Deep reinforcement learning based computation offloading and resource allocation for MEC
The DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.
Abstract
Mobile edge computing (MEC) has the potential to enable computation-intensive applications in 5G networks. MEC can extend the computational capacity at the edge of wireless networks by migrating the computation-intensive tasks to the MEC server. In this paper, we consider a multi-user MEC system, where multiple user equipments (UEs) can perform computation offloading via wireless channels to an MEC server. We formulate the sum cost of delay and energy consumptions for all UEs as our optimization objective. In order to minimize the sum cost of the considered MEC system, we jointly optimize the offloading decision and computational resource allocation. However, it is challenging to obtain an optimal policy in such a dynamic system. Besides immediate reward, Reinforcement Learning (RL) also takes a long-term goal into consideration, which is very important to a time-variant dynamic systems, such as our considered multi-user wireless MEC system. To this end, we propose RL-based optimization framework to tackle the resource allocation in wireless MEC. Specifically, the Q-learning based and Deep Reinforcement Learning (DRL) based schemes are proposed, respectively. Simulation results show that the proposed scheme achieves significant reduction on the sum cost compared to other baselines.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Mobile 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×
“Therefore, the computation offloading and computational resource allocation themes have attracted great interests as a key point in the MEC system [3].”
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 1×
“But according to [14], [15], the download data rate is very high in general, and the data size of the result is much smaller than that of input data, so the delay and energy consumptions of this step are neglected in the rest of this paper.”
BackgroundCloud computing for mobile users: can offloading computation save energy?
Kumar, K., & Lu, Y.-H. (2010) · Computer · doi:10.1109/mc.2010.98 · Cited by 1,493 · cited 1×
“The work in [5] proposed general guidelines to make offloading decision for energy consumption minimization, where the communication links were easily assumed to have a fixed rate.”
BackgroundSelf-citationEnergy-Efficient Offloading for Mobile Edge Computing in 5G Heterogeneous Networks
Zhang, K., Mao, Y., Leng, S., Zhao, Q., Li, L., Peng, X., Pan, L., Maharjan, S., & Zhang, Y. (2016) · IEEE Access · doi:10.1109/access.2016.2597169 · Cited by 855 · cited 1×
“But according to [14], [15], the download data rate is very high in general, and the data size of the result is much smaller than that of input data, so the delay and energy consumptions of this step are neglected in the rest of this paper.”
BackgroundDelay-optimal computation task scheduling for mobile-edge computing systems
Liu, J., Mao, Y., Zhang, J., & Letaief, K. B. (2016) · 2016 IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit.2016.7541539 · Cited by 759 · cited 1×
“The work in [8] designed the single-user delay-optimal task scheduling policies based on the theory of MDP, which controlled the states of the local processing and transmission units and the task buffer queue length based on the channel state.”
MethodJaszkiewicz, A. (2002) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2002.802873 · Cited by 474
Communicating While Computing: Distributed mobile cloud computing over 5G heterogeneous networks
Barbarossa, S., Sardellitti, S., & Di Lorenzo, P. (2014) · IEEE Signal Processing Magazine · doi:10.1109/msp.2014.2334709 · Cited by 468 · cited 2×
“Since the data rates for wireless communications are not constant, the optimal binary computation offloading decision using convex optimization was proposed in [6], where the the famous Shannon-Hartley formula gave the power-rate function.”
BackgroundMobile-edge computing architecture: the role of mec in the internet of things
Sabella, D., Vaillant, A., Kuure, P., Rauschenbach, U., & Giust, F. (2016) · IEEE Consumer Electronics Magazine · doi:10.1109/mce.2016.2590118 · Cited by 413 · cited 1×
“MEC is a new paradigm in C-RAN, which can enhance the computation capacity at the edge of mobile networks by deploying high-performance servers [2].”
BackgroundEnergy-optimal mobile application execution: Taming resource-poor mobile devices with cloud clones
Wen, Y., Zhang, W., & Luo, H. (2012) · 2012 Proceedings IEEE INFOCOM · doi:10.1109/infcom.2012.6195685 · Cited by 394 · cited 1×
“We set zn = 10−27 ( f l n )2 according to the practical measurement in [13].”
MethodPeng, M., Sun, Y., Li, X., Mao, Z., & Wang, C. (2016) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2016.2548658 · Cited by 386
Cited by
Items 201–300 of 560
Energy-Efficient Task Offloading Under E2E Latency Constraints
Tajallifar, M., Ebrahimi, S., Javan, M. R., Mokari, N., & Chiaraviglio, L. (2021) · IEEE Transactions on Communications · doi:10.1109/tcomm.2021.3132909 · Cited by 25
Task offloading in Multiple-Services Mobile Edge Computing: A deep reinforcement learning algorithm
Peng, Z., Wang, G., Nong, W., Qiu, Y. F., & Huang, S. (2023) · Computer Communications · doi:10.1016/j.comcom.2023.02.001 · Cited by 24
An intelligent approach of task offloading for dependent services in Mobile Edge Computing
Chen, J., Leng, Y., & Huang, J. (2023) · Journal of Cloud Computing Advances Systems and Applications · doi:10.1186/s13677-023-00477-9 · Cited by 23
“With reference to [31, 32], we compare the proposed algorithm with three other offloading baseline strategies and the earliest completion time offloading strategy proposed in [33]: (1) Local computing strategy: The local computing strategy does not involve task offloading.”
