Distributed Multi-Cloud Multi-Access Edge Computing by Multi-Agent Reinforcement Learning
The DOI matches its Crossref record; 44 of the 44 references it cites were found in a registry or an index.
Abstract
In this paper, we consider a three-layer distributed multi-access edge computing (MEC) network where multiple clouds, MEC servers, and edge devices (EDs) are deployed at the top layer, middle layer, and bottom layer, respectively. Each cloud center (CC) is associated with an independent service provider and publishes an application-driven computing task. To deliver the tasks, CCs rely on EDs to generate the raw data and offload part of the computing tasks to both EDs and MEC servers such that their computing and transmission resources can be fully utilized to reduce the system latency. However, in such a three-layer network, the distributed deployment of tasks leads to inevitable resource competition among CCs. To address this issue, we propose a distributed scheme based on multi-agent reinforcement learning, where each CC jointly determines the task offloading and resource allocation strategy based on its inference of other CCs’ decisions. Simulation results indicate that a lower system latency is achieved via our proposed scheme compared with the existing schemes. In addition, the influence of the number of CCs, MEC servers, and EDs on latency performance is also discussed.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Besides, a multi-agent RL approach was developed in [260] to solve the distributed mixed combinatorial optimization problem for task offloading and resource allocation in multi-layer edge inference systems.”
From Edge artificial intelligence for 6g: vision, enabling technologies, and applications (2022) · cites this paper as [260]
Citations
Cites
Fundamentals of Wireless Communication
Tse, D., & Viswanath, P. (2005) · doi:10.1017/cbo9780511807213 · Cited by 13,162 · cited 1×
“Note that the orthogonal resources, e.g., spectrum and time resources, are considered as the wireless transmission resources in this paper which influence the wireless data rate in a linear manner [34].”
BackgroundArmbrust, M., Fox, A., Griffith, R., Joseph, A. D., Katz, R., Konwinski, A., Lee, G., Patterson, D., Rabkin, A., Stoica, I., et al. (2010) · Communications of the ACM · doi:10.1145/1721654.1721672 · Cited by 9,464 · cited 1×
“These applications are generally processed in the remote cloud centers (CCs), such as Amazon EC2, which is called cloud computing [4]–[6].”
BackgroundWatkins, C. J. C. H., & Dayan, P. (1992) · Machine Learning · doi:10.1007/bf00992698 · Cited by 9,083
Reinforcement Learning: A Survey
Kaelbling, L. P., Littman, M. L., & Moore, A. W. (1996) · Journal of Artificial Intelligence Research · doi:10.1613/jair.301 · Cited by 8,972 · cited 1×
“…task offloading [27], [28] scheme for MEC systems under a stochastic and dynamic environment, several initial works have considered reinforcement learning (RL) as a promising technique since it takes the future feedback from the environment into account, thereby achieving a long-term goal [29].”
BackgroundA Survey on Mobile Edge Computing: The Communication Perspective
Mao, Y., You, C., Zhang, J., Huang, K., & Letaief, K. B. (2017) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2017.2745201 · Cited by 5,607 · cited 1×
“…with the issue and support more access modes including wired and wireless access in heterogeneous networks [11], [12], the concept of multi-access edge computing (MEC) has been proposed to enable the computing tasks to be offloaded to MEC servers which are deployed between the EDs and CCs [13]–[15].”
BackgroundMobile Edge Computing: A Survey on Architecture and Computation Offloading
Mach, P., & Becvar, Z. (2017) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2017.2682318 · Cited by 3,258 · cited 1×
“To cope with the issue and support more access modes including wired and wireless access in heterogeneous networks [11], [12], the concept of multi-access edge computing (MEC) has been proposed to enable the computing tasks to be offloaded to MEC servers which are deployed between the EDs and CCs [13]–[15].”
BackgroundEfficient multi-user computation offloading for mobile-edge cloud computing
Chen, X., Jiao, L., Li, W., & Fu, X. (2016) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2015.2487344 · Cited by 2,675 · cited 2×
“In the literature, existing works have studied the task offloading problem either in a two-layer ED-MEC network [16]–[22], or in the three-layer ED-MEC-CC network with a single CC [23]–[25].”
