Recently, LoRa mesh networks have appeared as a communication technology for Internet of Things (IoT) devices. Through node-to-node communication, novel distributed IoT applications that extend beyond the capabilities of the LoRaWAN architecture can be enabled. However, current technologies for LoRa networks do not provide mechanisms for large and reliable data transfers between IoT nodes. This paper presents a service for such data transfers in LoRa mesh network applications, along with the protocol and formats used for inter-node communication. We explain the design choices and detail the implementation decisions to ensure that this service is practically usable. To this end, the service was integrated into the LoRaMesher library and is available as an open-source operational implementation. In experiments with ten real nodes and two network topologies, we observe that the service effectively achieves a large and reliable message delivery in an environment of concurrent transmissions and packet losses. In contrast, the cost of reliability for large data transfers is an increased number of messages and a higher delivery time. With the integration of the service into the LoRaMesher technology, developers now have a library that provides a reliable and large payload service for LoRa mesh network applications, eliminating the need to develop such capacity as a specific application-level solution.

LoRa mesh networks have recently gained an increasing interest to extend traditional LoRaWAN-based IoT applications. The mesh technology introduces the capacity of multi-hop and node-to-node communication in LoRa networks. This more sophisticated network service delivered by LoRa mesh networks compared to LoRaWAN raises the need for network management, to understand the situation of the different nodes that operate as routers and hosts of applications. In this paper, we present a monitoring solution for a LoRa mesh network that not only passively collects data about the nodes for visualization, but also allows Internet services to actively send queries to any network node to ask for its values. We show a proof of feasibility of the monitoring system with the deployment of real IoT boards and operational services.

Recently, LoRa mesh networks have gained increasing interest as a communication layer for sending data between IoT nodes. However, the network service of the firmware on the microcontroller-based nodes is typically limited to sending and receiving LoRa packets through the LoRa radio. Therefore, the packet processing by the node has to be done using an application-specific implementation. In this article, we present the design and implementation of a middleware that facilitates the development and operation of multiple distributed applications on LoRa mesh network nodes. The components we propose leverage the routing capacity of a LoRa mesh network enabled by the LoRaMesher library and provide a service for applications to send and receive messages from each other. Running several applications concurrently is also supported. We experiment with the middleware implemented in the node firmware with distributed applications that span from the LoRa mesh network to the Internet over MQTT. Our results show the support of bidirectional application-level communication, which can be used to build cross-network distributed applications that integrate services on LoRa mesh network nodes.

Amidst rapid and constant technological change, keeping IT higher education curricula up to date is becoming increasingly challenging. For a decade, the course”Project on Information Technologies” within the undergraduate computer science studies offered by a major technical university has been pursuing an effort of continuous curriculum adaptation and active learning practices based on an open project-based learning (PBL) methodology. This article researches the implications of employing an open-ended PBL approach, with a specific focus on the alignment of acquired skills with the trends in the professional landscape. Our analysis has identified a strong correlation between the technologies utilized in the projects and the contemporary technological trends in the areas of global technological focus, programming languages, server-side technologies, database management systems, and DevOps-related tools. For the study, we analyzed empirical data gathered from over 100 projects involving more than 400 students who enrolled in this reference course, belonging to the last year of the IT higher education programme in the last 10 years. The results suggest the open project-based design as a teaching means in the student’s study plan for fostering the student the learning of prevailing current practical technologies.

Training machine learning models in resource-constrained edge devices using federated learning is not yet deeply explored by the research community. There are important technical challenges, such as the limited computing capacity of microcontrollers, and the restricted network connectivity and bandwidth of IoT environments to coordinate and execute the federated learning process. In this paper, we demonstrate a prototype implementation of a federated learning model trained over a LoRa mesh network. We leverage the LoRaMesher library to provide the LoRa mesh network service and integrate it into a keyword spotting federated learning application that runs on a microcontroller-based IoT board. The experimentation with the prototype demonstrates the recent vision of providing edge intelligence with low-capacity networked adaptive microcontroller-based nodes.

In on-device training of machine learning models on microcontrollers a neural network is trained on the device. A specific approach for collaborative on-device training is federated learning. In this paper, we propose embedded federated learning on microcontroller boards using the communication capacity of a LoRa mesh network. We apply a dual board design: The machine learning application that contains a neural network is trained for a keyword spotting task on the Arduino Portenta H7. For the networking of the federated learning process, the Portenta is connected to a TTGO LORA32 board that operates as a router within a LoRa mesh network. We experiment the federated learning application on the LoRa mesh network and analyze the network, system, and application level performance. The results from our experimentation suggest the feasibility of the proposed system and exemplify an implementation of a distributed application with re-trainable compute nodes, interconnected over LoRa, entirely deployed at the tiny edge.