MethodDRL-Based Computation Offloading and Resource Allocation in Green MEC-Enabled Maritime-IoT Networks
Wei, Z. F., He, R., Li, Y., & Song, C. (2023) · Electronics · doi:10.3390/electronics12244967 · Cited by 23
Leng, L., Li, J., Shi, H., & Zhu, Y. (2021) · Multimedia Tools and Applications · doi:10.1007/s11042-021-11130-5 · Cited by 25
“Although the existing DRL-based offloading methods have improved the MEC applications to some extent [22], there are several challenges in modeling task offloading.”
BackgroundSelf-citationChen, N., Zhang, S., Qian, Z., Wu, J., & Lu, S. (2019) · IEEE International Conference on Parallel and Distributed Systems (ICPADS) · doi:10.1109/icpads47876.2019.00066 · Cited by 22
“In [21], the author considered a multi-user MEC system, and proposed RL-based optimization framework to tackle computation offloading and resource allocation for MEC.”
BackgroundDynamic Pricing Scheme for Edge Computing Services: A Two-layer Reinforcement Learning Approach
Lyu, F., Cai, X., Wu, F., Lu, H., Duan, S., & Ren, J. (2022) · International Workshop on Quality of Service · doi:10.1109/iwqos54832.2022.9812869 · Cited by 22
“In [34], the authors proposed a deep reinforcement learning based offloading control framework,”
BackgroundDistributed Convex Relaxation for Heterogeneous Task Replication in Mobile Edge Computing
Dai, P., Han, B., Wu, X. Y., Xing, H., Liu, B., & Liu, K. (2022) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2022.3232495 · Cited by 22
“Following these literature [12], [34] related to INLP problem, it is difficult to obtain the optimal solution in polynomial time.”
MethodAbdalla, A. S., Behfarnia, A., & Marojevic, V. (2023) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2023.3285737 · Cited by 22
“UAV Trajectory Optimization The objective function of (28) is non-convex with respect to parameters xr, yr, zr, P , and the constraints, and the problem is NP-hard [23], [41]–[43].”
BackgroundBlockchain and RL-Based Secured Task Offloading Framework for Software-Defined 5G Edge Networks
Subramanian, N. S., Krishnan, P., Jain, K., Kumar, K. B. A., Pandey, T., & Buyya, R. (2025) · IEEE Access · doi:10.1109/access.2025.3554638 · Cited by 29
Intelligent Task Offloading: Advanced MEC Task Offloading and Resource Management in 5G Networks
Ebrahimi, A., & Afghah, F. (2025) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc61545.2025.10978559 · Cited by 22
“The publication [20] addresses concerns regarding execution delay and energy consumption when deciding on offloading requests.”
Reinforcement Learning Based Offloading for Realtime Applications in Mobile Edge Computing
Huang, H., Ye, Q., & Du, H. (2020) · International Conference on Communications · doi:10.1109/icc40277.2020.9148748 · Cited by 24
“To be specific, a combination of decisions that consist of CPU frequency and offloading policy, are made based on local system usage and the remaining computation capacity in edge servers [12].”
BackgroundNwogbaga, N. E., Latip, R. B., Affendey, L. S., & Rahiman, A. R. A. (2021) · Journal of Cloud Computing Advances Systems and Applications · doi:10.1186/s13677-021-00254-6 · Cited by 25
A Reputation Value‐Based Task‐Sharing Strategy in Opportunistic Complex Social Networks
Wu, J., Gou, F., Xiong, W., & Zhou, X. (2021) · Complexity · doi:10.1155/2021/8554351 · Cited by 21
“+e paper [13] considers a multi-user MEC system in which a single MEC server can handle the computational tasks shared by multiple user devices over wireless channels.”
BackgroundResource Allocation in MEC-enabled Vehicular Networks: A Deep Reinforcement Learning Approach
Tan, G., Zhang, H., & Zhou, S. (2020) · IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) · doi:10.1109/infocomwkshps50562.2020.9162980 · Cited by 21
“The authors in [8] proposed a RL-based framework to optimize the resource allocation in multi-user MEC system.”
BackgroundUser Allocation in Mobile Edge Computing: A Deep Reinforcement Learning Approach
Panda, S. P., Banerjee, A., & Bhattacharya, A. (2021) · IEEE International Conference on Web Services (ICWS) · doi:10.1109/icws53863.2021.00064 · Cited by 23
“Although DRL is used for the EUA problem in [29], it still assumes a linear relationship between resource utilization and execution time.”
