sentiment analysis in social big data. Inf Process Manag 2021;58:102435. https://doi.org/10.1016/j.ipm.2020.102435.Search in Google Scholar
24. Limouni, T, Yaagoubi, R, Bouziane, K, Guissi, K, El, HB. Accurate one step and multistep forecasting of very short-term PV power using LSTM-TCN model. Renew Energy 2023;205:1010–24. https://doi.org/10.1016/j.renene.2023.01.118.Search in Google Scholar
25. Yang, C, Liu, Y. Multi-objective optimization for robust attitude determination of satellite with narrow bound theory. Adv Space Res 2024;74:3273–83. https://doi.org/10.1016/j.asr.2024.06.002.Search in Google Scholar
26. Qiao, K, Liang, J, Yu, K, Guo, W, Yue, C, Qu, B, et al.. Benchmark problems for large-scale constrained multi-objective optimization with baseline results. Swarm Evol Comput 2024;86:101504. https://doi.org/10.1016/j.swevo.2024.101504.Search in Google Scholar
27. Mashru, N, Tejani, GG, Patel, P, Khishe, M. Optimal truss design with MOHO: a multi-objective optimization perspective. PLoS One 2024;19:e0308474. https://doi.org/10.1371/journal.pone.0308474.Search in Google Scholar PubMed PubMed Central
28. Cai, X, Wu, L, Zhao, T, Wu, D, Zhang, W, Chen, J. Dynamic adaptive multi-objective optimization algorithm based on type detection. Inf Sci 2024;654:119867. https://doi.org/10.1016/j.ins.2023.119867.Search in Google Scholar
29. Abdollahzadeh, B, Soleimanian Gharehchopogh, F. A multi-objective optimization algorithm for feature selection problems. Eng Comput 2022;38:1845–63. https://doi.org/10.1007/s00366-021-01369-9.Search in Google Scholar
30. Chen, R, Tsay, Yaw-S, Zhang, T. A multi-objective optimization strategy for building carbon emission from the whole life cycle perspective. Energy 2023;262:125373. https://doi.org/10.1016/j.energy.2022.125373.Search in Google Scholar
31. Ma, H, Haoyu, W, Tian, Y, Cheng, R, Zhang, X. A multi-stage evolutionary algorithm for multi-objective optimization with complex constraints. Inf Sci 2021;560:68–91. https://doi.org/10.1016/j.ins.2021.01.029.Search in Google Scholar
32. Ala, A, Goli, A, Mirjalili, S, Simic, V. A fuzzy multi-objective optimization model for sustainable healthcare supply chain network design. Appl Soft Comput 2024;150:111012. https://doi.org/10.1016/j.asoc.2023.111012.Search in Google Scholar
33. Li, Z, Zhao, Y, Xia, H, Xie, S. A multi-objective optimization framework for building performance under climate change. J Build Eng 2023;80:107978. https://doi.org/10.1016/j.jobe.2023.107978.Search in Google Scholar
34. Zhang, D, Zhu, H, Zhang, H, Goh, HH, Liu, H, Wu, T. Multi-objective optimization for smart integrated energy system considering demand responses and dynamic prices. IEEE Trans Smart Grid 2021;13:1100–12. https://doi.org/10.1109/tsg.2021.3128547.Search in Google Scholar
35. Hasanzadeh, R, Mojaver, P, Azdast, T, Khalilarya, S, Chitsaz, A. Developing gasification process of polyethylene waste by utilization of response surface methodology as a machine learning technique and multi-objective optimizer approach. Int J Hydrogen Energy 2023;48:5873–86. https://doi.org/10.1016/j.ijhydene.2022.11.067.Search in Google Scholar
36. Gómez-Expósito, A, Conejo, AJ, Cañizares, C, editors. Electric energy systems: analysis and operation. Tokyo: CRC Press; 2018.10.1201/9781420007275Search in Google Scholar
37. Jradi, M, Veje, C, Jørgensen, BN. Performance analysis of a soil-based thermal energy storage system using solar-driven air-source heat pump for Danish buildings sector. Appl Therm Eng 2017;114:360–73. https://doi.org/10.1016/j.applthermaleng.2016.12.005.Search in Google Scholar