BackgroundMethodA survey of mobile cloud computing: architecture, applications, and approaches
Dinh, H. T., Lee, C., Niyato, D., & Wang, P. (2013) · Wireless Communications and Mobile Computing · doi:10.1002/wcm.1203 · Cited by 2,391 · cited 1×
“These applications are generally processed in the remote cloud centers (CCs), such as Amazon EC2, which is called cloud computing [4]–[6].”
BackgroundTaleb, T., Samdanis, K., Mada, B., Flinck, H., Dutta, S., & Sabella, D. (2017) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2017.2705720 · Cited by 1,775 · cited 1×
“To cope with the issue and support more access modes including wired and wireless access in heterogeneous networks [11], [12], the concept of multi-access edge computing (MEC) has been proposed to enable the computing tasks to be offloaded to MEC servers which are deployed between the EDs and CCs…”
BackgroundThe dynamics of reinforcement learning in cooperative multiagent systems
Claus, C., & Boutilier, C. E. (1998) · National Conference on Artificial Intelligence · Cited by 1,463
Cited by
Edge artificial intelligence for 6g: vision, enabling technologies, and applications
Letaief, K. B., Shi, Y., Lu, J., & Lu, J. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3126076 · Cited by 829
Alam, M., & Jamalipour, A. (2022) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2022.3160099 · Cited by 150
Blockchain-Empowered Collaborative Task Offloading for Cloud-Edge-Device Computing
Yao, S. F., Wang, M., Qu, Q., Zhang, Z., Zhang, Y.-F., Xu, K., & Xu, M. (2022) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2022.3213358 · Cited by 72
Self-citationLiu, Q., Zhang, H., Zhang, X., & Yuan, D. (2024) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2024.3430486 · Cited by 61
“Most of works tackle this problem by optimizing the communication and computing resources to reduce delay and energy consumption [6], [7], [8], [9].”
BackgroundSuzuki, A., Kobayashi, M., & Oki, E. (2023) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2023.3267809 · Cited by 57
“Several studies have addressed task-offloading problems for CC and EC [1], [2], [3], [4], [5], [6], [7], [8].”
BackgroundMethodInfluentialOn Joint Offloading and Resource Allocation: A Double Deep Q-Network Approach
Khoramnejad, F., & Erol‐Kantarci, M. (2021) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2021.3116251 · Cited by 53
Chen, Y., Sun, Y., Yu, H., & Taleb, T. (2024) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2024.3375374 · Cited by 55
“Therefore, we compare the value-based MADRL methods that enable each user to decide their task allocation, as proposed in many previous works [8], [17], [51].”
BackgroundMethodInfluentialDai, M., Huang, N., Wu, Y., Qian, L., Lin, B., Su, Z., & Lu, R. (2023) · IEEE Transactions on Communications · doi:10.1109/tcomm.2023.3306581 · Cited by 45
“In [36], Zhang et al. proposed a three-layer distributed multi-access edge computing network to reduce the task processing latency.”
BackgroundMulti-Agent Reinforcement Learning for Task Offloading in Crowd-Edge Computing
Yao, S. F., Wang, M., Ren, J., Xia, T., Wang, W., Xu, K., Xu, M., & Zhang, H. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3531793 · Cited by 54
“Unlike the above methods [30], [31] that only consider the task offloading to Cloud or edge servers, our solutions are designedforcrowd-edgewithheterogeneousresourcecapacities andcomplexsystemenvironments.”
Zeng, C., Wang, X., Zeng, R., Li, Y., Shi, J., & Huang, M. (2024) · Future Generation Computer Systems · doi:10.1016/j.future.2024.01.025 · Cited by 46
Joint Resource Overbooking and Container Scheduling in Edge Computing
Tang, Z., Mou, F., Lou, J., Weijia Jia, B., Wu, Y., & Zhao, W. (2024) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2024.3386936 · Cited by 43
“This issue could be mitigated by employing multi-agent RL, i.e., deploying a decision-making agent at each edge node [56].”
Chen, J., Chen, P., Niu, X., Wu, Z., Xiong, L., & Shi, C. (2022) · Journal of Cloud Computing Advances Systems and Applications · doi:10.1186/s13677-022-00372-9 · Cited by 42
“Zhang et al. [16] considered a three-layer distributed multi-cloud multi-access edge, and proposed a multi-agent reinforcement learning to make task offloading and resource allocation strategy.”