MethodNear-optimal and learning-driven task offloading in a 5G multi-cell mobile edge cloud
Xia, Q., Lou, Z., Xu, W., & Xu, Z. (2020) · Computer Networks · doi:10.1016/j.comnet.2020.107276 · Cited by 21
Semi-Online Computational Offloading by Dueling Deep-Q Network for User Behavior Prediction
Song, S., Fang, Z., Zhang, Z., Chen, C., & Sun, H. (2020) · IEEE Access · doi:10.1109/access.2020.3004861 · Cited by 23
“Reference [16] proposes Q-learning based and Deep Reinforcement Learning (DRL) based schemes for a multi-user mobile edge computing (MEC) system.”
BackgroundDeep Reinforcement Learning for MEC Streaming with Joint User Association and Resource Management
Chou, P.-Y., Chen, W.-Y., Wang, C.-Y., Hwang, R., & Chen, W.-T. (2020) · International Conference on Communications · doi:10.1109/icc40277.2020.9149086 · Cited by 22
“Several studies have adopted deep Q learning-based approaches to solve the resource allocation and offloading problem in cache-aided MEC network [10], [11].”
BackgroundDRL-based Distributed Resource Allocation for Edge Computing in Cell-Free Massive MIMO Network
Tilahun, F. D., Abebe, A. T., & Kang, C. G. (2022) · Globecom · doi:10.1109/globecom48099.2022.10000910 · Cited by 21
“For instance, deep Q-network (DQN) is employed in [1, 2] for designing joint offloading and resource allocation decisions, while [3] presents a deep deterministic policy gradient (DDPG)-based scheme in heterogeneous networks with multiple users.”
MethodMaximizing the Average Secrecy Rate for UAV-assisted MEC: A DRL Method
Jing, L., Jia, X., Lv, Y., & Wan, N. (2021) · IEEE Advanced Information Technology, Electronic and Automation Control Conference (IAEAC) · doi:10.1109/iaeac50856.2021.9390913 · Cited by 20
“Authors in [10] proposed a DRL-based scheme to solve the problem of resource allocation in MEC, and the results showed that the proposed scheme reduced system overhead compared with other schemes.”
ResultAdaptive Training and Aggregation for Federated Learning in Multi-Tier Computing Networks
Hou, W., Wen, H., Zhang, N., Lei, W., Lin, H., Han, Z., Liu, Q., & Tian, W. (2023) · Elsevier eBooks · doi:10.1016/b978-0-44-344433-3.00020-4 · Cited by 22
MADDPG-M&L: UAV-Assisted Joint User Association and Slicing Resource Allocation in HetNets
Chen, G., Sun, F., Liang, H., Zeng, Q., & Zhang, Y. (2025) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2025.3554991 · Cited by 23
“[34], [35], [36] proposed a single-agent deep reinforcement learning framework for computational offloading and resource allocation, enabling the dynamic optimization of offloading strategies and efficient resource allocation.”
Computing Offloading Decision Based on DDPG Algorithm in Mobile Edge Computing
Chen, X., Ge, H., Liu, L., Li, S., Jia-peng, H., & Gong, H. (2021) · International Conference on Cloud Computing and Big Data Analytics (ICCCBDA) · doi:10.1109/icccbda51879.2021.9442599 · Cited by 20
“For example, literature [7] proposed an algorithm based on Deep Q-learning (DQN) to solve the offloading decision problem of multi-user shared network edge computing resources.”
MethodWang, J., & Wang, L. (2021) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-021-03458-5 · Cited by 21
Wang, T., Luo, X., & Zhao, W. (2022) · IET Communications · doi:10.1049/cmu2.12334 · Cited by 22
Learning-Based Task Offloading for Marine Fog-Cloud Computing Networks of USV Cluster
Cui, K., Lin, B., Sun, W., & Sun, W. (2019) · Electronics · doi:10.3390/electronics8111287 · Cited by 20
“Reference [16] proposes a RL-based optimized algorithm to solve the task allocation problem in wireless mobile edge computing network.”
MethodDelay-aware resource allocation for partial computation offloading in mobile edge cloud computing
Yu, L., Xu, H., Zeng, Y., & Deng, J. (2024) · Pervasive and Mobile Computing · doi:10.1016/j.pmcj.2024.101996 · Cited by 22
A Reinforcement Learning Based Task Offloading Scheme for Vehicular Edge Computing Network
Zhang, J., Guo, H., & Liu, J. (2019) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-030-22971-9_38 · Cited by 20
Optimal Offloading Decision Strategies and Their Influence Analysis of Mobile Edge Computing
Xu, J., Hao, Z., & Sun, X. (2019) · Sensors · doi:10.3390/s19143231 · Cited by 19
“There is a liner relation between Bn and Dn [8].”
