Computing Offloading Strategy Using Improved Genetic Algorithm in Mobile Edge Computing System

Zhu, Anqing; Wen, Youyun

doi:10.1007/s10723-021-09578-8

Cited by 29 publications

(10 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus it can find the suboptimal solution to the offloading problem. In addition, the DDOA is compared to a genetic algorithm (GA) in which the offloading strategy is represented as a chromosome 26 . The GA aims to find the optimal solution to the offloading problem using crossover and mutation operations.…”

Section: Simulation Results and Discussionmentioning

confidence: 99%

Dingo‐optimization‐based task‐offloading algorithm in multihop V2V/V2I‐enabled networks

Song

Wang

Xie

et al. 2023

Trans Emerging Tel Tech

View full text Add to dashboard Cite

In the Vehicle‐to‐Vehicle‐ (V2V) and Vehicle‐to‐Infrastructure‐ (V2I) enabled edge computing networks, the task vehicle may fail to offload tasks to the nodes outside the one‐hop communication with high computing resources, resulting in longer offloading time. Therefore, in this paper, we first construct a multihop V2V/V2I communications‐enabled edge computing architecture, which innovatively adopts vehicles and roadside units (RSUs) task offloading jointly to expand the communication resources of the task vehicle. Then, for the offloading node selection strategy, we create a vehicle adjacency table and propose a quickly depth‐first search‐based scheme to search the optimal multihop path. Finally, we develop an optimal offloading scheme based on the discrete dingo optimization algorithm (DDOA) to solve the task‐processing‐time minimization problem, which can converge quickly and achieve lower task offloading latency. Each dingo in DDOA is designed to choose one of the group attack, persecution, and scavenger strategies to search the solution space and accelerate the convergence of the DDOA by a survival rule. The numerical experimental results reveal that our proposed algorithm can outperform the other algorithms and reduce the delay time by 80% compared with the local scheme.

show abstract

Section: Simulation Results and Discussionmentioning

confidence: 99%

Dingo‐optimization‐based task‐offloading algorithm in multihop V2V/V2I‐enabled networks

Song

Wang

Xie

et al. 2023

Trans Emerging Tel Tech

View full text Add to dashboard Cite

show abstract

“…If the retrieved data exists in the cache pool, the system directly dispatches the cached results. Since the amount of data processed as a result is negligibly compared to the incoming data, the result return time is ignored [27]. The time for task processing is…”

Section: Computing Modelmentioning

confidence: 99%

“…To solve this problem, this paper proposes IGA-TSPA for selecting the optimal feasible solution in the vast solution space. The genetic algorithm (GA) is a global heuristic algorithm, which follows the law of "superiority and inferiority" in nature to select feasible solutions and obtain the optimal solution to the problem [27]. However, the GA has disadvantages including large solution space, long iteration cycles, and slow convergence, which cannot meet the requirements of the industrial internet.…”

Section: Proof Of Theoremmentioning

confidence: 99%

“…In GA, the mutation is the way to possibly skip local optimal solutions. Mutation operations can accelerate the convergence speed of optimal solutions while maintaining population diversity and preventing it fall into "premature maturity" [27]. Because the mutation is an uncontrollable, random operation, there are some cases of invalid operation, which instead make the value of the fitness function smaller than before.…”

Section: Crossover and Mutationmentioning

confidence: 99%

See 1 more Smart Citation

Edge Computing Task Scheduling with Joint Blockchain and Task Caching in Industrial Internet

Chen¹,

Bai²,

Jin³

et al. 2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Deploying task caching at edge servers has become an effective way to handle compute-intensive and latency-sensitive tasks on the industrial internet. However, how to select the task scheduling location to reduce task delay and cost while ensuring the data security and reliable communication of edge computing remains a challenge. To solve this problem, this paper establishes a task scheduling model with joint blockchain and task caching in the industrial internet and designs a novel blockchain-assisted caching mechanism to enhance system security. In this paper, the task scheduling problem, which couples the task scheduling decision, task caching decision, and blockchain reward, is formulated as the minimum weighted cost problem under delay constraints. This is a mixed integer nonlinear problem, which is proved to be nonconvex and NP-hard. To solve the optimal solution, this paper proposes a task scheduling strategy algorithm based on an improved genetic algorithm (IGA-TSPA) by improving the genetic algorithm initialization and mutation operations to reduce the size of the initial solution space and enhance the optimal solution convergence speed. In addition, an Improved Least Frequently Used algorithm is proposed to improve the content hit rate. Simulation results show that IGA-TSPA has a faster optimal solution-solving ability and shorter running time compared with the existing edge computing scheduling algorithms. The established task scheduling model not only saves 62.19% of system overhead consumption in comparison with local computing but also has great significance in protecting data security, reducing task processing delay, and reducing system cost.

show abstract

“…An improved firefly swarm optimization algorithm was proposed to generate the offloading decision, which significantly reduced the system cost. Zhu and Wen [9] defined the weighted sum of energy consumption and delay as an optimization function of total overhead. An offloading strategy based on an improved genetic algorithm was proposed, which achieved better results on delay and load balance, but not on energy consumption reduction.…”

Section: Introductionmentioning

confidence: 99%

Dependent Task-Offloading Strategy Based on Deep Reinforcement Learning in Mobile Edge Computing

Gong

Jiang

2023

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

In mobile edge computing, there are usually relevant dependencies between different tasks, and traditional algorithms are inefficient in solving dependent task-offloading problems and neglect the impact of the dynamic change of the channel on the offloading strategy. To solve the offloading problem of dependent tasks in a dynamic network environment, this paper establishes the dependent task model as a directed acyclic graph. A Dependent Task-Offloading Strategy (DTOS) based on deep reinforcement learning is proposed with minimizing the weighted sum of delay and energy consumption of network services as the optimization objective. DTOS transforms the dependent task offloading into an optimal policy problem under Markov decision processes. Multiple parallel deep neural networks (DNNs) are used to generate offloading decisions, cache the optimal decisions for each round, and then optimize the DNN parameters using priority experience replay mechanism to extract valuable experiences. DTOS introduces a penalty mechanism to obtain the optimal task-offloading decisions, which is triggered if the service energy consumption or service delay exceeds the threshold. The experimental results show that the algorithm produces better offloading decisions than existing algorithms, can effectively reduce the delay and energy consumption of network services, and can self-adapt to the changing network environment.

show abstract

Computing Offloading Strategy Using Improved Genetic Algorithm in Mobile Edge Computing System

Cited by 29 publications

References 14 publications

Dingo‐optimization‐based task‐offloading algorithm in multihop V2V/V2I‐enabled networks

Dingo‐optimization‐based task‐offloading algorithm in multihop V2V/V2I‐enabled networks

Edge Computing Task Scheduling with Joint Blockchain and Task Caching in Industrial Internet

Dependent Task-Offloading Strategy Based on Deep Reinforcement Learning in Mobile Edge Computing

Contact Info

Product

Resources

About