Towards Autonomic Computing: Adaptive Job Routing and Scheduling

Journal of Scientific and Engineering Research, 2024

In the backdrop of the growing demand for network capacity and performance, the traditional optimization strategies are often found unfit to deal with complex and dynamic network environments. This study explores the use of machine learning (ML) techniques for improving network performance highlight their ability to read through large datasets, and recognize patterns, and can make real-time decisions. We study different machine learning methods, their application in network conditions, and the advantages they provide regarding network optimization. The findings reveal that machine learning can considerably boost the network's efficiency, reliability, and user experience. Besides, we look into the problems and future opportunities for the introduction of machine learning to network management systems.

Computer systems are rapidly becoming so complex that maintaining them with human support staffs will be prohibitively expensive and inefficient. In response, visionaries have begun proposing that computer systems be imbued with the ability to configure themselves, diagnose failures, and ultimately repair themselves in response to these failures. However, despite convincing arguments that such a shift would be desirable, as of yet there has been little concrete progress made towards this goal. We view these problems as fundamentally machine learning challenges. Hence, this article presents a new network simulator designed to study the application of machine learning methods from a system-wide perspective. We also introduce learning-based methods for addressing the problems of job routing and CPU scheduling in the networks we simulate. Our experimental results verify that methods using machine learning outperform reasonable heuristic and hand-coded approaches on example networks designed to capture many of the complexities that exist in real systems.

Lecture Notes in Computer Science, 2005

The increasing scale complexity, heterogeneity and dynamism of networks, systems and applications have made our computational and information infrastructure brittle, unmanageable and insecure. This has necessitated the investigation of an alternate paradigm for system and application design, which is based on strategies used by biological systems to deal with similar challengesa vision that has been referred to as autonomic computing. The overarching goal of autonomic computing is to realize computer and software systems and applications that can manage themselves in accordance with high-level guidance from humans. Meeting the grand challenges of autonomic computing requires scientific and technological advances in a wide variety of fields, as well as new software and system architectures that support the effective integration of the constituent technologies. This paper presents an introduction to autonomic computing, its challenges, and opportunities.

WSEAS Transactions on Communications

The eagerness of Internet and Intranet computing applications has fueled the complexity of the network administration tasks. Nowadays, the network management tools have usually insufficient resources to monitor the complexity of computer networks. The majority of the agents used in computer networks are passive agents, i.e., they have no autonomy, nor participate in the decision-making procedures. We have assessed multiple artificial intelligence (AI) techniques to improve network management systems, according to the autonomic computing concept introduced by IBM. In this paper, we present a methodology for agent's development based on artificial intelligence techniques. The reported results show that the proposed methodology is adequate to support the development of active agents.

2020

IEEE Transactions on Network and Service Management

IEEE Access, 2021

Communication networks are expanding rapidly and becoming increasingly complex. As a consequence, the conventional rule-based algorithms or protocols may no longer perform at their best efficiencies in these networks. Machine learning (ML) has recently been applied to solve complex problems in many fields, including finance, health care, and business. ML algorithms can offer computational models that can solve complex communication network problems and consequently improve performance. This paper reviews the recent trends in the application of ML models in communication networks for prediction, intrusion detection, route and path assignment, Quality of Service improvement, and resource management. A review of the recent literature reveals extensive opportunities for researchers to exploit the advantages of ML in solving complex performance issues in a network, especially with the advancement of softwaredefined networks and 5G.

2023

In the realm of telecommunications, maintaining robust network performance and ensuring service reliability are critical to customer satisfaction and operational efficiency. With the increasing complexity of telecom networks and the growing volume of data they generate, traditional methods of troubleshooting and maintenance have become insufficient for managing network health proactively. This paper explores the transformative role of machine learning (ML) in predictive troubleshooting within telecom networks, offering a comprehensive examination of how advanced algorithms can enhance network management through proactive identification of potential issues. Machine learning algorithms have emerged as pivotal tools in the analysis of extensive and complex network data sets. By leveraging historical and real-time data, these algorithms identify patterns and anomalies that precede network disruptions or failures. This predictive capability allows for early intervention, significantly mitigating the risk of downtime and service degradation. The paper delves into various ML techniques, including supervised learning, unsupervised learning, and reinforcement learning, elucidating their application in predictive analytics for telecom networks.

2020

Network resource management is one of the vibrant factors in the current dynamic technological computing paradigms. This reduces poor resource utilization; network resources include network devices, management networks, management systems, and management support organizations carrying out task planning, resource scheduling, and network managing among many more. It's now been observed within different networks that machine learning has been applied to help in carrying some network tasks. This paper surveys current approaches that have been done in managing resources with a deep focus on energy optimization, auto-scaling methods based on current machine learning approaches. We further present the proposed techniques that are identified by evolving this overview by investigating other state-of-the-art recommendations. This study provides a deep insight into proposed methods, loopholes that will aid researchers to design, model, or create novel frameworks that focus on the better op...

IEEE Transactions on Network and Service Management, 2020

I. INTRODUCTION N ETWORK and Service analytics can harness the immense stream of operational data from clouds, to services, to social and communication networks. In the era of big data and connected devices of all varieties, analytics and machine learning have found ways to improve reliability, configuration, performance, fault and security management. In particular, we see a growing trend towards using machine learning, artificial intelligence and data analytics to improve operations and management of information technology services, systems and networks. Research is therefore needed to understand and improve the potential and suitability of data analytics and machine learning in the context of services, systems and network management. This will provide deeper understanding and better decision making based on largely collected and available operational and service data. It will also present opportunities for improving machine learning and data analytics algorithms and methods on aspects such as reliability, dependability and scalability, as well as demonstrate the benefits of these methods in management and control systems. Moreover, there is an opportunity to define novel platforms that can harness the vast operational data and advanced data analysis algorithms to drive management decisions in networks, data centers, and clouds.