BackgroundMethodInfluentialSpeed-Aware and Customized Task Offloading and Resource Allocation in Mobile Edge Computing
Zhu, D., Li, T., Tian, H., Yang, Y., Liu, Y., Liu, H., Geng, L., & Sun, J. (2021) · IEEE Communications Letters · doi:10.1109/lcomm.2021.3075690 · Cited by 19
Fine-Grained Offloading for Multi-Access Edge Computing with Actor-Critic Federated Learning
Liu, K.-H., Hsu, Y.-H., Lin, W.-N., & Liao, W. (2021) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc49053.2021.9417477 · Cited by 19
“In [4], Li et al . solved the problem of computation offloading decision and computing resource allocation by a combination of Q-learning and deep neural network (DNN), which is known as deep-Q-network (DQN).”
BackgroundTask Offloading Algorithms for Novel Load Balancing in Homogeneous Fog Network
Yan, J., Wu, J., Wu, Y., Chen, L., & Liu, S. (2021) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd49262.2021.9437748 · Cited by 19
“Let e cik be the energy consumption of executing r ik , which is defined as follows. where (cid:22) is the effective switched capacitance correlated to the chip architecture [12].”
BackgroundMobility-Aware Computation Offloading for Swarm Robotics using Deep Reinforcement Learning
Wang, X., & Guo, H. (2021) · IEEE Consumer Communications and Networking Conference · doi:10.1109/ccnc49032.2021.9369456 · Cited by 19
“We also consider the approaches in [9] and POJ in [3].”
MethodTwo-Level Scheduling Algorithms for Deep Neural Network Inference in Vehicular Networks
Wu, Y., Wu, J., Yao, M., Liu, B., Chen, L., & Lam, S.-K. (2023) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2023.3266795 · Cited by 18
“Here, μ is effective capacitance, which depends on the chip architecture, it is set to 10−27 by default [41].”
BackgroundJoint Computation Offloading and Radio Resource Allocations in Wireless Cellular Networks
Chen, H., Zhao, D., Chen, Q., & Chai, R. (2018) · International Conference on Wireless Communications and Signal Processing (WCSP) · doi:10.1109/wcsp.2018.8555588 · Cited by 18
“Joint offloading decision and computational resource allocation is studied in [9] for a multiuser mobile edge computing (MEC) system to minimize the sum cost of delay and energy consumptions for all UEs.”
BackgroundApplications of Deep Reinforcement Learning in Communications and Networking: A Survey
Luong, N. C., Hoang, D. T., Gong, S., Niyato, D., Wang, P., Liang, Y.-C., & Kim, D. I. (2018) · arXiv · doi:10.48550/arxiv.1810.07862 · Cited by 17
“used for each mobile user to learn the optimal offloading policy from past experiences such as the approaches proposed in [101] and [102].”
BackgroundKhuntia, P., & Hazra, R. (2019) · Transactions on Emerging Telecommunications Technologies · doi:10.1002/ett.3671 · Cited by 17
“To tackle jointly the offloading and resource allocation for a multiuser mobile computing system, Li et al 23 exploited a Deep Q-learning to minimize the sum cost for delay and energy consumption of user equipment.”
MethodQi, J., Liu, Y., Ling, Y., Xu, B., Dong, Z., & Sun, Y. (2022) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2022.3210752 · Cited by 17
“where fp is the computing capacity of the main node and η = 10−27 is the energy coefficient [26].”
BackgroundYang, H., Ding, W., Min, Q., Dai, Z., Jiang, Q., & Gu, C. (2023) · Applied Sciences · doi:10.3390/app13095412 · Cited by 17
Task Offloading and Resource Allocation Strategies Among Multiple Edge Servers
Shi, B., & Wu, Y. (2023) · IEEE Internet of Things Journal · doi:10.1109/jiot.2023.3343793 · Cited by 17
“For research on task offloading and resource allocation problems with one edge server, Li et al. [6] analyzed the problem by considering a single-edge server with multiple users in the system.”
Li, Q., Zhu, Y., Ding, J., Li, W., Sun, W., & Ding, L. (2024) · CSEE Journal of Power and Energy Systems · doi:10.17775/cseejpes.2021.02390 · Cited by 17
“Methods based on q learning and deep reinforcement learning, respectively, were proposed in order to address the resource allocation issue of the wireless MEC system [18].”
Xing, S., Wang, Y., & Liu, W. (2025) · Symmetry · doi:10.3390/sym17071109 · Cited by 63
Neural Combinatorial Optimization for Energy-Efficient Offloading in Mobile Edge Computing
Jiang, Q., Zhang, Y., & Yan, J. (2020) · IEEE Access · doi:10.1109/access.2020.2974484 · Cited by 17
“With the notable success of deep learning approaches, researchers have begun to construct deep neural networks to solve combinatorial optimization problems [7]–[9].”
BackgroundPower Consumption Optimization Using Gradient Boosting Aided Deep Q-Network in C-RANs
Luo, Y., Yang, J., Xu, W., Wang, K., & Renzo, M. D. (2020) · IEEE Access · doi:10.1109/access.2020.2978935 · Cited by 18
“Furthermore, as reported in [34], DQN achieved a better performance on resource allocation problems, compared with the traditional Q-learning based method.”
