Decentralized Job Scheduling in the Cloud Based on a Spatially Generalized Prisoner’s Dilemma Game

Abstract

We present in this paper a novel distributed solution to a security-aware job scheduling problem in cloud computing infrastructures. We assume that the assignment of the available resources is governed exclusively by the specialized brokers assigned to individual users submitting their jobs to the system. The goal of this scheme is allocating a limited quantity of resources to a specific number of jobs minimizing their execution failure probability and total completion time. Our approach is based on the Pareto dominance relationship and implemented at an individual user level. To select the best scheduling strategies from the resulting Pareto frontiers and construct a global scheduling solution, we developed a decision-making mechanism based on the game-theoretic model of Spatial Prisoner's Dilemma, realized by selfish agents operating in the two-dimensional cellular automata space. Their behavior is conditioned by the objectives of the various entities involved in the scheduling process and driven towards a Nash equilibrium solution by the employed social welfare criteria. The performance of the scheduler applied is verified by a number of numerical experiments. The related results show the effectiveness and scalability of the scheme in the presence of a large number of jobs and resources involved in the scheduling process.

A Survey of Swarm Intelligence Based Load Balancing Techniques in Cloud Computing Environment

“…It also refers applications that need more time, and relative to other jobs, it gives preference to tasks that need immediate execution [21]. Other load balancing goals include reducing energy consumption, avoiding bottlenecks, providing resources, and meeting QoS criteria for improving load balancing [22]. Proper workload mapping and load balancing strategies that consider various metrics require consideration.…”

Massive Data Balance Scheduling in Cloud Computing Environment

“…According to the principle of clonal selection, the attributes of the massive data in the cloud computing environment are defined as antigens, and the antibody encoding mode of the massive data balance scheduling is designed. Meanwhile, the individual data with the higher affinity to the antigens are selected from the antibody for mutation treatment, and the balance of massive data scheduling is quantified in cloud computing environment [16]. According to the different attribute characteristics of massive data, the corresponding distribution strategy is put forward, so as to construct the massive data balance scheduling model in the cloud computing environment.…”

“…According to the parameter of data balance scheduling, the corresponding delay response parameter  and the data flow control parameter  can be selected and determined. The parameter solving process is: (16) Thus it obtains the model of massive data balance scheduling in the cloud computing environment:…”

A Comprehensive Study on Load Balancing Algorithms in Cloud Computing Environments

“…The token generation model is heuristic and finds optimal providers with agent's partial observation to global load distribution. Gasior and Seredynski (2012) proposed an load balancing method in cloud computing system through formation of coalitions in a spatially generalized prisoner's dilemma game. This method is highly parallel and distributed which works in environments where local information alone is available.…”