Multi-Agent Systems for Collaborative Inference Based on Deep Policy Q-Inference Network

doi:10.1007/s10723-024-09750-w

CSpace

	Multi-Agent Systems for Collaborative Inference Based on Deep Policy Q-Inference Network
	Wang, Shangshang 1; Jing, Yuqin 2; Wang, Kezhu 3; Wang, Xue 4,5
	2024-03
发表期刊	JOURNAL OF GRID COMPUTING
ISSN	1570-7873
卷号	22 期号:1
摘要	This study tackles the problem of increasing efficiency and scalability in deep neural network (DNN) systems by employing collaborative inference, an approach that is gaining popularity because to its ability to maximize computational resources. It involves splitting a pre-trained DNN model into two parts and running them separately on user equipment (UE) and edge servers. This approach is advantageous because it results in faster and more energy-efficient inference, as computation can be offloaded to edge servers rather than relying solely on UEs. However, a significant challenge of collaborative belief is the dynamic coupling of DNN layers, which makes it difficult to separate and run the layers independently. To address this challenge, we proposed a novel approach to optimize collaborative inference in a multi-agent scenario where a single-edge server coordinates the assumption of multiple UEs. Our proposed method suggests using an autoencoder-based technique to reduce the size of intermediary features and constructing tasks using the deep policy inference Q-inference network's overhead (DPIQN). To optimize the collaborative inference, employ the Deep Recurrent Policy Inference Q-Network (DRPIQN) technique, which allows for a hybrid action space. The results of the tests demonstrate that this approach can significantly reduce inference latency by up to 56% and energy usage by up to 72% on various networks. Overall, this proposed approach provides an efficient and effective method for implementing collaborative inference in multi-agent scenarios, which could have significant implications for developing DNN systems.
关键词	Deep Reinforcement Learning Mobile Edge Computing Multi-user Collaborative inference Hybrid action space
DOI	10.1007/s10723-024-09750-w
收录类别	SCIE
语种	英语
WOS研究方向	Computer Science
WOS类目	Computer Science, Information Systems ; Computer Science, Theory & Methods
WOS记录号	WOS:001171784300001
出版者	SPRINGER
原始文献类型	Article
EISSN	1572-9184
引用统计	被引频次：1[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://ir.library.ouchn.edu.cn/handle/39V7QQFX/169786
专题	国家开放大学
通讯作者	Wang, Xue
作者单位	1.Peoples Friendship Univ Russia, Acad Engn, Fundamental Informat & Informat Technol, Moscow 117198, Russia; 2.Chongqing Open Univ, Coll Elect & Informat Engn, Chongqing 400052, Peoples R China; 3.Luan Vocat & Tech Coll, Dept Business Adm, Anhui 2370000, Peoples R China; 4.Nanjing Normal Univ, Sch Educ Sci, Nanjing 210097, Jiangsu, Peoples R China; 5.Nanjing Audit Univ, Smart Campus Management Off, Nanjing 211815, Jiangsu, Peoples R China
推荐引用方式 GB/T 7714	Wang, Shangshang,Jing, Yuqin,Wang, Kezhu,et al. Multi-Agent Systems for Collaborative Inference Based on Deep Policy Q-Inference Network[J]. JOURNAL OF GRID COMPUTING,2024,22(1).
APA	Wang, Shangshang,Jing, Yuqin,Wang, Kezhu,&Wang, Xue.(2024).Multi-Agent Systems for Collaborative Inference Based on Deep Policy Q-Inference Network.JOURNAL OF GRID COMPUTING,22(1).
MLA	Wang, Shangshang,et al."Multi-Agent Systems for Collaborative Inference Based on Deep Policy Q-Inference Network".JOURNAL OF GRID COMPUTING 22.1(2024).