MethodResultDouble Deep Q-Network for Power Allocation in Cloud Radio Access Network
Iqbal, A., Tham, M., & Chang, Y. C. (2020) · IEEE International Conference on Computer and Communication Engineering Technology (CCET) · doi:10.1109/ccet50901.2020.9213138 · Cited by 17
“RA works such as [16], [17] resort to deep Q network (DQN), which is a combination of a neural network and Q-learning [18].”
BackgroundDynamic Resource Allocation for Multi-Access Edge Computing in Urban Rail Transit
Zhang, Q., Zhang, C., Zhao, J., Wang, D., & Xu, W. (2024) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2024.3479215 · Cited by 18
“Because the downlink transmission rate is typically substantially higher than the uplink rate, we do not take into account the backhaul delay like most researches [26], [27], [28].”
Deep Reinforcement Learning Based Offloading Scheme for Mobile Edge Computing
Yao, P., Chen, X., Chen, Y., & Li, Z. (2019) · IEEE International Conference on Smart Internet of Things (SmartIoT) · doi:10.1109/smartiot.2019.00074 · Cited by 17
“W 10MHz ui Uniform in [2,10]Mb fl Uniform in [0.”
BackgroundComputing Cost Optimization for Multi-BS in MEC by Offloading
Li, W., Wang, F., Pan, Y., Zhang, L., & Liu, J. (2020) · Mobile Networks and Applications · doi:10.1007/s11036-020-01627-y · Cited by 16
“Li et al. [27] aim to optimize the formulated cost model in multi-users scenarios by Deep Reinforcement Learning (DRL) method [28].”
MethodWan, Z., & Li, Y. (2020) · Wireless Communications and Mobile Computing · doi:10.1155/2020/6684293 · Cited by 17
Q-learning algorithm for resource allocation in WDMA-based optical wireless communication networks
Elgamal, A. S., Aletri, O. Z., Qidan, A. A., El-Gorashi, T. E. H., & Elmirghani, J. M. H. (2021) · International Conference on Smart and Sustainable Technologies (SpliTech) · doi:10.23919/splitech52315.2021.9566383 · Cited by 16
Gan, Z., Lin, R., & Zou, H. (2022) · IEEE/ACM International Symposium on Cluster, Cloud and Grid Computing (CCGrid) · doi:10.1109/ccgrid54584.2022.00074 · Cited by 16
End-to-end simulation environment for mobile edge computing
Gilly, K., Bernad, C., Roig, P. J., Alcaraz, S., & Filiposka, S. (2022) · Simulation Modelling Practice and Theory · doi:10.1016/j.simpat.2022.102657 · Cited by 17
Beyond 5G networks: Integration of communication, computing, caching, and control
Adam, M. M., Zhao, L., Wang, K., & Han, Z. (2023) · China Communications · doi:10.23919/jcc.2023.00.039 · Cited by 18
“In [105, 106], Q learning and DQN have been studied to overcome some challenges related to joint optimization of 4C; see [8].”
Chen, Y., Chen, S., Li, K., Liang, W., & Li, Z. (2022) · Cluster Computing · doi:10.1007/s10586-022-03768-z · Cited by 15
“In order to minimize the overall cost in terms of time and energy for all users, a scheme based on Deep Q-Networks (DQN) is proposed in [28] to optimize computation offloading and resource allocation jointly.”
MethodWei, D., Wang, R., Xia, C., Xia, T., Jin, X. H., & Xu, C. (2022) · Mathematics · doi:10.3390/math10244812 · Cited by 15
Online-learning task scheduling with GNN-RL scheduler in collaborative edge computing
Jian, C., Pan, Z., Bao, L., & Zhang, M. (2023) · Cluster Computing · doi:10.1007/s10586-022-03957-w · Cited by 15
“Li et al. [16] proposed an RL based optimization framework to solve the resource allocation problem in wireless MEC.”
Cong, Y., Liu, M., Wang, C., Sun, S., Hu, F., Liu, Z., & Wang, C. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3387072 · Cited by 16
“Li et al. [26] addressed the offloading decision problem among multiple users through an algorithm based on deep Q learning.”
MethodOffloading Strategy Based on Graph Neural Reinforcement Learning in Mobile Edge Computing
Wang, T., Ouyang, X., Sun, D., Chen, Y., & Li, H. Q. (2024) · Electronics · doi:10.3390/electronics13122387 · Cited by 15
Intelligent Task Offloading Algorithm for Mobile Edge Computing in Vehicular Networks
Cui, Y., Liang, Y., & Wang, R. (2020) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2020-spring48590.2020.9128803 · Cited by 16
“Inspired by the aforementioned works in [9-11], this paper proposes a multi-platform offload intelligent resource allocation algorithm combining cloud computing, mobile edge computing and local computing, aiming at minimizing delay.”
