Martin Randles

A Comparative Study into Distributed Load Balancing Algorithms for Cloud Computing

The anticipated uptake of Cloud computing, built on well-established research in Web Services, networks, utility computing, distributed computing and virtualisation, will bring many advantages in cost, flexibility and availability for service users. These benefits are expected to further drive the demand for Cloud services, increasing both the Clouds customer base and the scale of Cloud installations. This has implications for many technical issues in Service Oriented Architectures and Internet of Services (IoS)-type applications; including fault tolerance, high availability and scalability. Central to these issues is the establishment of effective load balancing techniques. It is clear the scale and complexity of these systems makes centralized assignment of jobs to specific servers infeasible; requiring an effective distributed solution. This paper investigates three possible distributed solutions proposed for load balancing; approaches inspired by Honeybee Foraging Behaviour, Biased Random Sampling and Active Clustering.

Energy Efficient Cloud Computing Environment via Autonomic Meta-director Framework

The ever-increasing density in cloud computing users, services, and data centres has led to significant increases in network traffic and the associated energy consumed by its huge infrastructure, e.g. extra servers, switches, routers, which is required to respond quickly and effectively to users requests. Transferring data, via a high bandwidth connection between data centres and cloud users, consumes even larger amounts of energy than just processing and storing the data on a cloud data centre, and hence producing high carbon dioxide emissions. This power consumption is highly significant when transferring data into a data centre located relatively far from the users geographical location. Thus, it became high-necessity to locate the lowest energy consumption route between the user and the designated data centre, while making sure the users requirements, e.g. response time, are met. This paper proposes a high-end autonomic meta-director framework to find the most energy efficient route to the green data centre by utilising the linear programming approach. The framework is, first, formalised by the situation calculus, and then evaluated against shortest path algorithm with minimum number of nodes traversed.

Towards a systemic approach to autonomic systems engineering

An autonomic system is structured as a network of autonomic elements that collaborate to achieve the systems purpose. This paper examines the potential benefit of using well-established systems concepts and techniques in the development of such systems. In particular, it considers the possible role of Checklands Soft Systems Methodology and Beers Viable Systems model in system design. The paper summarizes the relevant aspects of each approach and then assesses both their individual and joint strengths in support of the construction and evaluation of designs. Some practical issues in the use of these approaches are also identified. The discussion is illustrated using aspects of the design of an autonomic operating system.

A principled approach to the design of healthcare systems: Autonomy vs. governance

In this paper, we look at decision support for post-operative breast cancer care. Our main concerns are to support autonomy of decision making whilst maintaining the governance and reliability of the decision-making process. We describe the context of our work in the wider medical setting. We then present a set of decision support tools based on the situation calculus as a means of maintaining the integrity of rule bases underlying the decision-making system. The decision support system, Neptune, allows for the authoring, maintenance and delivery of decisions in a self-governing framework. Finally we discuss the implications of our work.

Adjustable deliberation of self-managing systems

In this paper a cybernetics-based viable system architectural model is introduced, which provides a blueprint for high-assurance systems and a meta-control model necessary for the adjustable deliberation and autonomy of self-managing systems. The logical formalism is provided by the Situation Calculus and underpinned by an Enhanced Belief-Desires-Intentions (EBDI) framework to facilitate the representation and reasoning of scaleable autonomic computing systems.

E-Government Information Systems and Cloud Computing (Readiness and Analysis)

A new wave of the IT revolution, e-government, presents a tremendous opportunity to move forward providing higher quality, and cost-effective government services as well as creating a better relationship between citizens and government. The literature review, presented in this paper however, indicated that e-government readiness is a major concern, and that currently there is little availability of comprehensive assessment methods for e-government readiness and most of the assessment frameworks, reviewed for this study, are varied in terms of philosophies, objectives, methodologies, approaches, and results. To this end, this research aims to develop a comprehensive framework of associated guidelines and tools to support E-government Information Systems (EGIS) readiness, with a specific focus on the EGIS migration to the Cloud Computing provisioning model.

Biased random walks on resource network graphs for load balancing

The currently emerging large-scale complex networks and networks of networks are becoming apparent in the pervasive supply of seamless and transparent access to heterogeneous resources and services such as network domains, applications, services and storage owned by multiple organizations. The dynamics and heterogeneous environments involved, however, pose many challenges for controlling and balancing resource access, composition and deployment across complex grid and network infrastructures. In this paper, a scheme is proposed that gives a distributed load-balancing scheme by generating almost regular resource allocation networks. This network system is self-organized and depends only on local information for load distribution and resource discovery. The in-degree of each node refers to its free resources, and the job assignment and resource discovery processes required for load-balancing are accomplished by using fitted random sampling. Simulation results show that the generated network system provides an effective, scalable, and reliable load-balancing scheme for the distributed resources in grids and networks. The proposed solution is tested with real world data and the performance is tested against a recently reported distributed algorithm for load balancing.

Addressing the Signal Grounding Problem for Autonomic Systems

This paper is concerned with the problem of intrinsically assigning meaning to the signals responsible for autonomic responses in a system. Without an associated cognitive system, the symbol grounding problem would constitute a major barrier in system adaptation and evolution. Based on an ongoing effort towards a formal and pragmatic development of self-regenerative software systems, this paper adopts concepts from artificial immune systems (AIS) engineering, information theory and the situation calculus dialect of predicate logic. These are used to formalise the monitoring and control of system autonomic functions. In this way danger signals as an immune (self-healing/protecting) response and evolutionary (self-adapting) responses can be formalised into autonomic conditional and anticipatory reaction triggers. Thus any threat or potential enhancement to the system can be monitored for and the appropriate action taken to facilitate system dependability and safety

Cross Layer Dynamics in Self-Organising Service Oriented Architectures

This paper assesses and analyses the in and cross layer dynamics engendered by the engineering of self-organisation in one layer of a global Service Oriented Architecture currently emerging as the Internet of Services. A resource allocation algorithm is implemented at the application (business services) layer and its impact is investigated across this layer and the resource (business function) layer through the analysis of the service (server) compositions (digital ecosystem) arising and its associated partitioning into task specific teams (communities). Beneficial self-organisation is shown to ensue in a remote layer from the initially instigated engineered self-organisation.

Towards an Advanced Framework for Whole Body Interaction

Whole Body Interaction has emerged in recent years as a discipline that integrates the physical, physiological, cognitive and emotional aspects of a persons complete interaction with a digital environment. In this paper we present a framework to handle the integration of the complex of input signals and the feedback required to support such interaction. The framework is based on the principles of Autonomic Computing and aims to provide adaption and robustness in the management of whole body interaction. Finally we present some example case studies of how such a framework could be used.