BackgroundDistributed Intelligence in Wireless Networks
Liu, X., Yu, J., Liu, Y., Gao, Y., Mahmoodi, T., Lambotharan, S., & Tsang, D. H. K. (2023) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2023.3265425 · Cited by 48
“In [134], each Cloud Center (CC) is considered as an agent, where each CC determines the task offloading strategy independently by learning explicit models of other CCs as stationary distributions over their actions.”
MethodDistributed resource scheduling in edge computing: Problems, solutions, and opportunities
Sahni, Y., Cao, J., Yang, L., & Wang, S. (2022) · Computer Networks · doi:10.1016/j.comnet.2022.109430 · Cited by 38
Reinforcement learning based tasks offloading in vehicular edge computing networks
Cao, S., Liu, D., Dai, C., Wang, C. C. Q., Yang, Y., Zhang, W., & Zheng, D. (2023) · Computer Networks · doi:10.1016/j.comnet.2023.109894 · Cited by 44
Efficient Microservice Deployment in Kubernetes Multi-Clusters through Reinforcement Learning
Santos, J., Zaccarini, M., Poltronieri, F., Tortonesi, M., Sleianelli, C., Cicco, N. D., & Turck, F. D. (2024) · IEEE/IFIP Network Operations and Management Symposium (NOMS) · doi:10.1109/noms59830.2024.10575912 · Cited by 44
“RL algorithms have been proposed in recent years as an alternative to current heuristics [21]–[23].”
MethodZhou, H., Long, Y., Gong, S., Zhu, K., Hoang, D. T., & Niyato, D. T. (2022) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2022.3202525 · Cited by 35
“As the MEC servers are usually co-located with the base stations or access points (APs) [9], the MEC servers’ resource allocation needs to be jointly optimized with the APs’ transmit control, e.g., power allocation or beamforming optimization.”
BackgroundSantos, J., Zaccarini, M., Poltronieri, F., Tortonesi, M., Stefanelli, C., Cicco, N. D., & Turck, F. D. (2025) · Future Generation Computer Systems · doi:10.1016/j.future.2024.107680 · Cited by 30
5G‐based smart healthcare system designing and field trial in hospitals
Tang, X., Zhao, L. L., Chong, J., You, Z., Zhu, L., Ren, H., Shang, Y., Han, Y., & Gong, L. (2021) · IET Communications · doi:10.1049/cmu2.12300 · Cited by 30
Wang, J., Zhang, M., Yin, Q., Yin, L., & Peng, Y. J. (2024) · Ad Hoc Networks · doi:10.1016/j.adhoc.2024.103671 · Cited by 29
Liu, Z., Zhao, Y., Song, J., Qiu, C., Chen, X., & Wang, X. (2021) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2021.3136942 · Cited by 27
“Multi-agent learning can be used not only in cooperative scenarios [34], [35], but also in competitive scenarios [36], [37].”
BackgroundDistributed Hybrid Task Offloading in Mobile-Edge Computing: A Potential Game Scheme
Niu, Z., Liu, H., Ge, Y., & Du, J. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3366194 · Cited by 30
“Zhang et al. [23] proposed a joint task offloading and resource allocation algorithm based on multiagent reinforcement learning for three-tier distributed multiaccess MEC networks, aiming to minimize system task execution latency.”
BackgroundDistributed Resource Optimization With Blockchain Security for Immersive Digital Twin in IIoT
Song, J., Kang, Y., Song, Q., Guo, L., & Jamalipour, A. (2022) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2022.3224986 · Cited by 29
“First, we estimate the convergence performance of the proposed FDMA-CA2C algorithm compared with those of the MA-CA2C [22], the MA-DDPG [23], and the MA-DQN [24] algorithms.”
MethodJoint Power Control and Task Offloading in Collaborative Edge–Cloud Computing Networks
Wang, S., & Gong, Y. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3264857 · Cited by 26
Deep Reinforcement Learning-Based Service-Oriented Resource Allocation in Smart Grids
Xi, L., Wang, Y., Wang, Y., Wang, Z., Wang, X., & Chen, Y. (2021) · IEEE Access · doi:10.1109/access.2021.3082259 · Cited by 24
FLoadNet: Load Balancing in Fog Networks With Cooperative Multiagent Using Actor–Critic Method
Baek, J.-Y., & Kaddoum, G. (2022) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2022.3210827 · Cited by 23
“Though distributed schemes with multiple agents were considered in [16], [17], [18], [19], [20], [21], [22], the prior studies have only considered computation offloading for server-level load balancing, and no work is done to optimize both the network and server load balancing together in fog…”
BackgroundMethodTwo Layer Stackelberg Game-Based Resource Allocation in Cloud-Network Convergence Service Computing
Lyu, T., Xu, H., Liu, F., Li, M., Li, L., & Han, Z. (2024) · IEEE Transactions on Cognitive Communications and Networking · doi:10.1109/tccn.2024.3392809 · Cited by 21
“In [21], the authors proposed a distributed resource allocation scheme based on multi-agent reinforcement learning to solve the problem of resource competition between different offloading tasks.”
