Distributed resource allocation in cloud computing using multi-agent systems

Mazrekaj, Artan; Minarolli, Dorian; Freisleben, Bernd

doi:10.5937/telfor1702110m

Cited by 8 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…• Resource management, allocating and optimising the use of resources to complete a task. For example, managing energy usage while performing a function within a physical environment [15,32,45].…”

Section: Introductionmentioning

confidence: 99%

Dynamic neighbourhood optimisation for task allocation using multi-agent

Creech¹,

Criado²,

Miles³

2021

Preprint

View full text Add to dashboard Cite

In large-scale systems there are fundamental challenges when centralised techniques are used for task allocation. The number of interactions is limited by resource constraints such as on computation, storage, and network communication. We can increase scalability by implementing the system as a distributed task-allocation system, sharing tasks across many agents. However, this also increases the resource cost of communications and synchronisation, and is difficult to scale.In this paper we present four algorithms to solve these problems. The combination of these algorithms enable each agent to improve their task allocation strategy through reinforcement learning, while changing how much they explore the system in response to how optimal they believe their current strategy is, given their past experience. We focus on distributed agent systems where the agents' behaviours are constrained by resource usage limits, limiting agents to local rather than system-wide knowledge. We evaluate these algorithms in a simulated environment where agents are given a task composed of multiple subtasks that must be allocated to other agents with differing capabilities, to then carry out those tasks. We also simulate real-life system effects such as networking instability. Our solution is shown to solve the task allocation problem to 6.7% of the theoretical optimal within the system configurations considered. It provides 5× better performance recovery over no-knowledge retention approaches when system connectivity is impacted, and is tested against systems up to 100 agents with less than a 9% impact on the algorithms' performance.

show abstract

Section: Introductionmentioning

confidence: 99%

Dynamic neighbourhood optimisation for task allocation using multi-agent

Creech¹,

Criado²,

Miles³

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…A run-time environment is provided by JADE, where agents can live, destroy, and communicate with each other. Agents have the behaviors of autonomy, reactivity, proactivity, and social behavior [21] throughout their lives. JADE supports all the features of an object-oriented language.…”

mentioning

confidence: 99%

A Proposed Architecture for Local-Host and AWS with Multiagent System

Chawla¹,

Ahlawat²

2023

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

Cloud computing has become one of the leading technologies in the world today. The benefits of cloud computing affect end users directly. There are several cloud computing frameworks, and each has ways of monitoring and providing resources. Cloud computing eliminates customer requirements such as expensive system configuration and massive infrastructure while improving dependability and scalability. From the user's perspective, cloud computing makes it easy to upload multiagents and operate on different web services. In this paper, the authors used a restful web service and an agent system to discuss, deployments, and analysis of load performance parameters like memory use, central processing unit (CPU) utilization, network latency, etc., both on localhost and an Amazon Web Service Elastic Cloud Computing (AWS-EC2) server. The Java Agent Development Environment (JADE) tool has been used to propose an architecture and conduct a comparative study on both local and remote servers. JADE is an open-source tool for maintaining applications on AWS infrastructure. The focus of the study should be to reduce the complexity and time of load performance parameters by using an agent system on a cloud server instead of establishing a massive infrastructure on a local system, even for a small application.

show abstract

A Survey on Cloud Resources Allocation Using Multi-agent System

Jowda

Al-Asfoor

2021

Expert Clouds and Applications

View full text Add to dashboard Cite

Distributed resource allocation in cloud computing using multi-agent systems

Cited by 8 publications

References 14 publications

Dynamic neighbourhood optimisation for task allocation using multi-agent

Dynamic neighbourhood optimisation for task allocation using multi-agent

A Proposed Architecture for Local-Host and AWS with Multiagent System

A Survey on Cloud Resources Allocation Using Multi-agent System

Contact Info

Product

Resources

About