There is a growing research interest in Federated Learning (FL), a promising approach for data privacy preservation and proximity of training to the network edge, where data is generated. Resource consumption for Machine Learning (ML) training and inference is important for edge nodes, but most of the proposed protocols and algorithms for FL are evaluated by simulations. In this demo paper, we present an environment based on distributed mini-PCs to enable experimental study of FL protocols and algorithms. We have installed low-capacity mini-PCs within a wireless city-level mesh network and deployed container-based FL components on these nodes. We show the deployed FL clients and server at different nodes in the city and demonstrate how an FL experiment can be set and run in a real environment.

LoRa is a popular communication technology used in Internet of Things (IoT) applications. Typically, in the LoRaWAN architecture, an end node periodically sends a LoRaWAN message to a gateway connected to the Internet. Recent works, however, showed the possibility of LoRa mesh networks where LoRa nodes communicate with each other. In this paper we present a monitoring system as a tool for observing the traffic and the operation of such LoRa mesh networks. The client side is implemented at the LoRa nodes which periodically send to a server detailed information about the nodes’ in-and outgoing LoRa packets. The server visualizes the information through a dashboard. Thus the monitoring tool allows network administrators to further analyze such LoRa mesh networks.

LoRa has become popular in the Internet of Things (IoT) domain as a Low Power, Wide Area Network (LPWAN) radio technology providing low-power and long-range communication. In a typical IoT application, the LoRaWAN architecture is applied, where LoRa end nodes communicate their data to a gateway, which then over the Internet sends these data to a cloud-based service for further processing. However, LoRa can also be used standalone for the communication between LoRa nodes forming a mesh network. In this demo paper we present a library called LoRaMesher, which runs on LoRa nodes and forms a mesh network among these nodes. By implementing a distance vector routing protocol, LoRaMesher enables two nodes to communicate data packets with each other while the other nodes in the mesh network operate as routers. LoRaMesher can open the possibility for new distributed applications hosted only on such tiny IoT nodes.

Machine learning is moving to the smallest computing devices. Today machine learning is applied even in tiny IoT microcontroller boards. In the IoT, LoRa is a popular communication technology to connect remote devices with gateways. Still, the confluence of machine learning in microcontrollers and networked LoRa connectivity is not yet fully exploited. In this paper we design a new LoRa connectivity for the Arduino Portenta H7, a recent microcontroller board equipped with embedded sensors suitable for diverse machine learning tasks. With the solution that we found the Arduino Portenta H7 is able to become part of a LoRa mesh network. This capacity increases the Portenta’s range of applications. For the vision of distributed machine learning at the tiny edge, we can add with the Portenta an important board to become a smart compute node within a LoRa mesh network.

Inference with trained machine learning models is now pos-sible with small computing devices while only a few years ago it was run mostly in the cloud only. The recent technique of Federated Learning offers now a way to do also the training of the machine learning models on small devices by distributing the computing effort needed for the training over many distributed machines. But, the training on these low-capacity devices takes a long time and often consumes all the available CPU resource of the device. Therefore, for Federated Learning to be done by low-capacity devices in practical environments, the training process must not only target for the highest accuracy, but also on reducing the training time and the resource consumption. In this paper, we present an approach which uses a dynamic epoch parameter in the model training. We propose the BePOCH (Best Epoch) algorithm to identify what is the best number of epochs per training round in Federated Learning. We show in experiments with medical datasets how with the BePOCH suggested number of epochs, the training time and resource consumption decreases while keeping the level of accuracy. Thus, BePOCH makes machine learning model training on low-capacity devices more feasible and furthermore, decreases the overall resource consumption of the training process, which is an important asnect towards greener machine learning techniques.

The Guifi.net community network has evolved during the past 15 years into a telecommunications infrastructure that offers Internet access to more than 80.000 people. The monitoring system currently in place for this network is lagging behind the growth of the infrastructure, requiring manual intervention and counting several single points of failure. In this paper we present REDEMON, a resilient decentralized monitoring system, hosted on distributed and interconnected edge devices, for a reliable, eventually-consistent monitoring of the Guifi.net network, leveraging CRDT-based data structures implemented on AntidoteDB. We developed the REDEMON system as a prototype featuring resilience, decentralization and automation, in order to replace the legacy monitoring system. To assess the system, this prototype was deployed on resource-constraint edge nodes in the Guifi.net production network and evaluated under realistic conditions. The decentralized assignment mechanism successfully achieves setting the minimum number of monitoring servers per network device that satisfies the established system requirements. Besides, by concentrating the workload on the minimum required number of servers running at their maximum capacity, the remaining devices can idle away, reducing the consumption footprint of the system. With regard to computing resources, we measure a moderate CPU and RAM usage by the monitoring system on low-capacity devices, while we observe that a considerable network traffic is required for achieving a resilient and consistent data storage layer. This resilient and decentralized architecture could lay the basis for other edge applications in the cloud computing domain that need to coordinate over distributed and consistent shared data.