Nguyen, C. T., Nguyen, D. N., Hoang, D. T., Phan, K. T., Niyato, D. T., Pham, H.-A., & Dutkiewicz, E. (2022) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2022.3213256 · Cited by 21
Liu, S., Xu, Y., Li, G., Xu, Y., Zhang, X., Gu, F., Ma, W., & Chen, T. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3366009 · Cited by 20
“In case the task needs to be offloaded, the UE sends an access request to the BS for offloading [18], [19].”
BackgroundMethodInfluentialWang, L., Hou, L., Liu, S., Han, Z., & Wu, J. (2023) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2023.3329643 · Cited by 18
“Y. Zhang et al. [18] proposed a distributed scheme based on multi-agent RL, where each cloud center jointly determines the task offloading and resource allocation strategy based on its inference of other cloud center’s decisions.”
BackgroundChen, S., Li, J., Yuan, Q., He, H., Li, S., & Yang, J. (2024) · IEEE Transactions on Parallel and Distributed Systems · doi:10.1109/tpds.2024.3467212 · Cited by 18
“In this context, some researches have attempted to develop a distributed task scheduling algorithm, where each data center makes its own scheduling decisions independently [11], [12].”
BackgroundComputing Offloading Based on TD3 Algorithm in Cache-Assisted Vehicular NOMA–MEC Networks
Zhou, T., Xu, M., Qin, D., Nie, X., Li, X., & Li, C. (2023) · Sensors · doi:10.3390/s23229064 · Cited by 16
“Compared with cloud computing (CC), which requires tasks to be uploaded to a remote cloud, MEC can provide additional computing resources for MDs within its coverage area and thus reduce their computing overhead [8–14].”
BackgroundA2C Learning for Tasks Segmentation with Cooperative Computing in Edge Computing Networks
Sun, Y., & Zhang, X. (2022) · Globecom · doi:10.1109/globecom48099.2022.10000948 · Cited by 15
“In [3], the authors designed a scheme to offload part of the computing tasks to both edge and cloud, but without coordination among ESs.”
BackgroundMulti-Agent Deep Reinforcement Learning for Cooperative Offloading in Cloud-Edge Computing
Suzuki, A., & Kobayashi, M. (2022) · International Conference on Communications · doi:10.1109/icc45855.2022.9838540 · Cited by 12
“The other is that existing studies [4]–[7] do not consider the bandwidth capacity and the backbone network topology.”
BackgroundLu, B., Huang, X., Wu, Y., Qian, L., Zhou, S., & Niyato, D. T. (2025) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2025.3528026 · Cited by 11
“Mobile edge computing (MEC) is also utilized to support computation-intensive fusion of sensing data to reduce computation delay [9], [10].”
Gao, R., Wenzhong, Z., Mao, W., Tan, J., Zhang, J., Haiyun, H., Tan, W., & Feiyue, H. (2025) · Journal of Industrial Information Integration · doi:10.1016/j.jii.2025.100776 · Cited by 12
Adil, M., Khan, M. K., Ali, A., Abulkasim, H., Farouk, A., Song, H., & Jin, Z. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3631333 · Cited by 13
“One promising approach to address this challenge is RL [13].”
Lim, D., & Joe, I. (2024) · Sensors · doi:10.3390/s24237760 · Cited by 9
“This shift has facilitated faster analysis of remote sensing data, crucial for the sustainable development of nations and cities [6–8].”
DRL-based Task and Computational Offloading for Internet of Vehicles in Decentralized Computing
Zhang, Z., Gu, K., & Xu, Z. (2024) · Journal of Grid Computing · doi:10.1007/s10723-023-09729-z · Cited by 10
“By collaborating and sharing information, the learning agents can effectively navigate the complex decision-making landscape and improve network performance in high-mobility environments [9].”
