Nashid Shahriar

Elastic virtual network function placement

Nowadays, many cloud providers offer Virtual Network Function (VNF) services that are dynamically scaled according to the workload. Enterprises enjoy these services by only paying for the actual consumed resources. From a cloud providers standpoint, the cost of these services must be kept as low as possible, while QoS is maintained and service downtime is minimized. In this paper, we introduce Elastic Virtual Network Function Placement (EVNFP) problem and present a model for minimizing operational costs in providing VNF services. In this model, the elasticity overhead and the trade-off between bandwidth and host resource consumption are considered together, while the previous works ignored this perspective of the problem. We propose a solution called Simple Lazy Facility Location (SLFL) that optimizes the placement of VNF instances in response to on-demand workload. Our experiments suggest that SLFL can accept two times more workload while incurring similar operational cost compared to first-fit and random placements.

SiMPLE: Survivability in multi-path link embedding

Internet applications are deployed on the same network infrastructure, yet they have diverse performance and functional requirements. The Internet was not originally designed to support the diversity of current applications. Network Virtualization can enable heterogeneous applications and network architectures to coexist without interference on the same infrastructure. Embedding a Virtual Network (VN) into a physical network is a fundamental problem in Network Virtualization. A VN Embedding that aims to survive physical (e.g., link) failures is known as the Survivable Virtual Network Embedding (SVNE). A key challenge in the SVNE problem is to ensure VN survivability with minimal resource redundancy. To address this challenge, we propose SiMPLE. By exploiting path diversity in the physical network, SiMPLE provides guaranteed VN survivability against single link failure. In addition, SiMPLE produces highly surviv-able VN embeddings in presence of multiple link failures while incurring very low resource redundancy. We provide an ILP formulation for this problem and implement it using GLPK. We also propose a greedy algorithm to solve larger instances of the problem. Simulation results show that our solution outperforms full backup and shared backup schemes for SVNE, and produces near-optimal results.

Distributed Service Function Chaining

A service-function chain, or simply a chain, is an ordered sequence of service functions, e.g., firewalls and load balancers, composing a service. A chain deployment involves selecting and instantiating a number of virtual network functions (VNFs), i.e., softwarized service functions, placing VNF instances, and routing traffic through them. In the current optimization-models of a chain deployment, the instances of the same function are assumed to be identical, while typical service providers offer VNFs with heterogeneous throughput and resource configurations. The VNF instances of the same function are installed in a single physical machine, which limits a chain to the throughput of a few instances that can be installed in one physical machine. Furthermore, the selection, placement, and routing problems are solved in isolation. We present distributed service function chaining that coordinates these operations, places VNF-instances of the same function distributedly, and selects appropriate instances from typical VNF offerings. Such a deployment uses network resources more efficiently and decouples a chain’s throughput from that of physical machines. We formulate this deployment as a mixed integer programming (MIP) model, prove its NP-Hardness, and develop a local search heuristic called Kariz. Extensive experiments demonstrate that Kariz achieves a competitive acceptance-ratio of 76%–100% with an extra cost of less than 24% compared with the MIP model.

Multi-Path Link Embedding for Survivability in Virtual Networks

Internet applications are deployed on the same network infrastructure, yet they have diverse performance and functional requirements. The Internet was not originally designed to support the diversity of current applications. Network virtualization enables heterogeneous applications and network architectures to coexist without interference on the same infrastructure. Embedding a virtual network (VN) into a physical network is a fundamental problem in network virtualization. A VN embedding that aims to survive physical (e.g., link) failures is known as the survivable VN embedding (SVNE). A key challenge in the SVNE problem is to ensure VN survivability with minimal resource redundancy. To address this challenge, we propose survivability in multi-path link embedding (SiMPLE). By exploiting path diversity in the physical network, SiMPLE provides guaranteed VN survivability against single link failure while incurring minimal resource redundancy. In case of multiple arbitrary link failures, SiMPLE provides maximal survivability to the VNs. We formulate this problem as an integer linear program and implement it using GNU linear programming kit. We propose a greedy proactive approach to solve larger instances of the problem in case of single link failures. In presence of more than one link failures, we propose a greedy reactive algorithm as an extension to the previous one, which opportunistically recovers the lost bandwidth in the VNs. Simulation results show that SiMPLE outperforms full backup and shared backup schemes for SVNE, and produces near-optimal results.

