Task Offloading and Resource Allocation for Mobile Edge Computing by Deep Reinforcement Learning Based on SARSA
In recent years, computation offloading has become an effective way to overcome the constraints of mobile devices (MDs) by offloading delay-sensitive and computation-intensive mobile application tasks to remote cloud-based data centers. Smart cities can benefit from offloading to edge points in the...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2020-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/9039672/ |
| _version_ | 1828928541424615424 |
|---|---|
| author | Taha Alfakih Mohammad Mehedi Hassan Abdu Gumaei Claudio Savaglio Giancarlo Fortino |
| author_facet | Taha Alfakih Mohammad Mehedi Hassan Abdu Gumaei Claudio Savaglio Giancarlo Fortino |
| author_sort | Taha Alfakih |
| collection | DOAJ |
| description | In recent years, computation offloading has become an effective way to overcome the constraints of mobile devices (MDs) by offloading delay-sensitive and computation-intensive mobile application tasks to remote cloud-based data centers. Smart cities can benefit from offloading to edge points in the framework of the so-called cyber-physical-social systems (CPSS), as for example in traffic violation tracking cameras. We assume that there are mobile edge computing networks (MECNs) in more than one region, and they consist of multiple access points, multi-edge servers, and N MDs, where each MD has M independent real-time massive tasks. The MDs can connect to a MECN through the access points or the mobile network. Each task be can processed locally by the MD itself or remotely. There are three offloading options: nearest edge server, adjacent edge server, and remote cloud. We propose a reinforcement-learning-based state-action-reward-state-action (RL-SARSA) algorithm to resolve the resource management problem in the edge server, and make the optimal offloading decision for minimizing system cost, including energy consumption and computing time delay. We call this method OD-SARSA (offloading decision-based SARSA). We compared our proposed method with reinforcement learning based Q learning (RL-QL), and it is concluded that the performance of the former is superior to that of the latter. |
| first_indexed | 2024-12-14T00:06:05Z |
| format | Article |
| id | doaj.art-0788f05474d14cd9ac061f3922a1740b |
| institution | Directory Open Access Journal |
| issn | 2169-3536 |
| language | English |
| last_indexed | 2024-12-14T00:06:05Z |
| publishDate | 2020-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj.art-0788f05474d14cd9ac061f3922a1740b2022-12-21T23:26:01ZengIEEEIEEE Access2169-35362020-01-018540745408410.1109/ACCESS.2020.29814349039672Task Offloading and Resource Allocation for Mobile Edge Computing by Deep Reinforcement Learning Based on SARSATaha Alfakih0https://orcid.org/0000-0003-0366-5932Mohammad Mehedi Hassan1https://orcid.org/0000-0002-3479-3606Abdu Gumaei2https://orcid.org/0000-0001-8512-9687Claudio Savaglio3https://orcid.org/0000-0001-5092-0823Giancarlo Fortino4https://orcid.org/0000-0002-4039-891XDepartment of Information Systems, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi ArabiaDepartment of Information Systems, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi ArabiaDepartment of Information Systems, College of Computer and Information Sciences, King Saud University, Riyadh, Saudi ArabiaDepartment of Informatics, Modeling, Electronics and Systems, University of Calabria, Rende, ItalyDepartment of Informatics, Modeling, Electronics and Systems, University of Calabria, Rende, ItalyIn recent years, computation offloading has become an effective way to overcome the constraints of mobile devices (MDs) by offloading delay-sensitive and computation-intensive mobile application tasks to remote cloud-based data centers. Smart cities can benefit from offloading to edge points in the framework of the so-called cyber-physical-social systems (CPSS), as for example in traffic violation tracking cameras. We assume that there are mobile edge computing networks (MECNs) in more than one region, and they consist of multiple access points, multi-edge servers, and N MDs, where each MD has M independent real-time massive tasks. The MDs can connect to a MECN through the access points or the mobile network. Each task be can processed locally by the MD itself or remotely. There are three offloading options: nearest edge server, adjacent edge server, and remote cloud. We propose a reinforcement-learning-based state-action-reward-state-action (RL-SARSA) algorithm to resolve the resource management problem in the edge server, and make the optimal offloading decision for minimizing system cost, including energy consumption and computing time delay. We call this method OD-SARSA (offloading decision-based SARSA). We compared our proposed method with reinforcement learning based Q learning (RL-QL), and it is concluded that the performance of the former is superior to that of the latter.https://ieeexplore.ieee.org/document/9039672/Mobile devicesedge computingmobile edge computingedge cloud computingvirtual machinesaccess points |
| spellingShingle | Taha Alfakih Mohammad Mehedi Hassan Abdu Gumaei Claudio Savaglio Giancarlo Fortino Task Offloading and Resource Allocation for Mobile Edge Computing by Deep Reinforcement Learning Based on SARSA IEEE Access Mobile devices edge computing mobile edge computing edge cloud computing virtual machines access points |
| title | Task Offloading and Resource Allocation for Mobile Edge Computing by Deep Reinforcement Learning Based on SARSA |
| title_full | Task Offloading and Resource Allocation for Mobile Edge Computing by Deep Reinforcement Learning Based on SARSA |
| title_fullStr | Task Offloading and Resource Allocation for Mobile Edge Computing by Deep Reinforcement Learning Based on SARSA |
| title_full_unstemmed | Task Offloading and Resource Allocation for Mobile Edge Computing by Deep Reinforcement Learning Based on SARSA |
| title_short | Task Offloading and Resource Allocation for Mobile Edge Computing by Deep Reinforcement Learning Based on SARSA |
| title_sort | task offloading and resource allocation for mobile edge computing by deep reinforcement learning based on sarsa |
| topic | Mobile devices edge computing mobile edge computing edge cloud computing virtual machines access points |
| url | https://ieeexplore.ieee.org/document/9039672/ |
| work_keys_str_mv | AT tahaalfakih taskoffloadingandresourceallocationformobileedgecomputingbydeepreinforcementlearningbasedonsarsa AT mohammadmehedihassan taskoffloadingandresourceallocationformobileedgecomputingbydeepreinforcementlearningbasedonsarsa AT abdugumaei taskoffloadingandresourceallocationformobileedgecomputingbydeepreinforcementlearningbasedonsarsa AT claudiosavaglio taskoffloadingandresourceallocationformobileedgecomputingbydeepreinforcementlearningbasedonsarsa AT giancarlofortino taskoffloadingandresourceallocationformobileedgecomputingbydeepreinforcementlearningbasedonsarsa |