Hu, S., Luo, Q., Li, G., Shi, W., & Ye, B. (2023) · Journal of Computer Science and Technology · doi:10.1007/s11390-023-2839-0 · Cited by 8
Kaur, R., Anand, D., Kaur, U., Verma, S., Kavita, K., Park, S.-W., Hosen, A. S. M. S., & Ra, I.-H. (2023) · Electronics · doi:10.3390/electronics12081810 · Cited by 7
Scheduling Latency-Sensitive Tasks in the Cloud Continuum with Hierarchical Reinforcement Learning
Monaco, D., Sacco, A., Casetti, C., & Marchetto, G. (2025) · IEEE/IFIP Network Operations and Management Symposium (NOMS) · doi:10.1109/noms57970.2025.11073729 · Cited by 8
“Nonetheless, some studies focus solely on efficient resource utilization [12], [14] or system latency minimization [13], and only a limited fraction of research works has addressed the reduction of network latency [15]– [17].”
Cross-Domain DRL Agents for Efficient Job Placement in the Cloud-Edge Continuum
Aslanidis, T., Kosta, S., Lalis, S., & Chatzopoulos, D. (2025) · Workshop on Machine Learning and Systems (EuroMLSys) · doi:10.1145/3721146.3721934 · Cited by 5
“Various DRL paradigms, including hierarchical [21], multi-agent [47], and multi-objective RL [14, 17], have been explored to improve scalability and adapt-ability.”
Efficient Multi-Cluster Scheduling for Heterogeneous Workloads
Wang, X., Li, X., Xia, X., & Yang, M. (2025) · IEEE Access · doi:10.1109/access.2025.3626730 · Cited by 5
“To address this issue, the proposed scheduling system incorporates a standardized resource capability assessment model, which normalizes the computational capacity of heterogeneous resources into a unified metric space [29], [30].”
Taher, B. H., Luo, J., Ghrabat, F., & Qiao, Y. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3656811 · Cited by 7
“Works by Zhang et al. [25], [26], and Lu et al. [27] reduce latency via distributed policies yet assume largely static graphs; under nonstationarity, learned policies can violate energy budgets or overflow queues.”
Huang, J., Zhou, F., Feng, L., Li, W., Zhao, M., Yan, X., Yan, X., & Wu, J. (2023) · IEEE International Conference on Communications workshops · doi:10.1109/iccworkshops57953.2023.10283633 · Cited by 5
“In [7], a distributed scheme based on MARL is proposed considering a cloud-edge-terminal three-layer network such that each cloud-centric node jointly decides the task offloading and resource allocation policy based on the decisions of other cloud-centric nodes.”
MethodA Multi-agent Reinforcement Learning based Offloading Strategy for Multi-access Edge Computing
Ma, L., Shi, H., Li, J., & Hwang, K. (2021) · International Automatic Control Conference · doi:10.1109/cacs52606.2021.9639048 · Cited by 5
Ai, P., & Wang, F. (2024) · Computer Networks · doi:10.1016/j.comnet.2024.110415 · Cited by 4
Cao, J., Zhang, C., Qi, P., & Hu, K. (2025) · Journal of Cloud Computing Advances Systems and Applications · doi:10.1186/s13677-025-00739-8 · Cited by 4
“Díaz et al. [28] proposed a distributed scheme based on multi-agent reinforcement learning, where each cloud center collaborates to determine task offloading and resource allocation strategies, based on its inference of other cloud centers’ decisions.”
Joint Beamforming and Clustering for Energy Efficient Multi-Cloud Radio Access Networks
Reifert, R.-J., Ahmad, A. A., Dahrouj, H., Chaaban, A., Sezgin, A., Al-Naffouri, T. Y., & Alouini, M. (2022) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc51071.2022.9771701 · Cited by 4
“Therefore, deploying several CPs, each managing their associated resources and set of BSs, all while utilizing a minimal communication overhead between the CPs, becomes a necessity [9].”