Summary Community networks are a growing network cooperation effort by citizens to build and maintain Internet infrastructure in regions that are not available. Adding that, to bring cloud services to community networks (CNs), microclouds were started as an edge cloud computing model where members cooperate using resources. Therefore, enhancing routing for services in CNs is an attractive paradigm that benefits the infrastructure. The problem is the growing consumption of resources for disseminating messages in the CN environment. This is because the services that build their overlay networks are oblivious to the underlying workload patterns that arise from social cooperation in CNs. In this paper, we propose Select in Community Networks (SELECTinCN), which enhances the overlay creation for pub/sub systems over peer‐to‐peer (P2P) networks. Moreover, SELECTinCN includes social information based on cooperation within CNs by exploiting the social aspects of the community of practice. Our work organizes the peers in a ring topology and provides an adaptive P2P connection establishment algorithm, where each peer identifies the number of connections needed based on the social structure and user availability. This allows us to propagate messages using a reduced number of hops, thus providing an efficient heuristic to an NP‐hard problem that maps the workload graph to the structured P2P overlays resulting in a number of messages close to the theoretical minimum. Experiments show that, by using social network information, SELECTinCN reduces the number of relay nodes by up to 89% using the community of practice information versus the state‐of‐the‐art pub/sub notification systems given as baseline.

New teaching methodologies which foster student involvement, such as project-based learning, are nowadays part of the study curriculum of many engineering schools. Project-based learning courses, however, often build upon other previously taught technical courses, where the technical content for the project to be developed is studied. That type of course design focuses on building the transversal capabilities of students, and the technical challenges of the project are the mean to acquire these non-technical skills. In this paper, we present and assess a project-based course on computer network applications of a computer science school, which has been designed to improve within the same course both the transversal and technical skills of the students. The proposition of interest is that the course not only aims to train the students’ transversal skills by a group work project, but also to practise new technical topics and technologies. We argue that the key element of the proposed course design is that each student project group defines with the instructor the project they would like to develop in the course. We present first the design of the course and then an assessment with questionnaires, which were conducted over two semesters with the students enrolled in the course. The obtained results indicate that the students achieved both technical and transversal skills, while the instructors need to be flexible to adapt to diverse technical topics of the proposed projects.

Community networks (CNs) have gained momentum in the last few years with the increasing number of spontaneously deployed WiFi hotspots and home networks. These networks, owned and managed by volunteers, offer various services to their members and to the public. While Internet access is the most popular service, the provision of services of local interest within the network is enabled by the emerging technology of CN micro-clouds. By putting services closer to users, micro-clouds pursue not only a better service performance, but also a low entry barrier for the deployment of mainstream Internet services within the CN. Unfortunately, the provisioning of these services is not so simple. Due to the large and irregular topology, high software and hardware diversity of CNs, a “careful” placement of micro-clouds services over the network is required to optimize service performance. This paper proposes to leverage state information about the network to inform service placement decisions, and to do so through a fast heuristic algorithm, which is critical to quickly react to changing conditions. To evaluate its performance, we compare our heuristic with one based on random placement in Guifi.net, the biggest CN worldwide. Our experimental results show that our heuristic consistently outperforms random placement by 2x in bandwidth gain. We quantify the benefits of our heuristic on a real live video-streaming service, and demonstrate that video chunk losses decrease significantly, attaining a 37% decrease in the packet loss rate. Further, using a popular Web 2.0 service, we demonstrate that the client response times decrease up to an order of magnitude when using our heuristic. Since these improvements translate in the QoE (Quality of Experience) perceived by the user, our results are relevant for contributing to higher QoE, a crucial parameter for using services from volunteer-based systems and adapting CN micro-clouds as an eco-system for service deployment.

Today's commercial model for edge computing services consists in lightweight devices at the network edge connected through the Internet to remote cloud data centers. Microclouds are an alternative vision of edge computing, where the cloud infrastructure runs at the network edge leveraging decentralized resource contributions of a community. But current attempts to build such microclouds lack a collaborative governance system to operate successfully. In this paper we discuss the opportunity to implement with blockchain technologies key services to enable the decentralized collaborative governance of microclouds. A multiagent approach could further contribute to improve the efficiency in the decision making in the collaborative governance service.

