Analysis and Multiobjective Optimization of a Machine Learning Algorithm for Wireless Telecommunication
There has been a fast deployment of wireless networks in recent years, which has been accompanied by significant impacts on the environment. Among the solutions that have been proven to be effective in reducing the energy consumption of wireless networks is the use of machine learning algorithms in...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-04-01
|
| Series: | Telecom |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-4001/4/2/13 |
| _version_ | 1827735513978634240 |
|---|---|
| author | Samah Temim Larbi Talbi Farid Bensebaa |
| author_facet | Samah Temim Larbi Talbi Farid Bensebaa |
| author_sort | Samah Temim |
| collection | DOAJ |
| description | There has been a fast deployment of wireless networks in recent years, which has been accompanied by significant impacts on the environment. Among the solutions that have been proven to be effective in reducing the energy consumption of wireless networks is the use of machine learning algorithms in cell traffic management. However, despite promising results, it should be noted that the computations required by machine learning algorithms have increased at an exponential rate. Massive computing has a surprisingly large carbon footprint, which could affect its real-world deployment. Thus, additional attention needs to be paid to the design and parameterization of these algorithms applied in order to reduce the energy consumption of wireless networks. In this article, we analyze the impact of hyperparameters on the energy consumption and performance of machine learning algorithms used for cell traffic prediction. For each hyperparameter (number of layers, number of neurons per layer, optimizer algorithm, batch size, and dropout) we identified a set of feasible values. Then, for each combination of hyperparameters, we trained our model and analyzed energy consumption and the resulting performance. The results from this study reveal a great correlation between hyperparameters and energy consumption, confirming the paramount importance of selecting optimal hyperparameters. A tradeoff between the minimization of energy consumption and the maximization of machine learning performance is suggested. |
| first_indexed | 2024-03-11T01:52:04Z |
| format | Article |
| id | doaj.art-674ba73857b34f729a8bc81cad5b50b3 |
| institution | Directory Open Access Journal |
| issn | 2673-4001 |
| language | English |
| last_indexed | 2024-03-11T01:52:04Z |
| publishDate | 2023-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Telecom |
| spelling | doaj.art-674ba73857b34f729a8bc81cad5b50b32023-11-18T12:53:14ZengMDPI AGTelecom2673-40012023-04-014221923510.3390/telecom4020013Analysis and Multiobjective Optimization of a Machine Learning Algorithm for Wireless TelecommunicationSamah Temim0Larbi Talbi1Farid Bensebaa2Computer Science and Engineering Department, University of Quebec in Outaouais, Gatineau, QC J9A 1L8, CanadaComputer Science and Engineering Department, University of Quebec in Outaouais, Gatineau, QC J9A 1L8, CanadaEnergy, Mining and Environment Research Centre, National Research Council, Ottawa, ON K1A 0R6, CanadaThere has been a fast deployment of wireless networks in recent years, which has been accompanied by significant impacts on the environment. Among the solutions that have been proven to be effective in reducing the energy consumption of wireless networks is the use of machine learning algorithms in cell traffic management. However, despite promising results, it should be noted that the computations required by machine learning algorithms have increased at an exponential rate. Massive computing has a surprisingly large carbon footprint, which could affect its real-world deployment. Thus, additional attention needs to be paid to the design and parameterization of these algorithms applied in order to reduce the energy consumption of wireless networks. In this article, we analyze the impact of hyperparameters on the energy consumption and performance of machine learning algorithms used for cell traffic prediction. For each hyperparameter (number of layers, number of neurons per layer, optimizer algorithm, batch size, and dropout) we identified a set of feasible values. Then, for each combination of hyperparameters, we trained our model and analyzed energy consumption and the resulting performance. The results from this study reveal a great correlation between hyperparameters and energy consumption, confirming the paramount importance of selecting optimal hyperparameters. A tradeoff between the minimization of energy consumption and the maximization of machine learning performance is suggested.https://www.mdpi.com/2673-4001/4/2/13energy consumptioncell traffic managementhyperparametersLSTMmachine learningoptimization |
| spellingShingle | Samah Temim Larbi Talbi Farid Bensebaa Analysis and Multiobjective Optimization of a Machine Learning Algorithm for Wireless Telecommunication Telecom energy consumption cell traffic management hyperparameters LSTM machine learning optimization |
| title | Analysis and Multiobjective Optimization of a Machine Learning Algorithm for Wireless Telecommunication |
| title_full | Analysis and Multiobjective Optimization of a Machine Learning Algorithm for Wireless Telecommunication |
| title_fullStr | Analysis and Multiobjective Optimization of a Machine Learning Algorithm for Wireless Telecommunication |
| title_full_unstemmed | Analysis and Multiobjective Optimization of a Machine Learning Algorithm for Wireless Telecommunication |
| title_short | Analysis and Multiobjective Optimization of a Machine Learning Algorithm for Wireless Telecommunication |
| title_sort | analysis and multiobjective optimization of a machine learning algorithm for wireless telecommunication |
| topic | energy consumption cell traffic management hyperparameters LSTM machine learning optimization |
| url | https://www.mdpi.com/2673-4001/4/2/13 |
| work_keys_str_mv | AT samahtemim analysisandmultiobjectiveoptimizationofamachinelearningalgorithmforwirelesstelecommunication AT larbitalbi analysisandmultiobjectiveoptimizationofamachinelearningalgorithmforwirelesstelecommunication AT faridbensebaa analysisandmultiobjectiveoptimizationofamachinelearningalgorithmforwirelesstelecommunication |