BackgroundAbuthahir, S. S., & Peter, J. S. P. (2025) · Transactions on Emerging Telecommunications Technologies · doi:10.1002/ett.70191 · Cited by 3
Zheng, T., Bi, Y., Han, G., Wang, X., Liu, Y., Liu, Y., & Chen, X. (2025) · IEEE Transactions on Computers · doi:10.1109/tc.2025.3605749 · Cited by 3
“…by x n and y n , and they are denoted as x n = 1 , y n = 1 , 1( active ) = 0 It is natural to formulate the problem P1 as an MDP [4], [33], [36], which is governed by the tuple (cid:8)S , A , P , rew (cid:9) , where S is the set of states, A is the set of actions available to the agent, P…”
Lightweight Task Coordination of LEO Satellite Cluster based on Distributed Reinforcement Learning
Qin, J., Li, X., Ma, X., & Yang, J. J. (2022) · Journal of Physics Conference Series · doi:10.1088/1742-6596/2400/1/012009 · Cited by 3
“Reference [11] proposed a distributed scheme based on Multi-Agent Reinforcement Learning, in which each collaboration center jointly determines the task unloading and resource allocation strategy according to its reasoning on the decisions of other collaboration centers.”
MethodJoint Task Offloading and Resource Allocation for Collaborative VEC Network
Xu, Z., Li, Y., Chen, Y., Cheng, Z., & Wang, Z. (2025) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2025.3631306 · Cited by 2
“Restrictions apply. cannot be directly solved [32].”
Suzuki, A., Kobayashi, M., & Oki, E. (2024) · International Conference on Computer Communications and Networks (ICCCN) · doi:10.1109/icccn61486.2024.10637522 · Cited by 1
“Additionally, these studies [4]–[8] fail to account for bandwidth capacity and the topology of the backbone network.”
BackgroundEvent-Triggered Switched Observers for Networked Distributed Multi-Agent Systems via Cloud Computing
Zhang, C., Ren, H., Ma, H., & Zhou, Q. F. (2024) · International Conference on Electronic Engineering and Informatics (EEI) · doi:10.1109/eei63073.2024.10696833 · Cited by 1
Kan, J., & Duan, X. (2024) · International Conference on Electronic Information Technology and Computer Engineering (EITCE) · doi:10.1145/3711129.3711272 · Cited by 1
“For cloud task deployment on mobile devices, a two-tier DRL framework was proposed, focusing on optimizing both task delay and resource utilization [14].”
Self-Adaptable Computation Offloading Strategy for UAV-Assisted Edge Computing
Wang, Y., Zhang, Y., Qian, Z., Zhao, Y., & Zhang, H. (2025) · Drones · doi:10.3390/drones9110748 · Cited by 1
Self-citationToward Sustainability-Aware Edge Computing Systems: A Heterogeneous MADRL Approach
Chen, Y., Taleb, T., Guo, Q., Lacalle, I., & Benmerar, T. Z. (2026) · IEEE Transactions on Green Communications and Networking · doi:10.1109/tgcn.2026.3689168 · Cited by 1
“Zhang et al. [31] studied hierarchical multi-cloud MEC systems where each cloud server learned task scheduling strategies through agent interaction, significantly reducing processing latency.”
Chen, J., Wu, Z., Wu, L., Xia, Y., Wang, Y., Xiong, L., & Shi, C. (2022) · IEEE International Conference on High Performance Computing and Communications; IEEE International Conference on Smart City; IEEE International Conference on Data Science and Systems (HPCC/SmartCity/DSS) · doi:10.1109/hpcc-dss-smartcity-dependsys57074.2022.00062 · Cited by 1
“So far, some researchers apply DRL methods to deal with the joint optimization problem in edge-cloud networks [15][16][17] [18][19].”
MethodEarly Warning Algorithm of College Students' Mental Health Based on Distributed Multi-Agent System
Liu, Z., Zhao, X., Liu, C., Li, Y., & Yin, W. (2024) · International Conference on Telecommunications and Power Electronics (TELEPE) · doi:10.1109/telepe64216.2024.00062 · Cited by 1
“Based on the above-mentioned behavior model and decision-making mechanism, an early warning model is constructed, and students' mental health status is predicted and evaluated by means of supervised learning and reinforcement learning[11].”
MethodEfficient Task Offloading and Resource Allocation in MEC
Yang, Y., & Yang, Q. (2025) · Journal of Cases on Information Technology · doi:10.4018/jcit.371753 · Cited by 1
“Zhang et al. (2020) proposed a distributed multi-cloud MEC framework using multi-agent reinforcement learning to optimize task offloading and resource allocation.”
