Towards Distributed Architecture for Collaborative Cloud Services in Community Networks

Abstract

Abstract-Internet and communication technologies have lowered the costs for communities to collaborate, leading to new services like user-generated content and social computing, and through collaboration, collectively built infrastructures like community networks have also emerged. Community networks get formed when individuals and local organisations from a geographic area team up to create and run a community-owned IP network to satisfy the community's demand for ICT, such as facilitating Internet access and providing services of local interest. The consolidation of today's cloud technologies offers now the possibility of collectively built community clouds, building upon user-generated content and user-provided networks towards an ecosystem of cloud services. To address the limitation and enhance utility of community networks, we propose a collaborative distributed architecture for building a community cloud system that employs resources contributed by the members of the community network for provisioning infrastructure and software services. Such architecture needs to be tailored to the specific social, economic and technical characteristics of the community networks for community clouds to be successful and sustainable. By real deployments of clouds in community networks and evaluation of application performance, we show that community clouds are feasible. Our result may encourage collaborative innovative cloud-based services made possible with the resources of a community.Index Terms-cloud computing; community cloud; community networks; collaborative resource sharing I . I N T R O D U C T I O NThe recent developments in information and communication technologies have significantly reduced the barriers for communication, coordination and collaboration for individuals and communities. This not only gave rise to widely adopted applications like social networking and user-generated content among many others, but infrastructures based on a cooperative model have also been built, for example community wireless mesh networks [1], which gained momentum in early 2000s in response to limited options for network connectivity in rural and urban communities. Using off-the-shelf network equipment and open unlicensed wireless spectrum, volunteers teamed up to invest, create and run wireless networks in their local communities as an open telecommunication infrastructure based on self-service and self-management by the users. These community networks have proved quite successful, for example Guifi.net 1 provides wireless and optical fibre based broadband 1 http://guifi.net access to more than 20,000 users. Current community networks use mainly wireless technology to interconnect nodes. With the commoditization of optical fibre, some community networks however have also started providing broadband services combining both technologies. Community networks are a successful case of resource sharing among a collective, where resources shared are not only the networking hardware but also the time, effort and knowledge contributed...

Cloud services in the Guifi.net community network

“…This is achieved by adopting a layered architecture, as shown in Figure 2. context enablers [45] that take advantage of the social and economic characteristics of the community networks to encourage participation from community network members and to ensure sustainability of the community cloud model.…”

Incentive-based resource assignment and regulation for collaborative cloud services in community networks

“…The architecture for the cloud management platform that we propose for community networks consists of multiple layers [15], with different components at each layer, as shown in Figure 6.…”

On Supporting Service Selection for Collaborative Multi-cloud Ecosystems in Community Networks

“…We have studied earlier that storage applications like Tahoe-LAFS can have quite different performance depending upon configuration, location and capability of storage nodes, as evident from Figure 5 [3]. We evaluated the storage performance of Tahoe-LAFS in the community network in order to assess the impact of network latency, connectivity and bandwidth.…”

“…There are not many applications and services used by members of community networks that take advantage of resources available within community networks. To overcome this limitation, we envision a specific kind of a community cloud [2] in which sharing of computing resources is from within community networks, using the application models of cloud computing in general [3], [4]. When members of community network can share and trade resources based on a collaborative cloud computing model, they can provide their excess capacity to others as the demand fluctuates and in return can take advantage of services and applications that were not possible earlier due to the limited resources.…”

“…For example, incentive mechanisms inspired by the social nature of community networks [18] can be built into resource regulation component to encourage users to contribute resources [19], [20]. The architecture for the cloud management system that we propose for community networks consists of multiple layers, as shown in Figure 2 [3]. Here a DSS as part of the support services can prove pivotal in ensuring quality of experience for the members of the community networks, facilitating adoption of community cloud services.…”