Mobility-aware partial computation offloading in vehicular networks: A deep reinforcement learning based scheme

Wang, Jianfei; Lv, Tiejun; Huang, Pingmu; Mathiopoulos, P. Takis

doi:10.23919/jcc.2020.10.003

Cited by 32 publications

(11 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A closed-form expression for the offloading delay is derived to find the global optimal solution with the lowest latency performance. Subdividing a task into the offloadable and non-offloadable part, the study in [3] constructs an opportunistic offloading model. A delayed offloading model is introduced in [4], in which tasks will wait as long as possible until the WIFI link is available to offload before the dead time arrives.…”

Section: Introductionmentioning

confidence: 99%

Randomization-Based Dynamic Programming Offloading Algorithm for Mobile Fog Computing

Bai

Yang

Zhang

et al. 2021

Security and Communication Networks

View full text Add to dashboard Cite

Offloading to fog servers makes it possible to process heavy computational load tasks in local devices. However, since the generation problem of offloading decisions is an N-P problem, it cannot be solved optimally or traditionally, especially in multitask offloading scenarios. Hence, this paper has proposed a randomization-based dynamic programming offloading algorithm, based on genetic optimization theory, to solve the offloading decision generation problem in mobile fog computing. The algorithm innovatively designs a dynamic programming table-filling approach, i.e., iteratively generates a set of randomized offloading decisions. If some in these sets improve the decisions in the DP table, then they will be merged into the table. The iterated DP table is also used to improve the set of decisions generated in the iteration to obtain the optimal offloading approximate solution. Extensive simulations show that the proposed DPOA can generate decisions within 3 ms and the benefit is especially significant when users are in multitask offloading scenarios.

show abstract

Section: Introductionmentioning

confidence: 99%

Randomization-Based Dynamic Programming Offloading Algorithm for Mobile Fog Computing

Bai

Yang

Zhang

et al. 2021

Security and Communication Networks

View full text Add to dashboard Cite

show abstract

“…Specifically, Table 1 shows all simulation parameters. 4 We compare the delay performance of our proposed strategy and other offloading strategies:…”

Section: Parameter Settingsmentioning

confidence: 99%

“…We use python 3.7 and tensorflow 1.0 to build and train the DDQN model. Specifically, Table 1 shows all simulation parameters 4 …”

Section: Performance Evaluationmentioning

confidence: 99%

Cooperative vehicles‐assisted task offloading in vehicular networks

Cui

et al. 2022

Trans Emerging Tel Tech

View full text Add to dashboard Cite

Cooperative task offloading emerges a well‐received paradigm for mobile applications that are sensitive to computational power, while dynamic and real‐time characteristics of vehicular networks makes it challenging to guarantee the low delay requirements of vehicular computation offloading. Existing researches cannot satisfy the real‐time computation requests due to the sparse deployment of infrastructure constructions and constrained computing resources of edge servers. Motivated by these, we consider the idea of distributed vehicle‐to‐vehicle task offloading, which makes vehicles act as cooperative nodes to execute tasks. In this paper, we utilize parallel computing of multi‐vehicle cooperation, to provide low‐delay computation services without exceeding the energy constraint. Furthermore, a cooperative vehicles assisted task offloading strategy based on double deep Q‐network is proposed to obtain the optimal task offloading ratio after selecting cooperative vehicles. Simulation results indicate that our proposed strategy can effectively decrease the total system delay. For example, compared with the local execution strategy, the total system delay of the proposed strategy can be reduced by 69.4% on average.

show abstract

“…The proposed algorithm considered the stochastic tasks and the variety of environments. Wang et al [22] presented a mobility-aware partial offloading scheme in vehicular networks. Compared with full offloading, partial offloading can improve the flexibility of intelligence applications.…”

Section: Computation Offloadingmentioning

confidence: 99%

Distributed Slice Selection-Based Computation Offloading for Intelligent Vehicular Networks

Tang

Duan

Zhou

et al. 2021

IEEE Open J. Veh. Technol.

View full text Add to dashboard Cite

Distributed artificial intelligence (AI) is becoming an efficient approach to fulfill the high and diverse requirements for future vehicular networks. However, distributed intelligence tasks generated by vehicles often require diverse resources. A customized resource provision scheme is required to improve the utilization of multi-dimensional resources. In this work, a slice selection-based online offloading (SSOO) algorithm is proposed for distributed intelligence in future vehicular networks. First, the response time and energy consumption are reduced for processing tasks locally on the vehicles. Then, the offloading overheads, including latency and energy consumption, are calculated by considering the available resource amount, wireless channel states and vehicle conditions. The slice selection results is obtained by the deep reinforcement learning (DRL)-based method. Based on the selection solution, resource allocation results are achieved by KKT conditions and bisection method. Finally, the experimental results depict that the proposed SSOO algorithm outperforms other comparing algorithms in terms of energy consumption and task completion rate.

show abstract

Mobility-aware partial computation offloading in vehicular networks: A deep reinforcement learning based scheme

Cited by 32 publications

References 5 publications

Randomization-Based Dynamic Programming Offloading Algorithm for Mobile Fog Computing

Randomization-Based Dynamic Programming Offloading Algorithm for Mobile Fog Computing

Cooperative vehicles‐assisted task offloading in vehicular networks

Distributed Slice Selection-Based Computation Offloading for Intelligent Vehicular Networks

Contact Info

Product

Resources

About