2021 Index IEEE Transactions on Wireless Communications Vol. 20
(2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2021.3135649
(2021) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2021.3060977
Location-Aware Application Deployment in Multi-Cloud
Shi, T. (2022) · Open Access Victoria University of Wellington | Te Herenga Waka (Figshare) · doi:10.26686/wgtn.20099645 · Cited by 1
Chen, Y., Li, X., Jin, Y., Wang, X., & Chen, Q. (2023) · IEEE International Conference on Internet of Things (iThings) and IEEE Green Computing and Communications (GreenCom) and IEEE Cyber, Physical and Social Computing (CPSCom) and IEEE Smart Data (SmartData) · doi:10.1109/ithings-greencom-cpscom-smartdata-cybermatics60724.2023.00027
“The RL algorithms can solve model-free dynamic programming problems which cannot be solved by traditional decision-making methods, and has been widely applied [10].”
Yang, T., Liao, S., Lyu, D., Lin, J., Liang, X., & Jia, J. (2025) · International Conference on Computer and Communication Systems (ICCCS) · doi:10.1109/icccs65393.2025.11069803
“Zhang et al. [15] considered a multi-access transformational computing scenario with multiple data centers and proposed a distributed task scheduling method based on reinforcement learning (RL).”
Self-citationYang, H., Li, X., Li, P., & Liu, S. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5428151
Mishra, D. (2025) · Research Square · doi:10.21203/rs.3.rs-7042782/v1
Reformed multi-source sharing (RMSS) for efficient resource distribution across edge servers
Srinivasan, K., Chauhan, G. S., Jadon, R., Budda, R., Gollapalli, V. S. T., & Awotunde, J. B. (2025) · Internet of Things · doi:10.1016/j.iot.2025.101848
Yang, H., Li, X., Pan, L., & Liu, S. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5995950
Adaptive scheduling strategy for cloud computing resources based on Q-learning algorithm
Xu, J., Gao, X., & Gao, N. (2026) · Mechanics & Industry · doi:10.1051/meca/2025034 · Cited by 1
Hierarchical MADRL for Mobile Edge Computing
Gong, S., Niyato, D. T., Gu, B., & Huang, K. (2026) · Wireless networks · doi:10.1007/978-3-032-22997-7_5
Hypergraph-based adaptive resource scheduling for fault-resilient multi-tenant cloud allocation
Murali, J. A. (2026) · Journal of Cloud Computing Advances Systems and Applications · doi:10.1186/s13677-026-00925-2
Toward Stable and Low-Latency Task Offloading: A Multi-Agent Framework for Vehicular Edge Computing
Wei, L., Yu, Y., Cui, J., Xie, X., Zhang, J., Bolodurina, I. P., & Zhong, H. (2026) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2026.3713305
“Zhang et al. [29] introduced a Multi-Agent Reinforcement Learning (MARL)-based distributed approach that considers a three-tier network comprising cloud, edge, and end devices, allowing each cloud node to collaboratively determine task offloading and resource allocation based on the decisions of…”
Zhang, Z., Xu, W., Xie, D., Jiang, X., Bin, Z., Dong, L., Ge, G., & Wan, Z. (2026) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2026.3721659
Wang, J., Fu, N., & Zhu, X. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.116466
Metadata
- Authors
- Zhang, Y., Di, B., Zheng, Z., Lin, J., & Song, L.
- Affiliations
- Peking University (CN)
- Imperial College London (GB)
- Venue
- IEEE Transactions on Wireless Communications
- Published
- 2021-04
- Volume
- 20
- Issue
- 4
- Pages
- 2565-2578
- ISSN
- 1536-1276 (ISSN-L)
- 1558-2248
- OpenAlex
- W3112164530
- Cited by
- 75
- References
- 44
- Citations by year
- 2026: 8 · 2025: 17 · 2024: 17 · 2023: 11 · 2022: 14 · 2021: 8
- FWCI
- 3.88
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Wireless Communications (publishedVersion)
- Funders
- National Natural Science Foundation of China (61625101, 61829101, 61941101)
- NSF (EARS-1839818, CNS-1717454, CNS-1731424, CNS-1702850)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Computer Science › Information Systems › Cloud Computing and Resource Management
- Physical Sciences › Computer Science › Hardware and Architecture › Energy Efficiency in Computing
- Keywords
- mobile edge computing, multi-cloud, task offloading, resource allocation, multi-agent reinforcement learning, three-layer network architecture, system latency, resource competition, decentralized decision-making, edge devices
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.