arXiv subjects

Felix Freitag

Publications and source records attributed to Felix Freitag.

4 recordsLinked to original sources

arXiv2017

Towards Decentralised Resilient Community Cloud Infrastructures

Recent years have seen a trend towards decentralisation - from initiatives on decentralized web to decentralized network infrastructures (e.g community networks). In this position paper, we present an architectural vision for decentralising cloud service infrastructures. Our vision is on the notion of community cloud infrastructures on top of decentralised access infrastructures i.e. community networks, using resources pooled from the community. Our architectural vision takes into consideration some of the fundamental challenges of integrating the current state of the art virtualisation technologies such as Software Defined Networking (SDN) into community infrastructures which are highly unreliable. Our proposed design goal is to include lightweight virtualization and fault tolerance mechanisms into the architecture to ensure sufficient level of reliability to support critical applications.

cs.DC↗

arXiv2017

Gelly-Scheduling: Distributed Graph Processing for Network Service Placement in Community Networks

Community networks (CNs) have seen an increase in the last fifteen years. Their members contact nodes which operate Internet proxies, web servers, user file storage and video streaming services, to name a few. Detecting communities of nodes with properties (such as co-location) and assessing node eligibility for service placement is thus a key-factor in optimizing the experience of users. We present a novel solution for the problem of service placement as a two-phase approach, based on: 1) community finding using a scalable graph label propagation technique and 2) a decentralized election procedure to address the multi-objective challenge of optimizing service placement in CNs. Herein we: i) highlight the applicability of leader election heuristics which are important for service placement in community networks and scheduler-dependent scenarios; ii) present a parallel and distributed solution designed as a scalable alternative for the problem of service placement, which has mostly seen computational approaches based on centralization and sequential execution.

cs.DC↗

arXiv2016

A Distributed Auctioneer for Resource Allocation in Decentralized Systems

In decentralized systems, nodes often need to coordinate to access shared resources in a fair manner. One approach to perform such arbitration is to rely on auction mechanisms. Although there is an extensive literature that studies auctions, most of these works assume the existence of a central, trusted auctioneer. Unfortunately, in fully decentralized systems, where the nodes that need to cooperate operate under separate spheres of control, such central trusted entity may not exist. Notable examples of such decentralized systems include community networks, clouds of clouds, cooperative nano data centres, among others. In this paper, we make theoretical and practical contributions to distribute the role of the auctioneer. From the theoretical perspective, we propose a framework of distributed simulations of the auctioneer that are Nash equilibria resilient to coalitions and asynchrony. From the practical perspective, our protocols leverage the distributed nature of the simulations to parallelise the execution. We have implemented a prototype that instantiates the framework for bandwidth allocation in community networks, and evaluated it in a real distributed setting.

cs.GT↗

arXiv2016

Bandwidth-aware Service Placement in Community Network Clouds

Seamless computing and service sharing in community networks have been gaining momentum due to the emerging technology of community network micro-clouds (CNMCs). However, running services in CNMCs can face enormous challenges such as the dynamic nature of micro-clouds, limited capacity of nodes and links, asymmetric quality of wireless links for services, deployment mod- els based on geographic singularities rather than network QoS, and etc. CNMCs have been increasingly used by network-intensive services that exchange significant amounts of data between the nodes on which they run, therefore the performance heavily relies on the available bandwidth resource in a network. This paper proposes a novel bandwidth-aware service placement algorithm which out- performs the current random placement adopted by Guifi.net. Our preliminary results show that the proposed algorithm consistently outperforms the current random placement adopted in Guifi.net by 35% regarding its bandwidth gain. More importantly, as the number of services increases, the gain tends to increase accordingly.

cs.NI↗