Research on resource allocation algorithm of centralized and distributed Q-learning in machine communication
Under the premise of ensuring partial machine type communication device (MTCD)’s quality of service (QoS) requirements, the resource allocation problem was studied with the goal of maximizing system throughput in the massive machine type communication (mMTC) scenario.Two resource allocation algorith...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | zho |
| Published: |
Beijing Xintong Media Co., Ltd
2021-11-01
|
| Series: | Dianxin kexue |
| Subjects: | |
| Online Access: | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2021244/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850072459200430080 |
|---|---|
| author | Yunhe YU Jun SUN |
| author_facet | Yunhe YU Jun SUN |
| author_sort | Yunhe YU |
| collection | DOAJ |
| description | Under the premise of ensuring partial machine type communication device (MTCD)’s quality of service (QoS) requirements, the resource allocation problem was studied with the goal of maximizing system throughput in the massive machine type communication (mMTC) scenario.Two resource allocation algorithms based on Q-learning were proposed: centralized Q-learning algorithm (team-Q) and distributed Q-learning algorithm (dis-Q).Firstly, taking into account MTCD’s geographic location and multi-level QoS requirements, a clustering algorithm based on cosine similarity (CS) was designed.In the clustering algorithm, multi-dimensional vectors that represent MTCD and data aggregator (DA) were constructed, and MTCDs can be grouped according to the CS value between multi-dimensional vectors.Then in the MTC network, the team-Q learning algorithm and dis-Q learning algorithm were used to allocate resource blocks and power for the MTCD.In terms of throughput performance, team-Q and dis-Q algorithms have an average increase of 16% and 23% compared to the dynamic resource allocation algorithm and the greedy algorithm, respectively.In terms of complexity performance, the dis-Q algorithm is only 25% of team-Q algorithm and even below, the convergence speed is increased by nearly 40%. |
| format | Article |
| id | doaj-art-e7567b988275454284088d6adb09cea1 |
| institution | DOAJ |
| issn | 1000-0801 |
| language | zho |
| publishDate | 2021-11-01 |
| publisher | Beijing Xintong Media Co., Ltd |
| record_format | Article |
| series | Dianxin kexue |
| spelling | doaj-art-e7567b988275454284088d6adb09cea12025-08-20T02:47:04ZzhoBeijing Xintong Media Co., LtdDianxin kexue1000-08012021-11-0137415059815767Research on resource allocation algorithm of centralized and distributed Q-learning in machine communicationYunhe YUJun SUNUnder the premise of ensuring partial machine type communication device (MTCD)’s quality of service (QoS) requirements, the resource allocation problem was studied with the goal of maximizing system throughput in the massive machine type communication (mMTC) scenario.Two resource allocation algorithms based on Q-learning were proposed: centralized Q-learning algorithm (team-Q) and distributed Q-learning algorithm (dis-Q).Firstly, taking into account MTCD’s geographic location and multi-level QoS requirements, a clustering algorithm based on cosine similarity (CS) was designed.In the clustering algorithm, multi-dimensional vectors that represent MTCD and data aggregator (DA) were constructed, and MTCDs can be grouped according to the CS value between multi-dimensional vectors.Then in the MTC network, the team-Q learning algorithm and dis-Q learning algorithm were used to allocate resource blocks and power for the MTCD.In terms of throughput performance, team-Q and dis-Q algorithms have an average increase of 16% and 23% compared to the dynamic resource allocation algorithm and the greedy algorithm, respectively.In terms of complexity performance, the dis-Q algorithm is only 25% of team-Q algorithm and even below, the convergence speed is increased by nearly 40%.http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2021244/resource allocationcentralized Q-learningdistributed Q-learningconsine similaritymulti-dimensional vector |
| spellingShingle | Yunhe YU Jun SUN Research on resource allocation algorithm of centralized and distributed Q-learning in machine communication Dianxin kexue resource allocation centralized Q-learning distributed Q-learning consine similarity multi-dimensional vector |
| title | Research on resource allocation algorithm of centralized and distributed Q-learning in machine communication |
| title_full | Research on resource allocation algorithm of centralized and distributed Q-learning in machine communication |
| title_fullStr | Research on resource allocation algorithm of centralized and distributed Q-learning in machine communication |
| title_full_unstemmed | Research on resource allocation algorithm of centralized and distributed Q-learning in machine communication |
| title_short | Research on resource allocation algorithm of centralized and distributed Q-learning in machine communication |
| title_sort | research on resource allocation algorithm of centralized and distributed q learning in machine communication |
| topic | resource allocation centralized Q-learning distributed Q-learning consine similarity multi-dimensional vector |
| url | http://www.telecomsci.com/zh/article/doi/10.11959/j.issn.1000-0801.2021244/ |
| work_keys_str_mv | AT yunheyu researchonresourceallocationalgorithmofcentralizedanddistributedqlearninginmachinecommunication AT junsun researchonresourceallocationalgorithmofcentralizedanddistributedqlearninginmachinecommunication |