Jéferson Campos Nobre

Distributed Reallocation Scheme for Virtual Network Resources

Network virtualization is an emerging technology for cost-effective sharing of network resources. The key strategy in network virtualization is of slicing physical resources (links, CPU, memory, and storage) to create virtual networks that are assigned to different operators. One important challenge on network virtualization is the efficient use of the physical resources. To accomplish such efficient use the management of the physical resources should be transparent to the applications running within the virtual networks, and should be executed at runtime in order to deal with the variation on the load requests of different virtual networks. Traditional resource allocation schemes use offline, centralized, and global view strategies to manage the use of physical resources. In contrast to these strategies, we propose a runtime, distributed, local view approach to manage physical resources. In this paper we introduce a virtual network architecture and an associated self-organizing algorithm to reallocate virtual network resources along different physical nodes in order to equalize the bandwidth, and storage consumption on the physical nodes. We developed a virtual network model based on Omnet++ to simulate the designed self-organizing algorithm. An IPTV testbed scenario is presented and initial experiments, about the interruption time of the application inside the IPTV virtual network, are described.

Consistency maintenance of policy states in decentralized autonomic network management

Autonomic network management is a vision that brings autonomic computing principles to network management. In this vision, the use of policies is a key aspect. Besides, it is necessary to add some level of decentralization to enable broad autonomic capabilities. Thus, the elements that build decentralized autonomic network management systems (known as autonomic management elements) must be policy-enabled. However, the consistency of policy states among autonomic management elements is an important challenge. Traditional mechanisms to maintain consistency of these states are supported by some centralization which wastes some desirable properties of decentralization. In contrast to these mechanisms, we propose a distributed, scalable and robust mechanism to maintain the consistency of policy states. In this paper we introduce multi-agent truth maintenance features in decentralized autonomic network management as a mechanism to bring consistency maintenance of policy states. We developed a model of a decentralized autonomic network management system on Peersim to perform simulation experiments. Besides, the utilization of policies in P2P-based autonomic network management systems is presented as case study.

Consistency of States of Management Data in P2P-Based Autonomic Network Management

Autonomic network management is a vision that brings autonomic computing principles to network management. Besides, it is necessary some level of decentralization to enable broad autonomic capabilities. An interesting alternative of infrastructure for this union is the utilization of peer-to-peer (P2P) overlays. However, the consistency of states of management data among peers is an important challenge. Traditional mechanisms to maintain consistency of these states are supported by some centralization which wastes some desirable properties of P2P facilities. In contrast to these mechanisms, we propose a distributed, scalable and robust mechanism to maintain the consistency of states of management data. In this paper we introduce multi-agent truth maintenance features in P2P-based autonomic network management as a mechanism to bring consistency maintenance of these states. We developed a model of a P2P-based autonomic network management system on Peersim to perform simulation experiments. Besides, the utilization of P2P-based autonomic network management systems in access networks is presented as a case study.

Toward software-defined battlefield networking

Battlefield networking (BN) considers each network entity as a network in itself, composed of several communication technologies usually interconnected by multiple satellites. In this context, we must consider the intrinsic properties of military contexts to apply SDN in BN to get more flexibility and programmability in network-centric operations. For instance, BN considers several communication technologies, as well as the distinct application requirements on the traffic transmitted over BN in terms of QoS and security features in dynamic environments, where flexible network-centric operations are mandatory. In this article, we define an SDBN architecture that adapts SDN technology to BN, enabling SDNbased applications, methods, and policies. To the best of our knowledge, the proposed architecture in this article is the first one aimed at integrating BN and SDN into dynamic and heterogeneous network-centric environments.

Coordination in P2P management overlays to improve decentralized detection of SLA violations

Critical networked services enable significant revenue for network operators and, in turn, are regulated by Service Level Agreements (SLAs). In order to ensure SLAs are being met, service levels need to be monitored. One technique for this involves active measurement mechanisms which employ measurement probes along the network to inject synthetic traffic and compute the network performance. However, these mechanisms are expensive in terms of resources consumption. Thus, active measurement mechanisms usually can cover only a fraction of what could be measured, which can lead to SLA violations being missed. Besides that, the definition of this fraction is a practice done by human administrators, which does not scale well and does not adapt to highly dynamic networking patterns. The contribution of the present work is the proposal of a solution to increase the potential number of detected SLA violations in which network devices autonomously and dynamically share service level measurement results. The sharing of these measurement results is based on the utilization of a Peer-to-Peer (P2P) management overlay built using past service level measurement results and a coordination strategy characterized by a high degree of decentralized decision making. The solution is evaluated using simulation and the results show its feasibility and interesting features.

