International Journal of Computer Applications (0975 – 8887) Volume 9– No.9, November 2010 1 Green Cloud: An Algorithmic Approach K.Mukherjee Department of Computer Science & Engineering Birla Institute of Technology Mesra, Ranchi,India G.Sahoo Department of Information Technology Birla Institute of Technology Mesra, Ranchi, India ABSTRACT Cloud computing has opened a new era to a shared IT infrastructure in which large pools of systems are linked together via the internet to provide IT services, such as different utility services of our day to day lives like tax calculation web services, weather information web services etc; which are on pay per user basis. It provides a virtual resource and therefore is not limited by the power and capabilities of local or remote computers. But cloud computing is in its nascent stage of progression. It has some serious demerits. The data centre hosting cloud application needs huge consumption of energy, which is subsequently responsible for the emission of carbon dioxide gas, which aggravates global warming-a threat to existence of life on earth. In this paper, we propose eco-friendly cloud computing which will not only mitigate global warming but also minimize operational cost by reducing power consumption. Here we have introduced noble algorithm for proper utilization of energy for cloud computing. We have validated our study by a set of experiments using Ubuntu’s 10.04 Server editions. Keywords Cloud computing, eco-friendly, bee colony algorithm, ant colony algorithm etc. 1. INTRODUCTION Cloud computing [16] has given a new orientation of computing based on “pay as you use” model . It is capable to provide massive computing or storage resources without the need to invest money or face the trouble to build or maintain such huge resources. The consumers only need to pay for using the services just like they do in case of other day to day utility services such as water, gas, electricity etc, which are on pay per user basis and hence our cloud computing resources are also on pay per user basis. Actually Cloud computing provides a platform for the execution of massive tasks on cloud instead of the execution of tasks on users’ Personal Computers, Servers etc. It is very beneficial for small organizations that cannot afford huge investment on their IT sector but at the same time expect maximum benefit from this supporting industry in order to survive in today’s complex competitive business world. Cloud computing can help such organizations by providing massive computing power, unlimited storage capacity, less maintenance cost, availability of useful web-services etc. As per Buyya et. all [7], “A Cloud is a type of parallel as well as distributed system consisting of a collection of interconnected and virtualized computers that are dynamically provisioned and presented as one or more unified computing resources based on service-level agreements established through negotiation between the service provider and consumer”. The definition clearly implies that there is a Service Level Agreement (SLA) between the provider and the consumer for getting services from cloud on pay per user basis. Actually Cloud computing offers three layers of abstraction such as Infrastructure as a Service (IaaS), Platform as a Service (PaaS), Software as a Service (SaaS). SaaS provides different types of applications as a Service for the end user. It includes different useful web-services. PaaS provides a standard platform for better execution of application with proper exploitation of physical resources using Middleware Services. PaaS includes Database services, Middleware Services etc. In this endeavor we intend to throw light on Platform as a Service (PaaS). IaaS provides the hardware infrastructure of cloud consisting of physical machines like clusters, datacenters etc to provide resources in order to meet the consumer’s request on demand. Again middleware of PaaS consists of core middleware and user level middleware. The core middleware exploits IaaS [7] at its best level to fulfill consumer’s demand, whereas the user level middleware provides the access point of services as delivered by the core middleware. It is observed that maintaining IaaS including their cooling involves a lot of energy consumption, thereby enhancing global warming by emission of huge carbon oxide and other related gases. There is a growing concern across the world to arrest the trend towards global warming by reducing these parameters which are responsible for it. Thus in an era of ecological degradation, the future of cloud computing is bright provided it is eco-friendly in nature. In this endeavor, we intend to throw some light on eco-friendly cloud computing. Organization of this paper is as follows: Related Work is discussed in section 2. Proposed Frame Work of Eco-Friendly Cloud Computing is discussed in section 3. Proposed algorithm is discussed in section 4. Section 5 gives details of the Experimental Results. Section 6 gives the Conclusion with a direction of the Future Work. 2. RELATED WORK The potentiality of computing utility was first pointed by Leonard Kleinrock[1], one of the pioneer researcher, who seeded the idea of internet. He had predicted long back, regarding the wide use of “computer utilities” as our day to day utilities like “Electrical Utilities”, “Telephone Utilities” etc. Today, his visi on came into existence in the form of cloud computing. Cloud computing provides different utilities in the form of web- services, which are on pay per user basis. Most of the existing work in web service performance focuses on the latest trend of technologies and standards. Andreozzi et al. [2] present a model for rigorous representation of service characteristics. Gouscos et