Grid Quality of Service Trustworthiness Evaluation Based on Bayesian Network

Abstract

Quality of Service (QoS) is applied to evaluate the satisfaction level of users using a service and it is a measure and evaluation of the service level of service providers. As one of the significant contents of grid technologies, the QoS has gradually become a focus of current Internet researches. The grid is a network infrastructure that can aggregate decentralized resources to form a higher-level distributed resource sharing environment; the highly dynamic performance presented by the grid system is caused by resource competition and task uncertainty and providing extraordinary QoS is one of the three criteria for evaluating the grid technologies. Bayesian network is a method of graphing knowledge and is a probabilistic model which can be calculated; data from various sources can be synthesized and comprehensively reasoned through this Bayesian network. On the basis of summarizing and analyzing previous research works, this paper expounds the development background, current situation and future challenges of Bayesian network technology, presents the studying status and existing problems of grid QoS trustworthiness evaluation, introduces network optimization analysis method and QoS trustworthiness evaluation algorithm, proposes the Bayesian network-based trustworthiness model, effectiveness function and grid QoS evaluation reasoning process, therefore, establishes grid QoS trustworthiness evaluation model and analyzes Bayesian networkbased QoS trustworthiness evaluation mechanism. The simulation results show that the proposed method can enhance the trustworthiness of service information and improve the rationality of service matching in a dynamic service grid environment. The study results of this paper provide a reference for the further researches on the grid QoS trustworthiness evaluation based on Bayesian network. INDEX TERMS Quality of Service (QoS), Bayesian network, trustworthiness evaluation, simulation experiment.

SparkGrid: Blockchain Assisted Secure Query Scheduling and Dynamic Risk Assessment for Live Migration of Services in Apache Spark based Grid Environment

“…Authors in [36] proposed an adaptive security architecture structure for protecting identity federations. Here, heterogeneous request are not consider that leads to high response time at the time of handling heterogeneous request that reduces QoS [37], [39]. Here, all the information are stored in a centralized manner that leads to single point of failure.…”

“…Authors in [38] proposed entropy based fractal transform to improve fault tolerance and load balancing in grid computing environment. This research faces high complexity because of not evaluating the legitimacy of the request that leads to high overload and poor security [39].Here, jobs request are stored in a tree structure database that is suitable for only small scale environment, because large scale environment processed multiple request in a specific time that increase searching latency due to high child nodes. Grid quality of service trustworthiness is evaluated using Bayesian network [39].Trustworthiness of service providers is calculated based on QoS which is not effective, since when the risk value of service providers is low, it does not handle large amount of requests.…”

“…This research faces high complexity because of not evaluating the legitimacy of the request that leads to high overload and poor security [39].Here, jobs request are stored in a tree structure database that is suitable for only small scale environment, because large scale environment processed multiple request in a specific time that increase searching latency due to high child nodes. Grid quality of service trustworthiness is evaluated using Bayesian network [39].Trustworthiness of service providers is calculated based on QoS which is not effective, since when the risk value of service providers is low, it does not handle large amount of requests. Agent based decentralized grid structure is proposed to overwhelm the drawbacks of the centralized grid structure [40].This research used traditional decentralized grid model that takes much time to complete the process of scheduling and resource allocation that increase high latency.…”

“…Based on the optimal agent, position of emperor penguin is updated which is defined as follows, 𝑈 ⃑ ⃑⃑ 𝑒𝑝 (𝑢 + 1) = 𝑈 ⃑ ⃑⃑ (𝑢) − 𝑈 ⃑ ⃑⃑ . 𝐶 ⃑ 𝑒𝑝 (39) Worker Performance Metrics…”

“…The proposed SparkGrid is evaluated by comparing with the previous approaches such as RL-Grid [37], Bayesian-Grid [39], Agent-Grid [40] in terms of makespan, failure rate, grid utilization, resource prediction accuracy, request start time, risk of worker, memory usage, response time and resource availability.…”