A Survey on the Use of P2P Technology for Network Management

Network management has steadily evolved over recent years. Along with the growing need for advanced features in network management solutions, several distribution models were investigated, varying from centralized to fully distributed models. Despite the common agreement that some sort of distribution is really needed to execute management tasks, there seems to exist a permanent quest for the next distributed network management model. Among the distributed models, an interesting and emerging possibility is the use of P2P technology in network management, also known as P2P-Based Network Management (P2PBNM). Several investigations have shown that P2PBNM can be seen as an enabler for advanced network management features. However, due to the dispersion concerning the concepts and features related to these investigations, it is difficult to draw a comprehensive picture of the P2PBNM area. The purpose of this article is to look at literature on P2PBNM and to highlight initiatives regarding the use of P2P technology in network management. Furthermore, such initiatives are classified in respect to proposed review questions. Finally, future trends are discussed in order to predict what the future holds for P2PBNM.

A P2P-Based self-healing service for network maintenance

The introduction of self-* properties over distributed network management infrastructures has been proving to be a feasible approach for the new demands of modern network management. Among the properties of the self-* management vision, self-healing figures as key property in improving the dependability of the managed infrastructures. An interesting possibility to materialize self-* support - and self-healing support as well - in network management is through the employment of peer-to-peer (P2P) management overlays. Considering this scenario, we introduce in this paper a self-healing service provided by a prototype P2P-Based Network Management (P2PBNM) system. Such a service is expected to be contracted by human administrators interested in monitoring and recovering their IT infrastructures. In addition, an experimental evaluation of the self-healing service is performed considering a case study where a Host-based Intrusion Detection System (HIDS) needs to be constantly observed and eventually healed to keep the underlying communication network protected.

Towards Consistency of Policy States in Decentralized Autonomic Network Management

Autonomic network management is a vision that brings autonomic computing principles to network management. In this vision, the use of policies is a key aspect. Besides, it is necessary some level of decentralization to enable broad autonomic capabilities. However, the consistency of policy states among autonomic management elements is an important challenge. In this paper we introduce multi-agent truth maintenance features in decentralized autonomic network management as a mechanism to bring consistency maintenance of policy states. We developed a model of a decentralized autonomic network management system on Peersim to perform simulation experiments. Besides, the utilization of policies in P2P-based autonomic network management systems is presented as case study.

Service Migration from Cloud to Multi-tier Fog Nodes for Multimedia Dissemination with QoE Support

A wide range of multimedia services is expected to be offered for mobile users via various wireless access networks. Even the integration of Cloud Computing in such networks does not support an adequate Quality of Experience (QoE) in areas with high demands for multimedia contents. Fog computing has been conceptualized to facilitate the deployment of new services that cloud computing cannot provide, particularly those demanding QoE guarantees. These services are provided using fog nodes located at the network edge, which is capable of virtualizing their functions/applications. Service migration from the cloud to fog nodes can be actuated by request patterns and the timing issues. To the best of our knowledge, existing works on fog computing focus on architecture and fog node deployment issues. In this article, we describe the operational impacts and benefits associated with service migration from the cloud to multi-tier fog computing for video distribution with QoE support. Besides that, we perform the evaluation of such service migration of video services. Finally, we present potential research challenges and trends.

On using P2P technology to enable opportunistic management in DTNs through statistical estimation

Disruption-Tolerant Networks (DTNs) are characterized by long delays and constant disconnections among nodes. These networks have management needs analogous to those of traditional computer networks, but, their intrinsic characteristics (e.g., intermittent connections) hinder the execution of network management tasks. The employment of P2P technology is an alternative for managing DTNs since this technology promotes the autonomy of management entities (i.e., management peers). This autonomy enables the use of local logic and data in order to perform opportunistic management tasks. We propose a solution to estimate the future contacts of nodes through distributed statistical analysis of past contacts. Besides that, nodes can share information about their contacts to improve contact estimation using a P2P management overlay. The proposed solution was implemented using an open source P2P-Based Network Management (P2PBNM) system, ManP2P-ng. Furthermore, the solution was evaluated through experiments performed using publicly available DTN traces. The results show that the proposed solution can improve the execution of management tasks in DTNs.