Deval Bhamare

A survey on service function chaining

Cloud computing is gaining significant attention and virtualized datacenters are becoming popular as a cost-effective infrastructure. The network services are transitioning from a host-centric to a data-centric model moving the data and the computational resources closer to the end users. To meet the dynamic user demands, network operators have chosen to use elastic virtual resources to implement network services over static rigid physical model. With the advent of network function virtualization (NFV), network services instances are provisioned across multiple clouds for performance and load balancing purposes. Interconnection of these instances to form a complete end-to-end network service is complex, time consuming and expensive task. Service function chaining (SFC) is a mechanism that allows various service functions to be connected to each to form a service enabling carriers to benefit from virtualized software defined infrastructure. SFC is an enabler for NFV, providing a flexible and economical alternative to todays static environment for Cloud Service providers (CSPs), Application Service Providers (ASPs) and Internet Service Providers (ISPs). This paper provides a closer look at the current SFC architecture and a survey of the recent developments in SFC including its relevance with NFV to help determine the future research directions and the standardization efforts of SFC. Finally, the paper discusses open research topics in relevance with the SFC architecture and demonstrates a need for an analytical model for the SFC architecture to achieve the optimal performance.

Multi-cloud Distribution of Virtual Functions and Dynamic Service Deployment: Open ADN Perspective

Network Function Virtualization (NFV) and Service Chaining (SC) are novel service deployment approaches in the contemporary cloud environments for increased flexibility and cost efficiency to the Application Service Providers and Network Providers. However, NFV and SC are still new and evolving topics. Optimized placement of these virtual functions is necessary for acceptable latency to the end-users. In this work we consider the problem of optimal Virtual Function (VF) placement in a multi-cloud environment to satisfy the client demands so that the total response time is minimized. In addition we consider the problem of dynamic service deployment for OpenADN, a novel multi-cloud application delivery platform.

Optimal virtual network function placement in multi-cloud service function chaining architecture

Service Function Chaining (SFC) is the problem of deploying various network service instances over geographically distributed data centers and providing inter-connectivity among them. The goal is to enable the network traffic to flow smoothly through the underlying network, resulting in an optimal quality of experience to the end-users. Proper chaining of network functions leads to optimal utilization of distributed resources. This has been a de-facto model in the telecom industry with network functions deployed over underlying hardware. Though this model has served the telecom industry well so far, it has been adapted mostly to suit the static behavior of network services and service demands due to the deployment of the services directly over physical resources. This results in network ossification with larger delays to the end-users, especially with the data-centric model in which the computational resources are moving closer to end users. A novel networking paradigm, Network Function Virtualization (NFV), meets the user demands dynamically and reduces operational expenses (OpEx) and capital expenditures (CapEx), by implementing network functions in the software layer known as virtual network functions (VNFs). VNFs are then interconnected to form a complete end-to-end service, also known as service function chains (SFCs). In this work, we study the problem of deploying service function chains over network function virtualized architecture. Specifically, we study virtual network function placement problem for the optimal SFC formation across geographically distributed clouds. We set up the problem of minimizing inter-cloud traffic and response time in a multi-cloud scenario as an ILP optimization problem, along with important constraints such as total deployment costs and service level agreements (SLAs). We consider link delays and computational delays in our model. The link queues are modeled as M/D/1 (single server/Poisson arrival/deterministic service times) and server queues as M/M/1 (single server/Poisson arrival/exponential service times) based on the statistical analysis. In addition, we present a novel affinity-based approach (ABA) to solve the problem for larger networks. We provide a performance comparison between the proposed heuristic and simple greedy approach (SGA) used in the state-of-the-art systems. Greedy approach has already been widely studied in the literature for the VM placement problem. Especially we compare our proposed heuristic with a greedy approach using first-fit decreasing (FFD) method. By observing the results, we conclude that the affinity-based approach for placing the service functions in the network produces better results compared against the simple greedy (FFD) approach in terms of both, total delays and total resource cost. We observe that with a little compromise (gap of less than 10% of the optimal) in the solution quality (total delays and cost), affinity-based heuristic can solve the larger problem more quickly than ILP.

