AoI-Aware Resource Scheduling for Industrial IoT with Deep Reinforcement Learning
Effective resource scheduling methods in certain scenarios of Industrial Internet of Things are pivotal. In time-sensitive scenarios, Age of Information is a critical indicator for measuring the freshness of data. This paper considers a densely deployed time-sensitive Industrial Internet of Things s...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-03-01
|
| Series: | Electronics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2079-9292/13/6/1104 |
| _version_ | 1797241309058039808 |
|---|---|
| author | Hongzhi Li Lin Tang Shengwei Chen Libin Zheng Shaohong Zhong |
| author_facet | Hongzhi Li Lin Tang Shengwei Chen Libin Zheng Shaohong Zhong |
| author_sort | Hongzhi Li |
| collection | DOAJ |
| description | Effective resource scheduling methods in certain scenarios of Industrial Internet of Things are pivotal. In time-sensitive scenarios, Age of Information is a critical indicator for measuring the freshness of data. This paper considers a densely deployed time-sensitive Industrial Internet of Things scenario. The industrial wireless device transmits data packets to the base station with limited channel resources under the constraints of Age of Information. It is assumed that each device has the capacity to store the packets it generates. The device will discard the data to alleviate the data queue backlog when the Age of Information of the data packet exceeds the threshold. We developed a new system utility equation to represent the scheduling problem and the problem is expressed as a trade-off between minimizing the average Age of Information and maximizing network throughput. Inspired by the success of reinforcement learning in decision-processing problems, we attempt to obtain an optimal scheduling strategy via deep reinforcement learning. In addition, a reward function is constructed to enable the agent to achieve improved convergence results. Compared with the baseline, our proposed algorithm can achieve better system utility and lower Age of Information violation rate. |
| first_indexed | 2024-04-24T18:21:16Z |
| format | Article |
| id | doaj.art-6930b74b25ae438288c10dd2c3741b69 |
| institution | Directory Open Access Journal |
| issn | 2079-9292 |
| language | English |
| last_indexed | 2024-04-24T18:21:16Z |
| publishDate | 2024-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Electronics |
| spelling | doaj.art-6930b74b25ae438288c10dd2c3741b692024-03-27T13:35:00ZengMDPI AGElectronics2079-92922024-03-01136110410.3390/electronics13061104AoI-Aware Resource Scheduling for Industrial IoT with Deep Reinforcement LearningHongzhi Li0Lin Tang1Shengwei Chen2Libin Zheng3Shaohong Zhong4School of Computer and Information Engineering, Central South University of Forestry and Technology, Changsha 410004, ChinaSchool of Computer and Information Engineering, Central South University of Forestry and Technology, Changsha 410004, ChinaSchool of Computer and Information Engineering, Central South University of Forestry and Technology, Changsha 410004, ChinaSchool of Computer and Information Engineering, Central South University of Forestry and Technology, Changsha 410004, ChinaSchool of Computer and Information Engineering, Central South University of Forestry and Technology, Changsha 410004, ChinaEffective resource scheduling methods in certain scenarios of Industrial Internet of Things are pivotal. In time-sensitive scenarios, Age of Information is a critical indicator for measuring the freshness of data. This paper considers a densely deployed time-sensitive Industrial Internet of Things scenario. The industrial wireless device transmits data packets to the base station with limited channel resources under the constraints of Age of Information. It is assumed that each device has the capacity to store the packets it generates. The device will discard the data to alleviate the data queue backlog when the Age of Information of the data packet exceeds the threshold. We developed a new system utility equation to represent the scheduling problem and the problem is expressed as a trade-off between minimizing the average Age of Information and maximizing network throughput. Inspired by the success of reinforcement learning in decision-processing problems, we attempt to obtain an optimal scheduling strategy via deep reinforcement learning. In addition, a reward function is constructed to enable the agent to achieve improved convergence results. Compared with the baseline, our proposed algorithm can achieve better system utility and lower Age of Information violation rate.https://www.mdpi.com/2079-9292/13/6/1104Age of Informationresource schedulingIndustrial Internet of Thingsdeep reinforcement learning |
| spellingShingle | Hongzhi Li Lin Tang Shengwei Chen Libin Zheng Shaohong Zhong AoI-Aware Resource Scheduling for Industrial IoT with Deep Reinforcement Learning Electronics Age of Information resource scheduling Industrial Internet of Things deep reinforcement learning |
| title | AoI-Aware Resource Scheduling for Industrial IoT with Deep Reinforcement Learning |
| title_full | AoI-Aware Resource Scheduling for Industrial IoT with Deep Reinforcement Learning |
| title_fullStr | AoI-Aware Resource Scheduling for Industrial IoT with Deep Reinforcement Learning |
| title_full_unstemmed | AoI-Aware Resource Scheduling for Industrial IoT with Deep Reinforcement Learning |
| title_short | AoI-Aware Resource Scheduling for Industrial IoT with Deep Reinforcement Learning |
| title_sort | aoi aware resource scheduling for industrial iot with deep reinforcement learning |
| topic | Age of Information resource scheduling Industrial Internet of Things deep reinforcement learning |
| url | https://www.mdpi.com/2079-9292/13/6/1104 |
| work_keys_str_mv | AT hongzhili aoiawareresourceschedulingforindustrialiotwithdeepreinforcementlearning AT lintang aoiawareresourceschedulingforindustrialiotwithdeepreinforcementlearning AT shengweichen aoiawareresourceschedulingforindustrialiotwithdeepreinforcementlearning AT libinzheng aoiawareresourceschedulingforindustrialiotwithdeepreinforcementlearning AT shaohongzhong aoiawareresourceschedulingforindustrialiotwithdeepreinforcementlearning |