MethodYu, Z., Liu, W., Liu, X., & Wang, G. (2021) · International Workshop on Quality of Service · doi:10.1109/iwqos52092.2021.9521327 · Cited by 15
DECENT: Deep Learning Enabled Green Computation for Edge Centric 6G Networks
Kashyap, P. K., Kumar, S., Jaiswal, A., Kaiwartya, O., Kumar, M., Dohare, U., & Gandomi, A. H. (2022) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2022.3145056 · Cited by 15
“In [13]–[14], Deep Q-network model used in”
BackgroundGerogiannis, G., Birbas, M., Leftheriotis, A., Mylonas, E., Tzanis, N., & Birbas, A. N. (2022) · IEEE Access · doi:10.1109/access.2022.3147674 · Cited by 15
HCOME: Research on Hybrid Computation Offloading Strategy for MEC Based on DDPG
Cao, S., Chen, S., Chen, H., Zhang, H., Zhan, Z., & Zhang, W. (2023) · Electronics · doi:10.3390/electronics12030562 · Cited by 16
Multi-Access Edge Computing (MEC) Based on MIMO: A Survey
Zhu, M., Gao, S., Tu, G., & Chen, D. (2023) · Sensors · doi:10.3390/s23083883 · Cited by 16
Adaptive and Collaborative Edge Inference in Task Stream with Latency Constraint
Song, J., Liu, Z., Wang, X., Qiu, C., & Chen, X. (2021) · International Conference on Communications · doi:10.1109/icc42927.2021.9500892 · Cited by 19
“We assume that the wireless network environment in the system is static and the time of that result returns from the edge server can be ignored [14].”
BackgroundQian, B., Su, J., Wen, Z., Jha, D. N., Li, Y., Guan, Y., Puthal, D., James, P., Yang, R., Zomaya, A. Y., et al. (2019) · White Rose Research Online (University of Leeds, The University of Sheffield, University of York) · doi:10.48550/arxiv.1910.05433 · Cited by 18
“sson learned from the successful attack. Developing new attacking and defending models.ML has been widely used in IoT system developments including network engineering [150, 168], resource allocation [146, 292], system debugging [38, 243], network intrusion detection [129, 158, 274] and network operations[116]. These…”
BackgroundCheng, M., Zhu, C., Lin, M., Wang, J.-B., & Zhu, W. (2023) · Computer Communications · doi:10.1016/j.comcom.2023.06.008 · Cited by 16
SIC-Enabled Intelligent Online Task Concurrent Offloading for Wireless Powered MEC
Jiao, X., Chen, Y., Chen, Y., Wu, X., Guo, S., Zhu, W., & Lou, W. (2024) · IEEE Internet of Things Journal · doi:10.1109/jiot.2024.3383469 · Cited by 14
“The task completion time δ t , l i of T i is given as following: Furthermore, the energy E t , l i consumed by T i under this pattern is achieved as following [45]: where σ represents a coefficient related to the computation energy efficiency.”
Safavifar, Z., Gyamfi, E., Mangina, E., & Golpayegani, F. (2024) · IEEE Access · doi:10.1109/access.2024.3405411 · Cited by 17
“In [36], a DRL-based framework is proposed to reduce the total delay and energy consumption of devices in the network.”
MethodYe, X., Li, M., Si, P., Yang, R., Sun, E., & Zhang, Y. (2021) · China Communications · doi:10.23919/jcc.2021.08.020 · Cited by 14
A Robust Distributed Hierarchical Online Learning Approach for Dynamic MEC Networks
Wu, Y.-C., Lin, C., & Quek, T. Q. S. (2021) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3118342 · Cited by 14
Deep reinforcement learning based flexible preamble allocation for RAN slicing in 5G networks
Gedikli, A. M., Köseoglu, M., & Şen, S. (2022) · Computer Networks · doi:10.1016/j.comnet.2022.109202 · Cited by 17
Dynamic visual SLAM and MEC technologies for B5G: a comprehensive review
Peng, J., Hou, Y., Xu, H., & Li, T. (2022) · EURASIP Journal on Wireless Communications and Networking · doi:10.1186/s13638-022-02181-9 · Cited by 15
“Li [90] proposed a system based on Q-Learning and deep Q-Learning to solve the offloading decision problem in multi-user MEC systems.”
MethodLai, S., Fan, X., Ye, Q., Tan, Z., Zhang, Y., He, X., & Nanda, P. (2020) · IEEE Access · doi:10.1109/access.2020.2965562 · Cited by 14
“Similarly, Li et al. [35] designed a DRL-based optimization framework with Q-learning for multi-use computation offloading and resource allocation in MEC.”
MethodLearning-Based Offloading of Tasks with Diverse Delay Sensitivities for Mobile Edge Computing
Zhang, T., Chiang, Y.-H., Borcea, C., & Ji, Y. (2019) · Globecom · doi:10.1109/globecom38437.2019.9013498 · Cited by 15
“Li et al. [16] aim to minimize delay and energy consumption through Q-learning and deep Q-network (DQN) schemes.”
