Font Size: a A A

Research On Resource Scheduling Algorithm In Fog Computing

Posted on:2020-01-11Degree:MasterType:Thesis
Country:ChinaCandidate:Y C LiuFull Text:PDF
GTID:2438330575457150Subject:Computer Science and Technology
Abstract/Summary:PDF Full Text Request
With the maturity of Internet of Things(IoT)technology,the number of IoT connection devices is increasing,and the amount of data is increasing rapidly.This has caused tremendous pressure on cloud data center,resulting that some delay-sensitive user requests can't be quickly responded.The great challenges are brought on the traditional cloud computing network architecture.As a new computing model,fog computing extends cloud computing to the edge of the network.It can better satisfy the delay-sensitive user requests with the characteristics of real-time and low latency.At present,resource scheduling is a new research hotspot in fog computing,which is an important factor affecting the performance of fog computing services.The process of resource scheduling will face large-scale tasks and diverse user demands,which brings great challenges to the fog computing architecture.Therefore,the problem of resource scheduling in fog computing is chosen as the research topic in this paper.The resource scheduling model is established combining with the fog computing architecture in this paper.The resource scheduling algorithm based on the fuzzy clustering algorithm and the resource scheduling algorithm based on the improved bee colony algorithm are proposed from the perspective of users and tasks.The specific research contents are as follows.(1)The resource scheduling algorithm based on fuzzy clustering algorithm in fog computing is designed.Firstly,the various performance indicators of resources are standardized and normalized to solve the problem of unbalanced impact on clustering results.Then,to reduce the search scale of resources,the fuzzy clustering algorithm and particle swarm optimization algorithm are combined to improve the clustering effect and complete the clustering partition of resources.Finally,the highest score is obtained by the weight matching method according to different task preferences,and the final scheduling results are returned to users.The matching of user requirements and resources is realized,and the reasonable scheduling of resources is completed.The experimental results show that the proposed scheduling algorithm can correctly cluster the fog resources and obtain the user requirements and resources matching results.Compared with the traditional Min-min algorithm,the algorithm effectively improves the user satisfaction.(2)The resource algorithm based on improved bee colony algorithm in fog computing is designed.Firstly,the fog computing resource scheduling problem is described and the mathematical model of fog computing resource scheduling is established.Then,the chaos strategy is introduced to optimize the initialization of artificial bee colony algorithm,and thepopulation initialization formula using chaotic variables is obtained,which improves the defects of standard artificial bee colony algorithm to a certain extent.Finally,the improved algorithm is applied to solve the problem of resource scheduling in fog computing,and the optimal scheme of resource scheduling is obtained.The experimental results show that the improved bee colony algorithm has faster convergence speed.The proposed scheduling algorithm reduces the task completion time in the fog environment,and improves the scheduling performance of fog computing.
Keywords/Search Tags:Fog computing, Resource scheduling, Fuzzy clustering algorithm, Particle swarm optimization, Bee colony algorithm
PDF Full Text Request
Related items