Research on Intelligent Local Energy System and Power Metering Based on Supply-side Demand Based on KNN
DOI:
https://doi.org/10.13052/spee1048-5236.4413Keywords:
KNN algorithm, smart local energy systems, electricity demand forecasting, electricity meteringAbstract
Based on the K-Nearest Neighbor algorithm, this paper deeply studies the intelligent local energy system and power metering problems of supply-side demand. Through the analysis of a large amount of energy consumption and supply data, we have built an intelligent system that can accurately predict and meet local energy demand. Specifically, we collected electricity consumption data for the past five years, including multi-dimensional information such as daily consumption, seasonal changes, and weather factors. Through the KNN algorithm, we successfully identified the key factors affecting electricity consumption and established a prediction model. The model can predict the power demand in the future based on historical data and real-time information, providing strong decision support for the supply side. In practical application, the system also plays an important role in power metering. Through the monitoring and analysis of real-time power data, the system can accurately calculate the power consumption of each region, providing data support for energy management and optimization. In the application of our pilot city, we’ve achieved remarkable results. The precision of our power demand prediction system has exceeded 90%, while the margin of error in power measurements remains below 2%. These improvements have had a profound impact on energy utilization efficiency and economic performance. Moreover, through meticulous data analysis, we’ve discovered that optimizing the energy mix and increasing the share of renewable energy are highly effective strategies for cutting energy costs and mitigating environmental pollution. Looking ahead, we intend to delve deeper into how the KNN algorithm and other cutting-edge technologies can be harnessed to further enhance the sustainability of our local energy system. The research in this paper not only provides theoretical support for the development of intelligent local energy system, but also provides a new idea for the innovation of power metering technology.
Downloads
References
Hernandez-Matheus, A., Löschenbrand, M., Berg, K., Fuchs, I., Aragüés-Peñalba, M., Bullich-Massagué, E., and Sumper, A. (2022). A systematic review of machine learning techniques related to local energy communities. Renewable and Sustainable Energy Reviews, 170, 112651.
Said, D. (2022). A survey on information communication technologies in modern demand-side management for smart grids: Challenges, solutions, and opportunities. IEEE Engineering Management Review, 51(1), 76–107.
Liao, J., Wu, X., Wu, Y., and Shu, J. (2024). K-NNDP: K-means algorithm based on nearest neighbor density peak optimization and outlier removal. Knowledge-Based Systems, 294, 111742.
Yuk Carrie Lin, K. (2024). Optimizing variable selection and neighbourhood size in the K-nearest neighbour algorithm. Computers & Industrial Engineering, 191, 110142.
Jurado, S., Nebot, À., and Mugica, F. (2020). The Importance of Robust and Reliable Energy Prediction Models: Next Generation of Smart Meters. In SIMULTECH (pp. 248–254).
Huang, H., Xu, H., Cai, Y., Khalid, R. S., and Yu, H. (2018). Distributed machine learning on smart-gateway network toward real-time smart-grid energy management with behavior cognition. ACM Transactions on Design Automation of Electronic Systems (TODAES), 23(5), 1–26.
Lee, S., Nengroo, S. H., H., Doh, Y., Lee, C., Heo, T., and Har, D. (2023). Anomaly detection of smart metering system for power management with battery storage system/electric vehicle. ETRI Journal, 45(4), 650–665.
Johannesen, N. J., Kolhe, M., and Goodwin, M. (2019). Relative evaluation of regression tools for urban area electrical energy demand forecasting. Journal of cleaner production, 218, 555–564.
Mousavi, S., Marroquín, M. G. V., Hajiaghaei-Keshteli, M., and Smith, N. R. (2023). Data-driven prediction and optimization toward net-zero and positive-energy buildings: A systematic review. Building and Environment, 110578.
Sarah, M., and Riadh, B. A. A. (2024). A new hybrid incremental learning system for an enhanced KNN algorithm (hoKNN). Evolving Systems, 3, 15.
Aguilar, J., Garces-Jimenez, A., R-moreno, M. D., and García, R. (2021). A systematic literature review on the use of artificial intelligence in energy self-management in smart buildings. Renewable and Sustainable Energy Reviews, 151, 111530.
