Raymond Carroll

Dynamic Optimization Solution for Green Service Migration in Data Centres

While many aspects of the Future Internet are uncertain, one thing that is clear is that service demand will continue to rise. Also, advances in mobile devices and service technology will almost certainly cause service usage patterns to vary considerably. Another issue that the Future Internet community must be acutely aware of is the huge movement towards more sustainable forms of computing and communications technology. With the recent attention that has been put on IT energy consumption (data-centres in particular), all computing and communications systems need to consider their environmental impact from the outset. With that in mind, we propose a solution for determining the optimal placement of services in data-centre network, in order to maximize the overall renewable energy usage and minimize the cooling energy consumption. We then perform a series of experiments in order to evaluate our solution, incorporating dynamic service request profiles and actual weather and renewable energy production values.

Adaptive Dynamic Routing Supporting Service Management for Future Internet

There is currently much debate in defining what form the Future Internet will take [22, 23, 24]. The current Internet is struggling to meet the needs of an ever-evolving society. This is largely due to the Internet now become a thriving marketplace with services at the core. The range, number and complexity of services are set to increase with an even more dynamic service environment envisioned in the future. However, as these services grow, service composition will become an important feature of the service environment, leading to new challenges in service discovery and composition mechanisms. At the same time, dynamic service environments will also require that the underlying infrastructure networks are flexible enough to handle the changing service landscape. One area this is particularly important is in dynamic routing to deal with highly dynamic and frequent service changes. In this paper, we adopt mechanisms from biology and apply these to the problems identified, resulting in an integrated Bio-inspired service management and dynamic routing solution for Future Internet. We demonstrate how the bio-inspired mechanisms not only improve each problem individually, but through their integration also improve overall network performance. Simulation results are presented to validate the proposed solution.

Biologically inspired future service environment

In recent years, a major factor that has attracted numerous users to the Internet is services, and it is anticipated that this trend will continue into the future. As the Internet of the future becomes increasingly service centric, this brings with it a number of well established challenges. With large volumes of services, service discovery becomes one of the most decisive issues, and even fundamental tasks such the management and maintenance of services become challenging. Also, as services evolve and change to meet users demands, an efficient delivery mechanism (routing and resource management) is required in the underlying network. In order to address these challenges, this paper proposes an integrated bio-inspired service management and distributed routing solution for future service environments. The proposed solution will demonstrate how biological processes can improve both the individual layers of service management and underlying infrastructure, as well as improve overall performance when these two layers are integrated. Simulation results are presented to help validate the proposed solution.

Application of Genetic Algorithm to Maximise Clean Energy Usage for Data Centres

The communications industry is currently witnessing a continued increase in energy consumption, and this trend is predicted to increase even more in the coming years. This is largely driven by the popularity of the Internet, which continues to attract growing numbers of users who now rely on the Internet as part of their daily lives. A major factor behind this attraction is the multitude of services available on the Internet, ranging from web based services (e.g. facebook) to heavy power consuming services such as multimedia (e.g. youtube, IPTV). Therefore the data centres housing these services are seeing their energy consumption increase proportionally, now leading researchers to actively search for solutions to improve the energy efficiency of data centres. In this paper we propose a green data centre solution that makes data centres and services prioritise the usage of clean, renewable energy sources. The solution allows data centres to share information regarding renewable energy and cooling, in order to exploit variance between different countries energy and temperature profiles by moving services between data centres. We employ a genetic-algorithm to find the optimal placement of services on the data centres.

Towards a framework for network management applications based on peer-to-peer paradigms The CELTIC project Madeira

The Madeira project addresses a novel approach for the management of network elements of increasing number, heterogeneity and transience. As next-generation networks exhibit major challenges for todays centralized network management systems, we investigate the feasibility of a peer-to-peer (P2P) approach, facilitating self-management and dynamic behavior of elements within networks. In this short paper we give an overview of the system architecture developed in Madeira and describe the key concepts, like Madeira platform services, adaptive management components and policies that provide the base for building distributed network management applications

Policy-Based management and context modelling contributions for supporting services in autonomic systems

Autonomic networking systems dynamically adapt the services and resources that they provide to meet the changing needs of users and/or in response to changing environmental conditions. This paper presents a novel policy-based, context-aware, service management framework for ensuring the efficient delivery and management of next generation services using autonomic computing principles. The novelty of this approach is its use of contextual information to drive policy-based changes that adapt network services and resources. Policies control the deployment and management of services and resources, as well as the software used to create, manage, and destroy these services and resources. Policies also control the distribution and deployment of the necessary components for fully managing the service lifecycle, and provide the efficiency and scalability necessary for supporting autonomic systems.

Bio-inspired service management framework: green data-centres case study

The internet is evolving into a full-scale distributed service platform, offering a plethora of services from communications to business, entertainment, social connectivity and much more. The range of services and applications offered is diversifying, with new applications constantly emerging. For example, utility-based computing e.g. HPC and cloud computing which relies heavily on data-centre resources. These services will be more dynamic and sophisticated, providing a range of complex capabilities, which puts further burden on data-centres, in terms of supporting and managing these services. At the same time, society is becoming acutely aware of the significant energy burden the communications industry, and in particular data-centres, are becoming. With these trends in mind we propose a biologically inspired service framework that supports services which can autonomously carry out management functions. We then apply this framework to address the emerging problem of a sustainable future internet by autonomously migrating services to greener locations.

Bio-inspired Service Management Framework: Green Data-Centres Case Study

Following the huge growth in usage over the last 10 years, the Internet has become a critical business and social tool. In the future however, this popularity will continue to rise, with the Internet evolving into a full scale distributed service platform, offering a plethora of services from communications to business, entertainment and much more. These services will be more dynamic and sophisticated providing a range of complex capabilities. However, this dynamic service environment will lead to overwhelming management problems if not dealt with adequately. At the same time, society is now acutely aware of the significant energy burden the communications industry is becoming. With these two trends in mind we propose a biologically-inspired service framework which supports services intelligently solving a number of management problems. We then as a case study application, use this framework to address the new, emerging problem of a sustainable future internet by migrating services to new, greener locations.

The Effect of Community on Distributed Bio-inspired Service Composition

The Future Internet is expected to cater for both a larger number and variety of services, which in turn will make basic tasks such as service lifecycle management increasingly important and difficult. At the same time, the ability for users to efficiently discover and compose these services will become a key factor for service providers to differentiate themselves in a competitive market. In previous work, we examined the effect adding biological mechanisms to services had on service management and discovery. In this paper we examine the effects of community on services, specifically in terms of composing services in a distributed fashion. By introducing aspects of community we aim to demonstrate that services can further improve their sustainability and indeed their efficiency.

Semantic Integration of User Data - Models and Processes Enabling Seamless Mobility

The networks of the future are touted as being highly dynamic, allowing users a huge degree of mobility and flexibility. Seamless Mobility demonstrates networks where users move seamlessly between providers obtaining the best possible service experience. While a large focus in this area is on enabling handover, what is ultimately important is the impact of this on the user. In this paper we discuss a novel approach which does not focus on network handover but instead adopts a different view to the problem. We focus on selecting, configuring or reconfiguring a service to suit the users current situation based on a number of factors including user profiles, user preferences and the available network.