BackgroundReCARL: Resource Allocation in Cloud RANs with Deep Reinforcement Learning
Xu, Z., Tang, J., Yin, C., Wang, Y., Xue, G., Wang, J., & Gursoy, M. C. (2020) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2020.3044282 · Cited by 19
Load Balancing and Resource Allocation in Smart Cities using Reinforcement Learning
AlOrbani, A., & Bauer, M. (2021) · IEEE International Smart Cities Conference (ISC2) · doi:10.1109/isc253183.2021.9562941 · Cited by 14
“In the Mobile Edge Computing (MEC) system [47], the authors assumed having a number of user equipment nodes (UEs), MEC servers and eNodeB - an entity that is the connector between all UEs and the server.”
BackgroundReinforcement Learning for Resource Allocation in Steerable Laser-Based Optical Wireless Systems
Elgamal, A. S., Aletri, O. Z., Qidan, A. A., El-Gorashi, T. E. H., & Elmirghani, J. M. H. (2021) · Conference proceedings - Canadian Conference on Electrical and Computer Engineering · doi:10.1109/ccece53047.2021.9569123 · Cited by 14
Li, Y., Zhu, L., Wu, J., Wang, H., & Yu, F. R. (2023) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2023.3258841 · Cited by 14
“Many researches propose and design offloading schemes to minimize task delay, reduce energy consumption, and optimize communication resource utility in various fields [9], [10], [11], [12], [13], [14], [15].”
BackgroundMobility-Aware Resource Allocation in Multi-Access Edge Computing Using Deep Reinforcement Learning
Din, N., Chen, H., & Khan, D. (2019) · IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA) · doi:10.1109/ispa-bdcloud-sustaincom-socialcom48970.2019.00038 · Cited by 13
“For instance, authors in [13] [14] presented a DRL-based framework for dynamic resource allocation in the MEC system.”
BackgroundPnP-DRL: A Plug-and-Play Deep Reinforcement Learning Approach for Experience-Driven Networking
Xu, Z., Wu, K., Zhang, W., Tang, J., Wang, Y., & Xue, G. (2021) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2021.3087270 · Cited by 13
Distributed Slice Selection-Based Computation Offloading for Intelligent Vehicular Networks
Tang, J., Duan, Y., Zhou, Y., & Jin, J. (2021) · IEEE Open Journal of Vehicular Technology · doi:10.1109/ojvt.2021.3087355 · Cited by 13
Iqbal, A., Tham, M., & Chang, Y. C. (2021) · Transactions on Emerging Telecommunications Technologies · doi:10.1002/ett.4417 · Cited by 13
“A similar power allocation strategy was adopted in another DQN work 25 by considering the scenario of mobile edge computing (MEC).”
MethodDeveloping a Testbed with P4 to Generate Datasets for the Analysis of 5G-MEC Security
Fernando, O. A., Xiao, H., & Spring, J. (2022) · IEEE Wireless Communications and Networking Conference · doi:10.1109/wcnc51071.2022.9771755 · Cited by 17
“We have employed (III) the MEC connected to a network edge point scenario due to its popularity [23]–[26].”
MethodSolving Task Scheduling Problems in Dew Computing via Deep Reinforcement Learning
Sanabria, P., Tapia, T. F., Icarte, R. T., & Neyem, A. (2022) · Applied Sciences · doi:10.3390/app12147137 · Cited by 13
Resource Scheduling in URLLC and eMBB Coexistence Based on Dynamic Selection Numerology
Wang, L., Tao, S., Zhao, L., Zhou, D., Liu, Z., & Sun, Y. J. (2024) · Wireless Communications and Mobile Computing · doi:10.1155/2024/9480388 · Cited by 13
“…learning (DRL) that does not require priori information on dynamic changes in URLLC data traf fi c and channel gain changes, etc. Li et al. [6] jointly optimized the of fl oading decision and computational resource allocation with the goal of minimizing the total cost of the considered…”
BackgroundComputation Offloading in Energy Harvesting Systems via Continuous Deep Reinforcement Learning
Zhang, J., Du, J., Jiang, C., Shen, Y., & Wang, J. (2020) · International Conference on Communications · doi:10.1109/icc40277.2020.9148938 · Cited by 13
“To tackle these problems, researchers have been turning to model the computation offloading problem as a Markov Decision Process (MDP) and solve it with reinforcement learning (RL) or Deep reinforcement learning (DRL) methods [8]–[11].”
BackgroundUnsupervised Deep Learning for Binary Offloading in Mobile Edge Computation Network
Chen, X., Xu, H., Zhang, G., Chen, Y., & Li, R. (2021) · Wireless Personal Communications · doi:10.1007/s11277-021-09433-9 · Cited by 15
“The optimization framework proposed in [26] exploits deep reinforcement learning method to tackle the resource allocation in wireless MEC.”