Generalized Recovery From Node Failure in Virtual Network Embedding

Network virtualization has evolved as a key enabling technology for offering the next generation network services. Recently, it is being rolled out in data center networks as a means to provide bandwidth guarantees to cloud applications. With increasing deployments of virtual networks (VNs) in commercial-grade networks with commodity hardware, VNs need to tackle failures in the underlying substrate network. In this paper, we study the problem of recovering a batch of VNs affected by a substrate node failure. The combinatorial possibilities of alternate embeddings of the failed virtual nodes and links of the VNs make the task of finding the most efficient recovery both non-trivial and intractable. Furthermore, any recovery approach ideally should not cause any service disruption for the unaffected parts of the VNs. We take into account these issues to design a generalized recovery approach that can achieve customized objectives such as fair treatment on the failed VNs, partial treatment based on priority, and so on. We provide integer linear programming (ILP) formulations for two variants of our recovery scheme, namely, fair recovery model and priority-based recovery model. We also propose a fast and scalable heuristic algorithm to tackle the computational complexity of the ILP solution. Evaluation results demonstrate that our heuristic performs close to the optimal solution and outperforms the state-of-the-art algorithm.

Connectivity-aware virtual network embedding

The problem of ensuring virtual network (VN) connectivity in presence of multiple link failures in the substrate network (SN) is not well investigated in Network Virtualization (NV) literature. We name this problem as Connectivity-aware Virtual Network Embedding (CoViNE). Solving CoViNE will enable a VN operator to perform failure recovery without depending on the SN provider, similar to the IP restoration mechanisms in IP-over-WDM networks. There are two steps in solving CoViNE: i) finding the virtual links that should be embedded disjointly, and ii) finding a substrate resource efficient embedding that ensures the virtual link disjointness constraint. We present two solutions to the CoViNE problem. The first solution uses a heuristic to compute the disjointness constraint, while an optimization model is used for VN embedding. The second solution, in contrast, uses heuristic for both the steps, and thus can solve larger instances of the problem. We compare our solutions with a cut set based approach that ensures VN connectivity for a single substrate link failure. Evaluation results show that our heuristics allocate ~15% extra resources on average compared to the cut set based optimal solution, and executes two to three orders of magnitude faster on the same problem instances.

Ensuring Beta-Availability in P2P Social Networks

Despite their tremendous success, centrally controlled cloud based solutions for social media networking have inherent issues related to privacy and user control. Alternatively, a decentralized approach can be used, but ensuring content availability will be the major challenge. In this work, we propose a time based user grouping and content replication protocol that exploits the cyclic diurnal pattern in user uptime behaviour to ensure content persistence with minimal replication overhead. We also introduce the concept of beta-availability, and propose a mechanism for ensuring the availability of at least beta members within a replication group at any given time. Simulation results show that a 2-availability grouping policy delivers high content persistence without incurring significant network and storage overheads.

Diurnal availability for peer-to-peer systems

Ensuring content availability in a persistent manner is essential for providing any consistent service over peer-to-peer (P2P) systems. This paper introduces an efficient protocol, called DATA, to design highly available P2P systems irrespective of peer uptime and churn. Our approach utilizes the diurnal pattern of globally dispersed peers to develop a grouping strategy where each group aims to ensure 24 × 7 data availability within the group. Simulation results reveal that our protocol converges fast and ensures high availability for each group with minimal overhead.

A comprehensive survey on machine learning for networking: evolution, applications and research opportunities

Machine Learning (ML) has been enjoying an unprecedented surge in applications that solve problems and enable automation in diverse domains. Primarily, this is due to the explosion in the availability of data, significant improvements in ML techniques, and advancement in computing capabilities. Undoubtedly, ML has been applied to various mundane and complex problems arising in network operation and management. There are various surveys on ML for specific areas in networking or for specific network technologies. This survey is original, since it jointly presents the application of diverse ML techniques in various key areas of networking across different network technologies. In this way, readers will benefit from a comprehensive discussion on the different learning paradigms and ML techniques applied to fundamental problems in networking, including traffic prediction, routing and classification, congestion control, resource and fault management, QoS and QoE management, and network security. Furthermore, this survey delineates the limitations, give insights, research challenges and future opportunities to advance ML in networking. Therefore, this is a timely contribution of the implications of ML for networking, that is pushing the barriers of autonomic network operation and management.

AVRA Bangladesh collection, analysis & visualization of road accident data in Bangladesh

Road accident is a global issue of concern and like many other countries in the world Bangladesh also suffers greatly due to road accidents every year. Our goal was to provide a complete & accurate accident information source available to general mass. In our software, we have tried to incorporate a complete picture of accident rate & accident trend. We have included a way to explore every possible source for collecting accident data in our software. Anyone can provide information regarding an accident which includes hospitals attending accident victims, print or electronic media even simple spectators. Our software introduces an Internet-based, GIS-compatible software process for automated road accident analysis & visualization. This site is capable of performing accident information query, trend analysis, statistical analysis, color-coded mapping, and other accident information display within the web-based environment. The Internet-accessible user interface allows users to inquire about detailed information on vehicle crashes associated with road segments and intersections for any geographical regions in Bangladesh via query forms or zoom-enabled interactive maps. In our program we have generated automated visualizations of accident rate & factors of accidents in formats of charts, table & maps. Visualization of traffic accidents by collision type & road class based on real data is included to demonstrate the effectiveness of our software.