A Real-World-Oriented Multi-Task Allocation Approach Based on Multi-Agent Reinforcement Learning in Mobile Crowd Sensing
Mobile crowd sensing is an innovative and promising paradigm in the construction and perception of smart cities. However, multi-task allocation in real-world scenarios is a huge challenge. There are many unexpected factors in the execution of mobile crowd sensing tasks, such as traffic jams or accid...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-02-01
|
| Series: | Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2078-2489/11/2/101 |
| _version_ | 1811290728321515520 |
|---|---|
| author | Junying Han Zhenyu Zhang Xiaohong Wu |
| author_facet | Junying Han Zhenyu Zhang Xiaohong Wu |
| author_sort | Junying Han |
| collection | DOAJ |
| description | Mobile crowd sensing is an innovative and promising paradigm in the construction and perception of smart cities. However, multi-task allocation in real-world scenarios is a huge challenge. There are many unexpected factors in the execution of mobile crowd sensing tasks, such as traffic jams or accidents, that make participants unable to reach the target area. In addition, participants may quit halfway due to equipment failure, network paralysis, dishonest behavior, etc. Previous task allocation approaches mainly ignored some of the heterogeneity of participants and tasks in the real-world scenarios. This paper proposes a real-world-oriented multi-task allocation approach based on multi-agent reinforcement learning. Firstly, under the premise of fully considering the heterogeneity of participants and tasks, the approach enables participants as agents to learn multiple solutions independently, based on modified soft Q-learning. Secondly, two cooperation mechanisms are proposed for obtaining the stable joint action, which can minimize the total sensing time while meeting the sensing quality constraint, which optimizes the sensing quality of mobile crowd sensing (MCS) tasks. Experiments verify that the approach can effectively reduce the impact of emergencies on the efficiency of large-scale MCS platform and outperform baselines based on a real-world dataset under different experiment settings. |
| first_indexed | 2024-04-13T04:17:45Z |
| format | Article |
| id | doaj.art-a57ca9b64a054ab38623d8866a452714 |
| institution | Directory Open Access Journal |
| issn | 2078-2489 |
| language | English |
| last_indexed | 2024-04-13T04:17:45Z |
| publishDate | 2020-02-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Information |
| spelling | doaj.art-a57ca9b64a054ab38623d8866a4527142022-12-22T03:02:56ZengMDPI AGInformation2078-24892020-02-0111210110.3390/info11020101info11020101A Real-World-Oriented Multi-Task Allocation Approach Based on Multi-Agent Reinforcement Learning in Mobile Crowd SensingJunying Han0Zhenyu Zhang1Xiaohong Wu2College of Information Science and Engineering, Xinjiang University, Urumqi 830046, ChinaCollege of Information Science and Engineering, Xinjiang University, Urumqi 830046, ChinaCollege of Information Science and Engineering, Xinjiang University, Urumqi 830046, ChinaMobile crowd sensing is an innovative and promising paradigm in the construction and perception of smart cities. However, multi-task allocation in real-world scenarios is a huge challenge. There are many unexpected factors in the execution of mobile crowd sensing tasks, such as traffic jams or accidents, that make participants unable to reach the target area. In addition, participants may quit halfway due to equipment failure, network paralysis, dishonest behavior, etc. Previous task allocation approaches mainly ignored some of the heterogeneity of participants and tasks in the real-world scenarios. This paper proposes a real-world-oriented multi-task allocation approach based on multi-agent reinforcement learning. Firstly, under the premise of fully considering the heterogeneity of participants and tasks, the approach enables participants as agents to learn multiple solutions independently, based on modified soft Q-learning. Secondly, two cooperation mechanisms are proposed for obtaining the stable joint action, which can minimize the total sensing time while meeting the sensing quality constraint, which optimizes the sensing quality of mobile crowd sensing (MCS) tasks. Experiments verify that the approach can effectively reduce the impact of emergencies on the efficiency of large-scale MCS platform and outperform baselines based on a real-world dataset under different experiment settings.https://www.mdpi.com/2078-2489/11/2/101mobile crowd sensingmulti-task allocationmulti-agent reinforcement learningreal-world-oriented |
| spellingShingle | Junying Han Zhenyu Zhang Xiaohong Wu A Real-World-Oriented Multi-Task Allocation Approach Based on Multi-Agent Reinforcement Learning in Mobile Crowd Sensing Information mobile crowd sensing multi-task allocation multi-agent reinforcement learning real-world-oriented |
| title | A Real-World-Oriented Multi-Task Allocation Approach Based on Multi-Agent Reinforcement Learning in Mobile Crowd Sensing |
| title_full | A Real-World-Oriented Multi-Task Allocation Approach Based on Multi-Agent Reinforcement Learning in Mobile Crowd Sensing |
| title_fullStr | A Real-World-Oriented Multi-Task Allocation Approach Based on Multi-Agent Reinforcement Learning in Mobile Crowd Sensing |
| title_full_unstemmed | A Real-World-Oriented Multi-Task Allocation Approach Based on Multi-Agent Reinforcement Learning in Mobile Crowd Sensing |
| title_short | A Real-World-Oriented Multi-Task Allocation Approach Based on Multi-Agent Reinforcement Learning in Mobile Crowd Sensing |
| title_sort | real world oriented multi task allocation approach based on multi agent reinforcement learning in mobile crowd sensing |
| topic | mobile crowd sensing multi-task allocation multi-agent reinforcement learning real-world-oriented |
| url | https://www.mdpi.com/2078-2489/11/2/101 |
| work_keys_str_mv | AT junyinghan arealworldorientedmultitaskallocationapproachbasedonmultiagentreinforcementlearninginmobilecrowdsensing AT zhenyuzhang arealworldorientedmultitaskallocationapproachbasedonmultiagentreinforcementlearninginmobilecrowdsensing AT xiaohongwu arealworldorientedmultitaskallocationapproachbasedonmultiagentreinforcementlearninginmobilecrowdsensing AT junyinghan realworldorientedmultitaskallocationapproachbasedonmultiagentreinforcementlearninginmobilecrowdsensing AT zhenyuzhang realworldorientedmultitaskallocationapproachbasedonmultiagentreinforcementlearninginmobilecrowdsensing AT xiaohongwu realworldorientedmultitaskallocationapproachbasedonmultiagentreinforcementlearninginmobilecrowdsensing |