Community networks (CNs) have gained momentum in the last few years with the increasing number of spontaneously deployed WiFi hotspots and home networks. These networks, owned and managed by volunteers, offer various services to their members and to the public. To reduce the complexity of service deployment, community micro-clouds have recently emerged as a promising enabler for the delivery of cloud services to community users. By putting services closer to consumers, micro-clouds pursue not only a better service performance, but also a low entry barrier for the deployment of mainstream Internet services within the CN. Unfortunately, the provisioning of the services is not so simple. Due to the large and irregular topology, high software and hardware diversity of CNs, it requires of a "careful" placement of micro-clouds and services over the network. To achieve this, this paper proposes to leverage state information about the network to inform service placement decisions, and to do so through a fast heuristic algorithm, which is vital to quickly react to changing conditions. To evaluate its performance, we compare our heuristic with one based on random placement in Guifi.net, the biggest CN worldwide. Our experimental results show that our heuristic consistently outperforms random placement by 211% in terms of bandwidth gain. We quantify the benefits of our heuristic on a real live video-streaming service, and demonstrate that video chunk losses decrease significantly, attaining a 37% decrease in the loss packet rate. Further, using a popular Web 2.0 service, we demonstrate that the client response times decrease up to an order of magnitude when using our heuristic.

Edge computing has been proposed for new types of cloud services, which need computing infrastructure at the network edge. Driven by important use cases from the Internet of Things (IoT) domain, edge cloud computing has also a huge business potential. Edge computing devices are already operational in many industrial and consumer-oriented scenarios. A typical characteristic of these solutions is, however, that the hardware and software platforms in use are proprietary and closed. The interaction among the different vendor platforms, and their extension with third party services, in general, is not well supported. As a consequence, the opportunities for third party providers to build new tailored edge services on these platforms face significant barriers. In this paper we argue to build a collaborative edge cloud deployed on home servers. We position the proposed system and describe its building elements, where we use Docker containers for provisioning the services.

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.

Seamless computing and service sharing in community networks (CNs) have gained momentum due to the emerging technology of community network micro-clouds (CNMCs). However, deploying and running services in CNMCs confront enormous challenges to cope with, such as the dynamic nature of micro-clouds, limited capacity of nodes and links, asymmetric quality of wireless links, geographic singularity based deployment model rather than network QoS based, etc. CNMCs have been increasingly used by network-intensive services which exchange significant amounts of data between nodes, therefore their performance heavily relies on the available bandwidth resource in a network. This paper proposes a novel bandwidth-aware service placement algorithm which aims to replace the current random placement adopted by Guifi.net. Our experimental results show that the proposed BASP algorithm consistently outperforms the random placement in Guifi.net by 35% regarding its bandwidth gain. More promisingly, as the number of services increases, the gain tends to increase accordingly.

Summary Community networks are self‐organized and decentralized communication networks built and operated by citizens, for citizens. The consolidation of today's cloud technologies offers now, for community networks, the possibility to collectively develop community clouds, building upon user‐provided networks and extending toward cloud services. Cloud storage, and in particular secure and reliable cloud storage, could become a key community cloud service to enable end‐user applications. In this paper, we evaluate in a real deployment the performance of Tahoe least‐authority file system (Tahoe‐LAFS), a decentralized storage system with provider‐independent security that guarantees privacy to the users. We evaluate how the Tahoe‐LAFS storage system performs when it is deployed over distributed community cloud nodes in a real community network such as Guifi.net. Furthermore, we evaluate Tahoe‐LAFS in the Microsoft Azure commercial cloud platform, to compare and understand the impact of homogeneous network and hardware resources on the performance of the Tahoe‐LAFS. We observed that the write operation of Tahoe‐LAFS resulted in similar performance when using either the community network cloud or the commercial cloud. However, the read operation achieved better performance in the Azure cloud, where the reading from multiple nodes of Tahoe‐LAFS benefited from the homogeneity of the network and nodes. Our results suggest that Tahoe‐LAFS can run on community network clouds with suitable performance for the needed end‐user experience. Copyright © 2015 John Wiley & Sons, Ltd.

Internet and communication technologies have lowered the costs for communities to collaborate, leading to new services and collectively built infrastructures like community networks. 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. To address the limitation and enhance utility of community networks, we deploy collaborative clouds in community networks that allow interesting applications to be developed for serving local needs of communities. Such collaborative clouds employ resources contributed by the members of the community network for provisioning infrastructure and software services, and adapt to the specific social, economic and technical characteristics of the community networks. We need to support mechanisms that provide assistance in cloud service selection while taking into account different aspects pertaining to associated risks in community clouds, quality concerns of the users and cost limitations specifically in multi-clouds ecosystems. This paper proposes a risk-cost-quality based decision support system to assist the community cloud users to select the most appropriate cloud services meeting their needs. The proposed framework not only increases the ease of adoption of community clouds by providing assistance to users in cloud service selection, but also provides insights into the improvement of community clouds based on user behaviour.

