Smart City Gnosys
Smart city article details
| Title | Understanding Of Cellular Network Workload And Prediction Using Machine Learning Approach |
|---|---|
| ID_Doc | 59474 |
| Authors | Gupta S.; Suman U. |
| Year | 2023 |
| Published | 3rd IEEE International Conference on ICT in Business Industry and Government, ICTBIG 2023 |
| DOI | http://dx.doi.org/10.1109/ICTBIG59752.2023.10456308 |
| Abstract | Management of world class services in smart cities required to deploy dense and efficient communication networks. Therefore, we need to increase the network infrastructure in terms of base stations. But increasing network base stations also increases the power consumption and during ideal conditions may cause the power wastage. In this paper, we have explored the workload data of the cellular base stations and presented their trends. In addition, we include Machine Learning (ML) approaches to predict hourly base station workload. In this context, K-Nearest Neighbour (KNN) regressor, Support Vector Regression (SVR) and XGBoost regression have been trained. The experiments with the 4G LTE cellular network traffic have been carried out, which consist of a total of 57 base station's workload for 24 hours. Among these base stations, we selected an individual base station to predict the workload. The proposed investigation will helpful for designing an effective proactive power allocation technique to reduce the power consumption in cellular base stations. On the other hand, when we compared the performance of these three algorithms for prediction accuracy, we found that the KNN regressor provides the best accuracy of 99% for predicting individual base station's hourly workload. © 2023 IEEE. |
| Author Keywords | Cellular network; Machine Learning; Power Consumption; Proactive Power scheduling; Workload Prediction |
Similar Articles
| Id | Similarity | Authors | Title | Published |
|---|---|---|---|---|
55683  | 0.894 | Punjabi M.; Gupta R. | The Impact Of Artificial Intelligence On Energy Optimization For Cellular Network Base Stations | Intelligent Networks: Techniques, and Applications (2024) |
| 48117 | 0.889 | Shrivastava P.; Patel S. | Selection Of Efficient And Accurate Prediction Algorithm For Employing Real Time 5G Data Load Prediction | 2021 IEEE 6th International Conference on Computing, Communication and Automation, ICCCA 2021 (2021) |
| 6021 | 0.876 | Yang T.J.; Nordin R.; Abdullah N.F.B.; Fauzi M.F.A.; Hliang N.W. | Accurate Fifth Generation Mobile Network Coverage Prediction In Smart Cities With Machine Learning | 2024 IEEE Asia-Pacific Conference on Applied Electromagnetics, APACE 2024 (2024) |
| 35951 | 0.866 | Yadav P.; Sharma S.; Singh P.K. | Machine Learning Driven Path Loss Prediction For 5G Networks In Smart Cities Metro Station Environments | ICDT 2025 - 3rd International Conference on Disruptive Technologies (2025) |
| 975 | 0.856 | Khan M.A.A.; Kaidi H.M. | A Comprehensive Survey Of Machine Learning Techniques In Next-Generation Wireless Networks And The Internet Of Things | Ingenierie des Systemes d'Information, 28, 4 (2023) |
| 17261 | 0.856 | Vesselinova N.; Harjula M.; Ilmonen P. | Data Matters: The Case Of Predicting Mobile Cellular Traffic | IEEE Vehicular Networking Conference, VNC (2025) |
| 35994 | 0.854 | Dritsas E.; Trigka M. | Machine Learning In Intelligent Networks: Architectures, Techniques, And Use Cases | IEEE Access, 13 (2025) |