Growing interest in Cloud Computing places a heavy workload on cloud providers which is becoming increasingly difficult for them to manage with their primary datacenter infrastructures. Resource limitations can make providers vulnerable to significant reputational damage and it often forces customers to select services from the larger, more established companies, sometimes at a higher price. Funding limitations, however, commonly prevent emerging and even established providers from making continual investment in hardware speculatively assuming a certain level of growth in demand. As an alternative, they may strive to use the current inter-cloud resource sharing platforms which mainly rely on monetary payments and thus putting pressure on already stretched cash flows. To address such issues, we have designed and implemented a new multi-agent based Cloud Resource Bartering System (CRBS) that fosters the management and bartering of pooled resources without requiring costly financial transactions between providers. Agents in CRBS not only strengthen the trading relationship among providers but also enable them to handle surges in demand with their primary setup. Unlike existing systems, CRBS assigns resources by considering resource urgency which comparatively improves customers satisfaction and the resource utilization rate by more than 50%.The evaluation results provide evidence that our system assists providers to timely acquire the additional resources and to maintain sustainable service delivery. We conclude that the existence of such a system is economically beneficial for cloud providers and enables them to adapt to fluctuating workloads.
The ever growing cloud popularity is placing heavy workloads on cloud providers and is making resource provisioning crucialfor them as revealed by recent reports [1]. In the near future, this issue is expected to grow in both number and severity due to the constant expansion of cloud workloads [3,4]. At present, many providers claim infinite scalability but in practice, this cannot be realized as they all have finite resources in their datacentres. Hardware capacity limitations or periods of maintenance make the satisfaction of dynamically changing levels of requestors' demands difficult to manage. As a result, providers could be forced to reject requests for resources which may damage their reputations for reliability.
In order to scale up providers’ capacity, existing cloud solutions (i.e. cloud federation) offer inter-cloud resource sharing on a monetary basis [5,6,7]. Price based resource exchange is daunting for providers with limited capital as instead of paying others they may prefer to invest in the expansion of their own data centres. However, in addition to the environmental and economic costs, the scaling of infrastructures has further implications as it may lead towards resource over-provisioning [8].
In response to these problems, it is clear that a flexible resource bartering system is required, which can expand providers’ capacities without any need for financial transaction. Resource bartering can help providers to initially borrow resources from their counterparts and then to pay the debt by contributing their resources in future when they become available. This enables providers with tight budgets to augment their physical resources and to thereby handle peak demand from their customers. To realize this concept, an alliance of cloud providers each having different levels of resource demand is created to barter resources with each other. This will not only reduce resource under/over-provisioning problems but will also help emerging providers to ensure long-term service availability. Despite having several benefits, the capability of bartering to assist cloud providers in managing their resource levels has not been well explored yet. Although it is considered an oldermodel of exchange, however, its trend has never gone out of fashion [9]. To demonstrate the validity of bartering in addressing the resource limitation problem of cloud providers, a new multi-agent based Cloud Resource Bartering System (CRBS) for Infrastructure as a Service (IAAS) cloud providers is presented in this paper. It is different from the existing cloud federation in several aspects, for example, it enables a price-free computational resource (i.e. virtual machine)exchange among providers while preserves the autonomy of their technological and business management decisions. To better utilize idle resources, unlike existing systems [5,6,7], CRBS prioritizes the most urgent requests and thus enables needy providers to maintain consistent service delivery by getting resources immediately.
The other contributions of this work are: 1) Exploiting multi-agent system’s efficiency to gather resources from the participating providers and to provide automatic resource matching. In contrast, current systems force requestors to search and compare each and every resource offer listed in the information directory manually. This is a challenging task when a number of options are available and especially when resources are quickly running out.2) Reserving privileges for altruistic participants (i.e. those who frequently share their resources) within the system. The reward mechanism is necessary to keep the system functional as it motivates the other participants of the system to collaborate actively. To the best of our knowledge, these features altogether have not been incorporated in any of the existing cloud systems and produce an approach that has never been used before. The effectiveness of the CRBS has been assessed by comparing it with the existing inter-cloud resource sharing systems. For evaluation purposes, several testing metrics which are commonly considered crucial for the success of a cloud marketplace have been evaluated. The experimental results validate the devised system ability to effectively barter resources under various scenarios. The remainder of the paper is structured as follows: Section 2 presents the work related to the existing resource sharing systems. Based on the literature review, the architecture and working of CRBS are presented in Sections3 and 4. The evaluation results have been compiled in Section 5 followed by the conclusion and future work.
Cloud computing has found applications in many fields including e-business and e-education [10]. To assist the scientific community in performing the resource-intensive tasks, Cloud@Home was introduced [11]. It enabled the sharing of virtual machines that were owned by individual users to perform complex tasks. Voluntarily sharing resources without an incent
This content is AI-processed based on open access ArXiv data.