Community networks are decentralized communication networks built and operated by citizens, for citizens. We consider service discovery for clouds in such community networks. The currently employed solutions for service discovery are static and are not able to follow the dynamics in cloud service provision. We propose a novel service discovery mechanism based on the common Linux tool Avahi combined with TincVPN, in which the VPN allows Avahi to reach nodes beyond the local link. The concept of the micro-cloud is introduced which contains the nodes reached with the extended broadcast domain of Avahi. We evaluate the performance of the proposed service discovery mechanism in a real community cloud deployment consisting of 25 geographically distributed nodes. In experiments with different settings and number of services, we measure the number of services discovered as a function of the discovery time. Our results show that while a client eventually discovers all the services, a significant time is needed to achieve a complete service discovery. The proposed mechanism therefore seems appropriate for the case of community clouds with many replicas of a sought service, where the fast discovery of just a few providers satisfies the requirements of a client. By applying standard Linux tools, an advantage of our solution is that it is by default available on most Linux distribution, which allows our solution to be easily used for real deployments.

Roles and positions are structural components in complex social systems which group actors based on how similarly they are connected to the rest of the actors. Role and position detection methods have been successfully used to evaluate and understand the dynamics of social networks and the behavior of their members. However, actor similarities used to detect positions have been based on pairwise comparisons so far: e.g., structural equivalence states that Alice and Bob are in the same position if they are both connected or not to the same other actors in the network, one by one. In this work we present a new framework to find positions and roles using comparisons between actors and sets of actors instead of just using pairwise comparisons. In this way we enable the usage of many more measures of similarity inside position and role detection methods, e.g., based on distances, community structure, triangles and cliques. As a result, we can identify new types of easily interpretable positions. Additionally, the proposed idea can be adapted to more complex models like hypergraphs or multiplex/multi-relational networks. We have evaluated our work on both synthetic and real data, using several existing and new similarity measures and providing both qualitative and quantitative evidence of the new possibilities enabled by our approach.

Wireless community networks (CNs) are large-scale, self-organized and decentralized communication infrastructures built and operated by citizens for citizens. CN cloud infrastructures have been recently introduced to run services inside the network, without the need to consume them from the Internet. We have developed a Linux-based distribution code-named Cloudy, which fosters the service deployment and automation in CN clouds. In this paper, we present two ways provisioned by Cloudy to integrate the services and improve the user QoS in these clouds. First, we present a distributed service discovery mechanism that helps users with service quality metrics to choose the best service from a pool of instances. Second, we experiment with a live video streaming service deployed in CN environments, using more than 50 real CN nodes distributed across Europe for the evaluation. Our analysis shows that, tuning the vital parameters of this service as neighborhood peer selection strategy and source node dispersion strategy, improves the video streaming QoS in the CNs. Our results indicate that both ways help the user to experience improved service performance. Automated service selection, needed once the number of micro service providers becomes larger, is the next step that can be built upon our results.

Technical communities are social structures that emerge around the interest of individuals to build and deploy their own technology or communication infrastructure, such as wireless community networks. In these communities, the access to shared resources is regulated by incentive mechanisms, which are usually based on the members' contributions. Typically, technical contributions are computed by these mechanisms, ignoring the non-technical activities that members voluntarily perform to keep the community alive, e.g., administration and coordination of the tasks performed by the sub-communities. This article presents a regulation mechanism that rewards not only the contribution of shared resources to the community, but also the participation of the community members in non-technical activities. This proposal was evaluated using simulations, and the obtained results allow researchers and managers of technical communities to build appropriate incentive mechanisms that rewards both, technical and non-technical contributions of their members.

Community networks refers to open, free and neutral network infrastructure built and maintained by citizens and organisations who pool their resources and coordinate their efforts. Among many examples of community networks around the world, this paper presents an analysis of the case of guifi.net, probably the largest in number of nodes and participants, and a success case of a community network daily used by thousands of participants, focusing on the organisational structures developed within the community. guifi.net is organized around the principle of a Common Pool Resource, a viable model for the development of network infrastructure commons. Following an action-research method, the paper describes the processes and tools developed by the community, the current status of its implementation, local impact and lessons learned for more than a decade.

