Balanced-DRL: A DQN-Based Job Allocation Algorithm in BaaS
Blockchain as a Service (BaaS) combines features of cloud computing and blockchain, making blockchain applications more convenient and promising. Although current BaaS platforms have been widely adopted by both industry and academia, concerns arise regarding their performance, especially in job allo...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-06-01
|
| Series: | Mathematics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2227-7390/11/12/2638 |
| _version_ | 1797593650599821312 |
|---|---|
| author | Chaopeng Guo Ming Xu Shengqiang Hu Jie Song |
| author_facet | Chaopeng Guo Ming Xu Shengqiang Hu Jie Song |
| author_sort | Chaopeng Guo |
| collection | DOAJ |
| description | Blockchain as a Service (BaaS) combines features of cloud computing and blockchain, making blockchain applications more convenient and promising. Although current BaaS platforms have been widely adopted by both industry and academia, concerns arise regarding their performance, especially in job allocation. Existing BaaS job allocation strategies are simple and do not guarantee load balancing due to the dynamic nature and complexity of BaaS job execution. In this paper, we propose a deep reinforcement learning-based algorithm, Balanced-DRL, to learn an optimized allocation strategy in BaaS based on analyzing the execution process of BaaS jobs and a set of job scale characteristics. Following extensive experiments with generated job request workloads, the results show that Balanced-DRL significantly improves BaaS performance, achieving a 5% to 8% increase in job throughput and a 5% to 20% decrease in job latency. |
| first_indexed | 2024-03-11T02:12:22Z |
| format | Article |
| id | doaj.art-621c3aaae334403fb3fdd27fc45a1d04 |
| institution | Directory Open Access Journal |
| issn | 2227-7390 |
| language | English |
| last_indexed | 2024-03-11T02:12:22Z |
| publishDate | 2023-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Mathematics |
| spelling | doaj.art-621c3aaae334403fb3fdd27fc45a1d042023-11-18T11:27:42ZengMDPI AGMathematics2227-73902023-06-011112263810.3390/math11122638Balanced-DRL: A DQN-Based Job Allocation Algorithm in BaaSChaopeng Guo0Ming Xu1Shengqiang Hu2Jie Song3Software College, Northeastern University, Shenyang 110169, ChinaSoftware College, Northeastern University, Shenyang 110169, ChinaSoftware College, Northeastern University, Shenyang 110169, ChinaSoftware College, Northeastern University, Shenyang 110169, ChinaBlockchain as a Service (BaaS) combines features of cloud computing and blockchain, making blockchain applications more convenient and promising. Although current BaaS platforms have been widely adopted by both industry and academia, concerns arise regarding their performance, especially in job allocation. Existing BaaS job allocation strategies are simple and do not guarantee load balancing due to the dynamic nature and complexity of BaaS job execution. In this paper, we propose a deep reinforcement learning-based algorithm, Balanced-DRL, to learn an optimized allocation strategy in BaaS based on analyzing the execution process of BaaS jobs and a set of job scale characteristics. Following extensive experiments with generated job request workloads, the results show that Balanced-DRL significantly improves BaaS performance, achieving a 5% to 8% increase in job throughput and a 5% to 20% decrease in job latency.https://www.mdpi.com/2227-7390/11/12/2638Blockchain as a Servicejob allocationload balancingdeep reinforcement learning |
| spellingShingle | Chaopeng Guo Ming Xu Shengqiang Hu Jie Song Balanced-DRL: A DQN-Based Job Allocation Algorithm in BaaS Mathematics Blockchain as a Service job allocation load balancing deep reinforcement learning |
| title | Balanced-DRL: A DQN-Based Job Allocation Algorithm in BaaS |
| title_full | Balanced-DRL: A DQN-Based Job Allocation Algorithm in BaaS |
| title_fullStr | Balanced-DRL: A DQN-Based Job Allocation Algorithm in BaaS |
| title_full_unstemmed | Balanced-DRL: A DQN-Based Job Allocation Algorithm in BaaS |
| title_short | Balanced-DRL: A DQN-Based Job Allocation Algorithm in BaaS |
| title_sort | balanced drl a dqn based job allocation algorithm in baas |
| topic | Blockchain as a Service job allocation load balancing deep reinforcement learning |
| url | https://www.mdpi.com/2227-7390/11/12/2638 |
| work_keys_str_mv | AT chaopengguo balanceddrladqnbasedjoballocationalgorithminbaas AT mingxu balanceddrladqnbasedjoballocationalgorithminbaas AT shengqianghu balanceddrladqnbasedjoballocationalgorithminbaas AT jiesong balanceddrladqnbasedjoballocationalgorithminbaas |