Singh, T., Solanki, A., and Sharma, S. K. (2022). Evolution of Smart Home Energy Management System Using Internet of Things and Machine Learning Algorithms. In ACI@ ISIC (pp. 135–151).
Jodas, D. S., Passos, L. A., Adeel, A., and Papa, J. P. (2023). PL-kNN: A Python-based implementation of a parameterless k-Nearest Neighbors classifier. Software Impacts, 15, 100459.
Li, S., Tsui, P.-H., Wu, W., Wu, S., and Zhou, Z. (2024). Ultrasound k-nearest neighbor entropy imaging: Theory, algorithm, and applications. Ultrasonics, 138, 107256.
Tascikaraoglu, A. (2018). Evaluation of spatio-temporal forecasting methods in various smart city applications. Renewable and Sustainable Energy Reviews, 82, 424–435.
Lu, X., Li, K., Xu, H., Wang, F., Zhou, Z. and Zhang, Y., 2020. Fundamentals and business model for resource aggregator of demand response in electricity markets. Energy, 204, p. 117885.
Matijašević, T., Antić, T., and Capuder, T. (2022). A systematic review of machine learning applications in the operation of smart distribution systems. Energy reports, 8, 12379–12407.
Gellert, A., Florea, A., Fiore, U., Palmieri, F., and Zanetti, P. (2019). A study on forecasting electricity production and consumption in smart cities and factories. International Journal of Information Management, 49, 546–556.
Rahman, T., Othman, M. L., Noor, S. B. M., Ahmad, W. F. B. W., and Sulaima, M. F. (2024). Methods and attributes for customer-centric dynamic electricity tariff design: A review. Renewable and Sustainable Energy Reviews, 192, 114228.
Hossain, E., Khan, I., Un-Noor, F., Sikander, S. S., and Sunny, M. S. H. (2019). Application of big data and machine learning in smart grid, and associated security concerns: A review. Ieee Access, 7, 13960–13988.
Zhang, H., Wang, Z., and Zhao, N. H. (2022). Weighted Adaptive KNN Algorithm With Historical Information Fusion for Fingerprint Positioning. IEEE wireless communications letters, 11(5), 1002–1006.
Yin, B., Li, Z., Xu, J., Li, L., Yang, X., and Du, Z. (2022). Non-intrusive load monitoring algorithm based on household electricity use habits. Neural Computing and Applications, 34(18), 15273–15291.
Agathos, A., and Azariadis, P. (2024). Multi-GPU 3D k-nearest neighbors computation with application to ICP, point cloud smoothing and normals computation. Parallel Computing, 121, 103093.
Chen, J., Zhang, X., and Yuan, Z. (2024). Feature selections based on two-type overlap degrees and three-view granulation measures for k-nearest-neighbor rough sets. Pattern Recognition, 156, 110837.
Dutta, A. K., Bharathi Krishna, L., Rayudu, K., Vedhagiri, D., Medikondu, N. R., SudarsananNair JalajaKumari, S. P., … and Saha, N. (2024). Battery-Based Energy Storage and Solar Technologies Integrated for Power Matching and Quality Improvement Using Artificial Intelligence. Electric Power Components and Systems, 52(2), 322–336.
Ding, S., Li, M., Huang, T., and Zhu, W. (2024). Local density based on weighted K-nearest neighbors for density peaks clustering. Knowledge-Based Systems, 305, 112609.
Ebrahimi, M., and Basiri, A. (2024). RACEkNN: A hybrid approach for improving the effectiveness of the k-nearest neighbor algorithm. Knowledge-Based Systems, 301, 112357.
Kikusato, H., Fujimoto, Y., Hanada, S. I., Isogawa, D., Yoshizawa, S., Ohashi, H., and Hayashi, Y. (2019). Electric vehicle charging management using auction mechanism for reducing PV curtailment in distribution systems. IEEE Transactions on Sustainable Energy, 11(3), 1394–1403.
Twala, S., Ye, X., and Zhang, L. (2023). Optimal integration of solar home systems and appliance scheduling for residential homes under severe national load shedding. Journal of Automation and Intelligence, 2(4), 227–238.
Li, F., Zheng, H., Li, X., and Yang, F. (2021). Day-ahead city natural gas load forecasting based on decomposition-fusion technique and diversified ensemble learning model. Applied Energy, 303, 117623.
https://aeeeuropeenergy.com/