This demo paper presents Cloudy, a Debian-based distribution to build and deploy clouds in community networks. The demonstration covers the following aspects: Installation of Cloudy, the Cloudy GUI for usage and administration by end users, demonstration of Cloudy nodes and services deployed in the Guifi community network.

This paper describes an operational geographically distributed and heterogeneous cloud infrastructure with services and applications deployed in the Guifi community network. The presented cloud is a particular case of a community cloud, developed according to the specific needs and conditions of community networks. We describe the concept of this community cloud, explain our technical choices for building it, and our experience with the deployment of this cloud. We review our solutions and experience on offering the different service models of cloud computing (IaaS, PaaS and SaaS) in community networks. The deployed cloud infrastructure aims to provide stable and attractive cloud services in order to encourage community network user to use, keep and extend it with new services and applications.

Wireless community networks are a successful example of a collective where communities operate ICT infrastructure and provide IP connectivity based on the principle of reciprocal resource sharing of network bandwidth. This sharing, however, has not extended to computing and storage resources, resulting in very few applications and services which are currently deployed within community networks. Cloud computing, as in today's Internet, has made it common to consume resources provided by public clouds providers, but such cloud infrastructures have not materialized within community networks. We analyse in this paper socio-technical characteristics of community networks in order to derive scenarios for community clouds. Based on an architecture for such a community cloud, we implement a prototype for the incentive-driven resource assignment component, deploy it in a test bed of community network nodes, and evaluate its behaviour experimentally. Our evaluation gives insight into how the deployed prototype components regulate the consumption of cloud resources taking into account the users' contributions, and how this regulation affects the system usage. Our results suggest a further integration of this regulation component into current cloud management platforms in order to open them up for the operation of an ecosystem of community cloud.

Energy consumption is increasing in the IT sector and a remarkable part of this energy is consumed in data centers. Numerous techniques have been proposed to solve the energy efficiency issue in cloud systems. Recently, there are some efforts to decentralize the cloud via distributing data centers in diverse geographical positions. In this paper, we elaborate on the energy consumption of different cloud architectures, from a mega-datacenter to a P2P-cloud that provides extreme decentralization in terms of datacenter size. P2P-cloud is defined as a set of commodity host machines, connected to each other to serve a community. Our evaluation results reveal the fact that the more decentralized the system is, the less energy may be consumed in the system. Studying the energy efficiency of P2P-cloud infrastructure shows that the additional system design complexity involved is warranted with improved energy-efficiency and better locality for some services. Our analysis indicates that such P2P-cloud outperforms the classic datacenter model as long as it meets the locality conditions, which are commonplace in communities. Moreover, we illustrate how much energy can be saved for MapReduce applications with a diverse range of specifications by switching to P2P-cloud.

Community networks is an emerging model in which communities of citizens build and own open shared networks. But currently, cloud computing infrastructures, common in today's Internet, hardy exist in community networks. We present in this paper our approach for bringing clouds into community networks. The main element of our strategy for achieving cloud uptake is the deployment of the Guifi-Community-Distribution (GCODIS) on all cloud nodes, a distribution containing common services and applications. We argue in the paper the reasons why this approach is appropriate for the scenario of community networks, where the user acceptance needs to be gained. We show the steps and the on-going process with which we actually implement our approach in the Guifi community network. With these key elements in place, we conclude that we are closer to the vision that the users of community networks ultimately will not need to consume cloud applications from the Internet, but find them within the community network. An interesting open issue is to what extend our approach can be applied to the more generic volunteer computing scenario.

Community-Lab is an open, distributed infrastructure for researchers to carry out experiments within wireless community networks. Community networks are an emergent model of infrastructures built with off-the-shelf communication equipment that aims to satisfy a community's demand for Internet access and ICT services. Community-Lab consists of more than 100 nodes that are integrated in existing community networks, thus giving researchers access to community networks and allowing them to conduct experimental evaluation of routing protocols, services and applications deployed there. Community networks have now the opportunity to extend the collaborative network building to the next level, that is, building collaborative services implemented as community clouds, built, operated and maintained by the community, that run on community-owned heterogeneous resources, and offer cloud-based services that are of the community's interest. This demo paper focuses on demonstrating the cloud extension of Community-Lab, enabling now community cloud experiments. By means of selected applications, we show how Community-Lab has been extended with distributed clouds, where different devices such as server, desktop PCs, low-resource embedded PCs and IoT boards are brought together forming a heterogeneous distributed cloud environment for researchers to experiment in community networks.