Network Slicing for 5G: Challenges and Opportunities

Network slicing for 5G provides Network-as-a-Service (NaaS) for different use cases, allowing network operators to build multiple virtual networks on a shared infrastructure. With network slicing, service providers can deploy their applications and services flexibly and quickly to accommodate diverse services’ specific requirements. As an emerging technology with a number of advantages, network slicing has raised many issues for the industry and academia alike. Here, the authors discuss this technology’s background and propose a framework. They also discuss remaining challenges and future research directions.

Multi-objective scheduling of micro-services for optimal service function chains

Lately application service providers (ASPs) and Internet service providers (ISPs) are being confronted with the unprecedented challenge of accommodating increasing service and traffic demands from their geographically distributed users. Many ASPs and ISPs, such as Facebook, Netflix, AT&T and others have adopted micro-service architecture to tackle this problem. Instead of building a single, monolithic application, the idea is to split the application into a set of smaller, interconnected services, called micro-services (or simply services). Such services are lightweight and perform distinct tasks independent of each other. Hence, they can be deployed quickly and independently as user demands vary. Nevertheless, scheduling of micro-services is a complex task and is currently under-researched. In this work, we address the problem of scheduling micro-services across multiple clouds, including micro-clouds. We consider different user-level SLAs, such as latency and cost, while scheduling such services. Our aim is to reduce overall turnaround time for the complete end-to-end service in service function chains and reduce the total traffic generated. In this work we present a novel fair weighted affinity-based scheduling heuristic to solve this problem. We also compare the results of proposed solution with standard biased greedy scheduling algorithms presented in the literature and observe significant improvements.

COLAP: A predictive framework for service function chain placement in a multi-cloud environment

Network function virtualization (NFV) over multi-cloud promises network service providers amazing flexibility in service deployment and optimizing cost. Telecommunications applications are, however, sensitive to performance indicators, especially latency, which tend to get degraded by both the virtualization and the multiple cloud requirement for widely distributed coverage. In this work we propose an efficient framework that uses the novel concept of random cloud selection combined with a support vector regression based predictive model for cost optimized latency aware placement (COLAP) of service function chains. Extensive empirical analysis has been carried out with training datasets generated using a queuing-theoretic model. The results show good generalization performance of the predictive algorithm. The proposed framework can place thousands of virtual network functions in less than a minute and has high acceptance ratio.

Exploring microservices for enhancing internet QoS

With the enhancements in the field of software-defined networking and virtualization technologies, novel networking paradigms such as network function virtualization (NFV) and the Internet of things (IoT) are rapidly gaining ground. Development of IoT as well as 5G networks and explosion in online services has resulted in an exponential growth of devices connected to the network. As a result, application service providers (ASPs) and Internet service providers (ISPs) are being confronted with the unprecedented challenge of accommodating increasing service and traffic demands from the geographically distributed users. To tackle this problem, many ASPs and ISPs, such as Netflix, Facebook, AT&T and others are increasingly adopting micro-services (MS) application architecture. Despite the success of MS in the industry, there is no specific standard or research work for service providers as guidelines, especially from the perspective of basic micro-service operations. In this work, we aim to bridge this gap between industry and academia and discuss different micro-service deployment, discovery and communication options for service providers as a means to forming complete service chains. In addition, we address the problem of scheduling micro-services across multiple clouds, including micro-clouds. We consider different user-level SLAs, such as latency and cost, while scheduling such services. We aim to reduce overall turnaround time as well as costs for the deployment of complete end-to-end service. In this work, we present a novel affinity-based fair weighted scheduling heuristic to solve this problem. We also compare the results of proposed solution with standard greedy scheduling algorithms presented in the literature and observe significant improvements.

