Distributed reinforcement learning-based memory allocation for edge-PLCs in industrial IoT
Abstract The exponential device growth in industrial Internet of things (IIoT) has a noticeable impact on the volume of data generated. Edge-cloud computing cooperation has been introduced to the IIoT to lessen the computational load on cloud servers and shorten the processing time for data. General...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2022-10-01
|
| Series: | Journal of Cloud Computing: Advances, Systems and Applications |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s13677-022-00348-9 |
| _version_ | 1811335252777369600 |
|---|---|
| author | Tingting Fu Yanjun Peng Peng Liu Haksrun Lao Shaohua Wan |
| author_facet | Tingting Fu Yanjun Peng Peng Liu Haksrun Lao Shaohua Wan |
| author_sort | Tingting Fu |
| collection | DOAJ |
| description | Abstract The exponential device growth in industrial Internet of things (IIoT) has a noticeable impact on the volume of data generated. Edge-cloud computing cooperation has been introduced to the IIoT to lessen the computational load on cloud servers and shorten the processing time for data. General programmable logic controllers (PLCs), which have been playing important roles in industrial control systems, start to gain the ability to process a large amount of industrial data and share the workload of cloud servers. This transforms them into edge-PLCs. However, the continuous influx of multiple types of concurrent production data streams against the limited capacity of built-in memory in PLCs brings a huge challenge. Therefore, the ability to reasonably allocate memory resources in edge-PLCs to ensure data utilization and real-time processing has become one of the core means of improving the efficiency of industrial processes. In this paper, to tackle dynamic changes in arrival data rate over time at each edge-PLC, we propose to optimize memory allocation with Q-learning distributedly. The simulation experiments verify that the method can effectively reduce the data loss probability while improving the system performance. |
| first_indexed | 2024-04-13T17:21:28Z |
| format | Article |
| id | doaj.art-617c79bef9dc477398bba2578d7d71d2 |
| institution | Directory Open Access Journal |
| issn | 2192-113X |
| language | English |
| last_indexed | 2024-04-13T17:21:28Z |
| publishDate | 2022-10-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Journal of Cloud Computing: Advances, Systems and Applications |
| spelling | doaj.art-617c79bef9dc477398bba2578d7d71d22022-12-22T02:37:57ZengSpringerOpenJournal of Cloud Computing: Advances, Systems and Applications2192-113X2022-10-0111111410.1186/s13677-022-00348-9Distributed reinforcement learning-based memory allocation for edge-PLCs in industrial IoTTingting Fu0Yanjun Peng1Peng Liu2Haksrun Lao3Shaohua Wan4School of Computer Science and Technology, Hangzhou Dianzi UniversitySchool of Computer Science and Technology, Hangzhou Dianzi UniversitySchool of Computer Science and Technology, Hangzhou Dianzi UniversityCenter of Engineering and Design, Chhong Cheng Chinese SchoolShenzhen Institute for Advanced Study, University of Electronic Science and Technology of ChinaAbstract The exponential device growth in industrial Internet of things (IIoT) has a noticeable impact on the volume of data generated. Edge-cloud computing cooperation has been introduced to the IIoT to lessen the computational load on cloud servers and shorten the processing time for data. General programmable logic controllers (PLCs), which have been playing important roles in industrial control systems, start to gain the ability to process a large amount of industrial data and share the workload of cloud servers. This transforms them into edge-PLCs. However, the continuous influx of multiple types of concurrent production data streams against the limited capacity of built-in memory in PLCs brings a huge challenge. Therefore, the ability to reasonably allocate memory resources in edge-PLCs to ensure data utilization and real-time processing has become one of the core means of improving the efficiency of industrial processes. In this paper, to tackle dynamic changes in arrival data rate over time at each edge-PLC, we propose to optimize memory allocation with Q-learning distributedly. The simulation experiments verify that the method can effectively reduce the data loss probability while improving the system performance.https://doi.org/10.1186/s13677-022-00348-9Industrial internet of thingsEdge-PLCResource allocationQ-learning |
| spellingShingle | Tingting Fu Yanjun Peng Peng Liu Haksrun Lao Shaohua Wan Distributed reinforcement learning-based memory allocation for edge-PLCs in industrial IoT Journal of Cloud Computing: Advances, Systems and Applications Industrial internet of things Edge-PLC Resource allocation Q-learning |
| title | Distributed reinforcement learning-based memory allocation for edge-PLCs in industrial IoT |
| title_full | Distributed reinforcement learning-based memory allocation for edge-PLCs in industrial IoT |
| title_fullStr | Distributed reinforcement learning-based memory allocation for edge-PLCs in industrial IoT |
| title_full_unstemmed | Distributed reinforcement learning-based memory allocation for edge-PLCs in industrial IoT |
| title_short | Distributed reinforcement learning-based memory allocation for edge-PLCs in industrial IoT |
| title_sort | distributed reinforcement learning based memory allocation for edge plcs in industrial iot |
| topic | Industrial internet of things Edge-PLC Resource allocation Q-learning |
| url | https://doi.org/10.1186/s13677-022-00348-9 |
| work_keys_str_mv | AT tingtingfu distributedreinforcementlearningbasedmemoryallocationforedgeplcsinindustrialiot AT yanjunpeng distributedreinforcementlearningbasedmemoryallocationforedgeplcsinindustrialiot AT pengliu distributedreinforcementlearningbasedmemoryallocationforedgeplcsinindustrialiot AT haksrunlao distributedreinforcementlearningbasedmemoryallocationforedgeplcsinindustrialiot AT shaohuawan distributedreinforcementlearningbasedmemoryallocationforedgeplcsinindustrialiot |