Testbeds are a stage between the simulation and the production stages. To this end they must be as close as possible to production environments (i.e. real hardware, on the field deployments) while also keeping the traits of experimentation facilities (i.e. fault tolerance, ease of deployment, testing and data collection). This paper presents WiBed, a FOSS platform for WiFi testbeds based on OpenWRT Linux made to run on commodity IEEE802.11 WiFi routers part of the Community-lab. net project, a global testbed for Community networks. WiBed has been designed to support realistic low layer network experiments (according to the OSI model). This work recollects the details of the architecture, design and implementation of WiBed consolidated during its operation as a testbed as well as two deployments where real experiments were performed.

Collaborative and volunteer applications need to implement incentive mechanisms to regulate resource sharing and encourage network nodes to contribute for reaching a certain goal. Typically, these incentive mechanisms assign resources to network node requests, based on the total amount of resources contributed by the requesting participant. This approach assumes that participants contributing more should also get back more resources from the collaborative environment. This assumption turns the system unfair to those participants with scarce resources, because they have just few resources to share. This paper proposes the use of an incentive strategy based on the contribution percentage of each node; i.e. an effort-based approach. This proposal is evaluated and compared to contribution-based strategies. The obtained results show that the proposed effort-based approach not only benefits participants that have scarce resources, but also it is able to satisfy the requests of the powerful nodes.

We present the community home gateway, a computer system attached to a wireless community network router, able to host platform and application services. Different to current home gateways and other low-end systems, the community home gateway offers resource virtualization, and can thus be used as a cloud resource. Furthermore, it removes the lack of a home gateway system that is open for service contributions and therefore constitutes an important step towards building P2P clouds with low-end devices.

Community-Lab is a testbed for researchers to carry out experiments within wireless community networks. Community networks are an emergent model of infrastructures built with off-the-shelf communication equipment that aims to satisfy a community's demand for Internet access and ICT services. Community-Lab consists of a set of nodes that are integrated in existing community networks, thus giving researchers access to community networks and allowing them to conduct experimental evaluation of applications deployed there. ICT services and applications beyond Internet access are an important milestone - yet not completely reached - to add value to community networks. The challenging environment of community networks however needs a careful evaluation of application performance to make the user experience successful. This paper focuses on demonstrating the deployment of applications in Community-Lab. By means of selected applications, we show how Community-Lab can be used by researchers to perform experiments with applications in community networks.

In community networks, individuals and local organizations 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. Most current community networks use wireless links for the node interconnection, applying off-the-shelf wireless equipment. While IP connectivity over the shared network infrastructure is successfully achieved, the deployment of applications in community networks is surprisingly low. To address the solution of this problem, we propose in this paper a service to incentivize the contribution of computing and storage as cloud resources to community networks, in order to stimulate the deployment of services and applications. Our final goal is the vision that in the long term, the users of community networks will not need to consume applications from the Internet, but find them within the wireless community network.

Advances in wireless communication systems and mobile devices allow nomad users to participate in mobile collaborative activities. However the availability of hardware resources in the mobile devices participating in the collaboration process enhances or jeopardizes such activity. This paper studies how the network topology and the hardware resources distributed into a mobile network influence the collaboration activities among the participants. Several simulations were done to try to understand this issue. The obtained results show that in mobile collaboration scenarios involving a high number of resources-constraint mobile devices (e.g. handhelds), the maximum cooperation among node is obtained in a small world network topology. The results also show that another factor that encourages cooperation among nodes is the network size.

In a market, information about its specifications and the behavior of its participants is essential for sophisticated and efficient negotiation strategies. However, there is currently no completely researched system to provide and consult an overall knowledge of economic information in distributed markets. These markets are implemented for example by grid applications and gained importance over the last few years. This paper presents the economic information requirements and a high-level architecture overview for a decentralized market information system (DMIS). The proposed system acquires economic data in a distributed environment for providing it to individual traders or other participants in a decentralized manner. First, we outline the economic information requirements which the system needs to achieve. Therefore their properties and a privacy model has to be considered. Then we propose an architecture for the system which combines technologies of distributed information aggregation system and distributed publish-subscribe models, based on a structured overlay network. The architecture has been designed to meet both the economic information requirements and that of scalability and robustness of a large-scale distributed environment. Initial measurements confirm the proof-of-concept implementation of the existing prototype.

The design of distributed systems for collaborative work or learning requires that both humans and machines be organized such that the potential and limitations of the human-machine interdependence is optimized. Current distributed architectures like peer-to-peer and Grids have not yet been optimized to support the needs of collaborative applications. In this paper, we investigate the requirements of collaborative applications for groups and, discuss current Grid and P2P architectures with regards to this. need. We suggest possible extensions described in a "function dispersion architecture". Finally, we present as case study our recent work on the design of a middleware to provide services for distributed collaborative applications that has been validated by simulation and prototyping.