Efficient virtual network function placement strategies for Cloud Radio Access Networks

Abstract The new generation of 5G mobile services place stringent requirements for cellular network operators in terms of latency and costs. The latest trend in radio access networks (RANs) is to pool the baseband units (BBUs) of multiple radio base stations and to install them in a centralized infrastructure, such as a cloud, for statistical multiplexing gains. The technology is known as Cloud Radio Access Network (CRAN). Since cloud computing is gaining significant traction and virtualized data centers are becoming popular as a cost-effective infrastructure in the telecommunication industry, CRAN is being heralded as a candidate technology to meet the expectations of radio access networks for 5G. In CRANs, low energy base stations (BSs) are deployed over a small geographical location and are connected to a cloud via finite capacity backhaul links. Baseband processing unit (BBU) functions are implemented on the virtual machines (VMs) in the cloud over commodity hardware. Such functions, built in software, are termed as virtual functions (VFs). The optimized placement of VFs is necessary to reduce the total delays and minimize the overall costs to operate CRANs. Our study considers the problem of optimal VF placement over distributed virtual resources spread across multiple clouds, creating a centralized BBU cloud. We propose a combinatorial optimization model and the use of two heuristic approaches, which are, branch-and-bound (BnB) and simulated annealing (SA) for the proposed optimal placement. In addition, we propose enhancements to the standard BnB heuristic and compare the results with standard BnB and SA approaches. The proposed enhancements improve the quality of the solution in terms of latency and cost as well as reduce the execution complexity significantly. We also determine the optimal number of clouds, which need to be deployed so that the total links delays, as well as the service migration delays, are minimized, while the total cloud deployment cost is within the acceptable limits.

Machine Learning for Anomaly Detection and Categorization in Multi-Cloud Environments

Cloud computing has been widely adopted by application service providers (ASPs) and enterprises to reduce both capital expenditures (CAPEX) and operational expenditures (OPEX). Applications and services previously running on private data centers are now being migrated to private or public clouds. Since most of the ASPs and enterprises have globally distributed user bases, their services need to be distributed across multiple clouds, spread across the globe which can achieve better performance in terms of latency, scalability and load balancing. The shift has eventually led the research community to study multi-cloud environments. However, the widespread acceptance of such environments has been hampered by major security concerns. Firewalls and traditional rule-based security protection techniques are not sufficient to protect user-data in multi-cloud scenarios. Recently, advances in machine learning techniques have attracted the attention of the research community to build intrusion detection systems (IDS) that can detect anomalies in the network traffic. Most of the research works, however, do not differentiate among different types of attacks. This is, in fact, necessary for appropriate countermeasures and defense against attacks. In this paper, we investigate both detecting and categorizing anomalies rather than just detecting, which is a common trend in the contemporary research works. We have used a popular publicly available dataset to build and test learning models for both detection and categorization of different attacks. To be precise, we have used two supervised machine learning techniques, namely linear regression (LR) and random forest (RF). We show that even if detection is perfect, categorization can be less accurate due to similarities between attacks. Our results demonstrate more than 99% detection accuracy and categorization accuracy of 93.6%, with the inability to categorize some attacks. Further, we argue that such categorization can be applied to multi-cloud environments using the same machine learning techniques.

Fault and Performance Management in Multi-Cloud Based NFV Using Shallow and Deep Predictive Structures

Deployment of Network Function Virtualization (NFV) over multiple clouds accentuates its advantages like flexibility of virtualization, proximity to customers and lower total cost of operation. However, NFV over multiple clouds has not yet attained the level of performance to be a viable replacement for traditional networks. One of the reasons is the absence of a standard based Fault, Configuration, Accounting, Performance and Security (FCAPS) framework for the virtual network services. In NFV, faults and performance issues can have complex geneses within virtual resources as well as virtual networks and cannot be effectively handled by traditional rule-based systems. To tackle the above problem, we propose a fault detection and localization model based on a combination of shallow and deep learning structures. Relatively simpler detection has been effectively shown to be handled by shallow machine learning structures like Support Vector Machine (SVM). Deeper structure, i.e., the stacked autoencoder has been found to be useful for a more complex localization function where a large amount of information needs to be worked through to get to the root cause of the problem. We provide evaluation results using a dataset adapted from fault datasets available on Kaggle and another based on multivariate kernel density estimation and Markov sampling.