MethodCom-DDPG: A Multiagent Reinforcement Learning-based Offloading Strategy for Mobile Edge ComputingPreprint
Gao, H., Wang, X., Ma, X., Wei, W., & Mumtaz, S. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2012.05105 · Cited by 16
“[24] studied the multiuser service delay problem in MEC offloading scenarios and proposed a partial computation offloading model.”
BackgroundSelf-citationLi, N., Iosifidis, A., & Zhang, Q. (2024) · IEEE Transactions on Wireless Communications · doi:10.1109/twc.2024.3518399 · Cited by 14
“Restrictions apply. decision-making process [4], [6], [7], [8].”
Multiperspective and Energy-Efficient Deep Learning in Edge Computing
Yuan, H., Bi, J., Wang, Z., Zhang, J., Zhou, M., & Buyya, R. (2025) · IEEE Internet of Things Journal · doi:10.1109/jiot.2025.3640292 · Cited by 18
“It introduces an interference-avoidant distributed DL method for IoMT to medical receptionists.”
Liu, Y., Cui, Q., Zhang, J., Chen, Y., & Hou, Y. (2019) · International Conference on Wireless Communications and Signal Processing (WCSP) · doi:10.1109/wcsp.2019.8927911 · Cited by 12
URLLC Resource Slicing and Scheduling in 5G Vehicular Edge Computing
Hao, M., Ye, D., Wang, S., Tan, B., & Yu, R. (2021) · IEEE Vehicular Technology Conference · doi:10.1109/vtc2021-spring51267.2021.9448805 · Cited by 12
“[8] employed reinforcement learning for optimization.”
Qu, B., Bai, Y., Chu, Y., Wang, L.-E., Feng, Y., & Li, X. (2022) · Computer Networks · doi:10.1016/j.comnet.2022.109181 · Cited by 14
Graph Reinforcement Learning-based CNN Inference Offloading in Dynamic Edge Computing
Li, N., Iosifidis, A., & Zhang, Q. (2022) · Globecom · doi:10.1109/globecom48099.2022.10001067 · Cited by 12
“[7] proposed to use deep RL (DRL)based optimization methods to address dynamic computational offloading problem.”
MethodVehicle-to-Infrastructure Communication for Real-Time Object Detection in Autonomous Driving
Hawlader, F., Robinet, F., & Frank, R. (2023) · Annual Conference on Wireless On-demand Network Systems and Services (WONS) · doi:10.23919/wons57325.2023.10061953 · Cited by 15
“However, collective perception using the V2X service allows cars to potentially offload sensory data to edge and cloud for resource-intensive computations [4, 22].”
BackgroundEnergy–latency tradeoffs edge server selection and DQN-based resource allocation schemes in MEC
Li, C., Ke, Z., Liu, Q., Hu, C., Chengwei, L., & Luo, Y. (2023) · Wireless Networks · doi:10.1007/s11276-023-03426-1 · Cited by 12
“[29] considered the case of multiple access and designed an orthogonal frequency division multiple access-based MEC resource allocation strategy.”
BackgroundMethodCrowdsourcing Live High Definition Map via Collaborative Computation in Automotive Edge Computing
Zhang, Y., Liu, Q., Wang, H., Chen, D., & Han, K. (2024) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2024.3393728 · Cited by 15
“Machine learning techniques have been increasingly utilized to deal with the high-dimensional network state, dynamics, and complicated correlations [31], [32], [33], [34] in a wide range of networking problems.”
BackgroundYang, Z., Du, Y., Che, C., Wang, W., Mei, H., Zhou, D., & Yang, K. (2019) · IEEE Access · doi:10.1109/access.2019.2942391 · Cited by 12
“According to [31], the offloading design and resource allocation are very critical to the energy consumption control of MEC systems.”
Background
Metadata
- Authors
- Li, J., Gao, H., Lv, T., & Lu, Y.
- Affiliations
- Beijing University of Posts and Telecommunications (CN)
- Venue
- 2018 IEEE Wireless Communications and Networking Conference (WCNC)
- Publisher
- IEEE
- Published
- 2018-04
- Pages
- 1-6
- ISSN
- 1525-3511 (ISSN-L)
- OpenAlex
- W2808381205
- Cited by
- 548
- References
- 17
- Citations by year
- 2026: 16 · 2025: 45 · 2024: 73 · 2023: 83 · 2022: 92 · 2021: 96 · 2020: 94 · 2019: 45 · 2018: 4
- FWCI
- 49.38
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- IEEE Wireless Communications and Networking Conference (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › IoT and Edge/Fog Computing
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Wireless Network Optimization
- Physical Sciences › Engineering › Aerospace Engineering › UAV Applications and Optimization
- Keywords
- mobile edge computing, computation offloading, resource allocation, deep reinforcement learning, Q-learning, multi-user systems, energy consumption, delay cost, 5G
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.