Application-layer networks (ALN) are software architectures that allow the provisioning of services requiring a huge amount of resources by connecting large numbers of individual computers. The ALN simulation project CATNET evaluates a decentralized mechanism for resource allocation in ALN, which is based on the economic paradigm of the Catallaxy, against a centralized mechanism using an arbitrator object. In both versions, software agents buy and sell network services and resources to and from each other. The economic model is based on self-interested maximization of utility and self-interested cooperation between agents. This article describes the design of money and message flows for centralized and decentralized coordination in both versions and shows preliminary results.

The aim of the CatNet project is to combine economic and computer science research to provide new coordination mechanisms for large-scale application-layer net-works. The ability of a free-market economy to balance and satisfy the convicting needs of millions of human agents recommends it as a decentralized organizational principle. CatNet will evaluate a decentralized mechanism for resource allocation in computer networks, which is based on the economic paradigm of the Catallaxy. The technical realization of the paradigm builds on software agents which buy and sell network services and resources. This concept is applied both to initial service deployment and service access and to provisioning during the network's lifecycle.

Tracing and performance analysis tools are an important component in the development of high performance applications. Tracing parallel programs with current tracing tools, however, easily leads to large trace files with hundreds of Megabytes. The storage, visualization, and analysis of such trace files is often difficult. We propose a trace-scaling agent for tracing parallel applications, which learns the application behavior in runtime and achieves a small, easy to handle trace. The agent dynamically identifies the amount of information needed to capture the application behavior. This knowledge acquired at runtime allows recording only the non-iterative trace information, which drastically reduces the size of the trace file.

We propose a dynamic periodicity detector (DPD) for the estimation of periodicities in data series obtained from the execution of applications. We analyze the algorithm used by the periodicity detector and its performance on a number of data streams. It is shown how the periodicity detector is used for the segmentation and prediction of data streams. In an application case we describe how the periodicity detector is applied to the dynamic detection of iterations in parallel applications, where the detected segments are evaluated by a speedup computation tool. We test the performance of the periodicity detector on a number of parallelized benchmarks. The periodicity detector correctly identifies the iterations of parallel structures also in the case where the application has nested parallelism. In our implementation we measure only a negligible overhead produced by the periodicity detector. We find the DPD to be useful and suitable for the incorporation in dynamic optimization tools.

The introduction of new services on the Internet is a laborious, time-consuming task. Application networks, applications being serviced through multiple interconnected service nodes disseminated across the Internet for better performance, fault tolerance and availability, as well are costly to set up. In order to provide a network-enabled application service, a number of surrogate servers have to be provisioned. We propose a mechanisms to dynamically deploy an application network: multicast injection. Currently employed dynamic deployment mechanisms, SNMP per-node configuration, is a centralized model that can not scale or be as fault tolerant as more distributed mechanisms such as multicast injection. We perform simulations to compare its efficiency in terms of deployment request success ratio, unused allocation percentage and traffic vs. deployment resource allocation requests. We show that multicast injection has a higher success ratio with lower bandwidth consumption at the deployers' locations.

This paper presents a speech recognition system which incorporates predictive neural networks. The neural networks are used to predict observation vectors of speech. The prediction error vectors are modeled on the state level by Gaussian densities, which provide the local similarity measure for the Viterbi algorithm during recognition. The system is evaluated on a continuous speech phoneme recognition task. Compared with a HMM reference system, the proposed system obtained better results in the speech recognition experiments.

In this paper a phoneme recognition system based on predictive neural networks is proposed. Neural networks are used to predict observation vectors of speech frames. The obtained prediction error is used for phoneme recognition as 1) distortion measure on the frame level and 2) as feature, which is statistically modeled by the Rayleigh distribution. Continuous speech phoneme recognition experiments are performed different settings of the system are evaluated.

In this paper we present a phoneme recognition system based on the Elman predictive neural networks.The recurrent neural networks are used to predict the observation vectors of speech frames.Recognition of phonemes is done using the prediction error as distortion measure in the Viterbi algorithm.The performance of the neural predictive networks is evaluated on both the training database and on a speaker independent test database.The results obtained on the training database are similar to a four state continuous density HMM, results on the test database results are comparable to a three state HMM.

In this paper a new approach for modelling time variations in the speech spectra is presented. We propose to approximate the trajectories of the frequency and amplitude of the poles of the LPC spectra with exponential functions. The obtained time constants of the exponential functions are incorporated in the observation vector and used for recognition in an HMM based recognition system. The performance of the new parameters is tested using a database of connected digits. The recognition rates obtained with the new parameters are compared to results obtained with delta parameters.