38. Shi, T, Li, P, Yang, W, Qi, A, Qiao, J. Research on air quality monitoring system based on STM32 single chip microcomputer. In: 2022 international symposium on intelligent signal processing and communication systems (ISPACS). Paris: IEEE; 2022:1–4 pp.10.1109/ISPACS57703.2022.10082790Search in Google Scholar
39. Huang, Y, Lei, D. Multisource data acquisition based on single-chip microcomputer and sensor technology. Open Computer Science 2022;12:416–26. https://doi.org/10.1515/comp-2022-0261.Search in Google Scholar
40. Li, J, An, X, Li, Q, Wang, C, Yu, H, Zhou, X, et al.. Application of XGBoost algorithm in the optimization of pollutant concentration. Atmos Res 2022;276:106238. https://doi.org/10.1016/j.atmosres.2022.106238.Search in Google Scholar
41. Pan, S, Zheng, Z, Guo, Z, Luo, H. An optimized XGBoost method for predicting reservoir porosity using petrophysical logs. J Petrol Sci Eng 2022;208:109520. https://doi.org/10.1016/j.petrol.2021.109520.Search in Google Scholar
42. Qiu, Y, Zhou, J, Khandelwal, M, Yang, H, Yang, P, Li, C. Performance evaluation of hybrid WOA-XGBoost, GWO-XGBoost and BO-XGBoost models to predict blast-induced ground vibration. Eng Comput 2022;38:4145–62. https://doi.org/10.1007/s00366-021-01393-9.Search in Google Scholar
43. Zhang, J, Ma, X, Zhang, J, Sun, D, Zhou, X, Mi, C, et al.. Insights into geospatial heterogeneity of landslide susceptibility based on the SHAP-XGBoost model. J Environ Manag 2023;332:117357. https://doi.org/10.1016/j.jenvman.2023.117357.Search in Google Scholar PubMed
44. Zhao, P, Yu, F, Wan, Z. A huber loss minimization approach to byzantine robust federated learning. Proc AAAI Conf Artif Intell 2024;38:21806–14. https://doi.org/10.1609/aaai.v38i19.30181.Search in Google Scholar
45. Taggart, RJ. Point forecasting and forecast evaluation with generalized huber loss. Electron J Statistics 2022;16:201–31. https://doi.org/10.1214/21-ejs1957.Search in Google Scholar
46. Meyer, GP. An alternative probabilistic interpretation of the huber loss. In: Proceedings of the ieee/cvf conference on computer vision and pattern recognition. New York: IEEE; 2021:5261–9 pp.10.1109/CVPR46437.2021.00522Search in Google Scholar
47. Waoo, AA, Soni, BK. Performance analysis of sigmoid and relu activation functions in deep neural network. In: Intelligent systems: proceedings of SCIS 2021. Springer, Singapore; 2021:39–52 pp.10.1007/978-981-16-2248-9_5Search in Google Scholar
48. Dubey, SR, Singh, SK, Chaudhuri, BB. Activation functions in deep learning: a comprehensive survey and benchmark. Neurocomputing 2022;503:92–108. https://doi.org/10.1016/j.neucom.2022.06.111.Search in Google Scholar
49. Ding, P, Blitzstein, JK. On the Gaussian mixture representation of the laplace distribution. Am Statistician 2018;72:172–4. https://doi.org/10.1080/00031305.2017.1291448.Search in Google Scholar
50. Jiang, Z, Zhou, W, Guo, Y, Zhang, C, Lu, T. A novel robust multivariate laplace distribution-based distributed consensus information fusion. Measurement 2024;225:113986. https://doi.org/10.1016/j.measurement.2023.113986.Search in Google Scholar
51. Wang, H, Liang, Q, Hancock, JT, Khoshgoftaar, TM. Feature selection strategies: a comparative analysis of SHAP-Value and importance-based methods. J Big Data 2024;11:44. https://doi.org/10.1186/s40537-024-00905-w.Search in Google Scholar
52. Mosca, E, Szigeti, F, Tragianni, S, Gallagher, D, Groh, G. SHAP-based explanation methods: a review for NLP interpretability. In: Proceedings of the 29th international conference on computational linguistics. Gyeongju, Republic of Korea: International Committee on Computational Linguistics (ICCL); 2022:4593–603 pp.Search in Google Scholar
© 2025 Walter de Gruyter GmbH, Berlin/Boston
