Virtual Network Functions Orchestration Research Articles

FIPAM: Fuzzy Inference Based Placement and Migration Approach for NFV-Based IoTs

The advancement and spread of the Internet-of-Things (IoT) have massively been increased over a decade. With the widespread of IoT networks, it is becoming difficult to acquire and execute real-time data. Network function virtualization (NFV) provides a flexible and efficient solution for IoT-based applications and service management. NFV creates a virtualized environment that can run a large number of micro-services for different IoT applications by using the virtual network functions (VNFs) through placement and chaining. In this paper, we propose a novel fuzzy inference-based placement and migration (FIPAM) approach for placement and migration/chaining of VNFs to ensure that resource allocation is carefully carried out during VNF orchestration and embedding. Firstly, we formulate the VNF chaining and placement problem. Secondly, we propose a lightweight VNF placement solution that considers the underlying network conditions while making the placement decisions. A novel usage of fuzzy inference is proposed to optimize the chaining mechanism along with the dynamic instantiation of VNFs to meet specific service needs. Simulation results are shown to validate the superiority of the proposed algorithm over existing schemes.

Intelligent network management system for solving the problem of offline monitoring 5G technologies

Maintenance and management of fourth-generation (4G) current networks are still done manually and semi-automatically, which is expensive and time-consuming. This poses a major challenge for network management of disparate, software-defined, and virtualized fifth-generation (5G) systems. Fifth-generation (5G) cellular networks include a wide variety of technologies to address very different uses. Assessing these technologies and exploring future alternatives is complicated by relying solely on network administrators. 5G network intelligence is an important alternative to network administrators. With the advent of network intelligence for the 5G system opens the possibility of intelligent control. Without the intervention of administrators, the new approach can autonomously solve network problems, cyberattacks and inefficient use of resources, which in turn can reduce operating costs, improve user experience and reduce the time to market of new services. This work presents a test bench of a 5G mobile network with a virtualized and organized structure that focuses on integration into artificial intelligence programs. The presented test bench uses open-source technologies for deployment and orchestration of virtual network functions for flexible creation of various scenarios of mobile networks with clear topologies of frontal and feedback. The article explains how to deploy the structure of the test bench and reproduce the presented results with the provided algorithms and presents the recommended architecture, functionality, closed control, algorithms that include network intelligence. An intelligent 5G test bench has been installed, and experimental results confirm the feasibility and effectiveness.

Management and Orchestration of Virtual Network Functions via Deep Reinforcement Learning

Management and orchestration (MANO) of resources by virtual network functions (VNFs) represents one of the key challenges towards a fully virtualized network architecture as envisaged by 5G standards. Current threshold-based policies inefficiently over-provision network resources and under-utilize available hardware, incurring high cost for network operators, and consequently, the users. In this work, we present a MANO algorithm for VNFs allowing a central unit (CU) to learn to autonomously re-configure resources (processing power and storage), deploy new VNF instances, or offload them to the cloud, depending on the network conditions, available pool of resources, and the VNF requirements, with the goal of minimizing a cost function that takes into account the economical cost as well as latency and the quality-of-service (QoS) experienced by the users. First, we formulate the stochastic resource optimization problem as a parameterized action Markov decision process (PAMDP). Then, we propose a solution based on deep reinforcement learning (DRL). More precisely, we present a novel RL approach, called parameterized action twin (PAT) deterministic policy gradient, which leverages an actor-critic architecture to learn to provision resources to the VNFs in an online manner. Finally, we present numerical performance results, and map them to 5G key performance indicators (KPIs). To the best of our knowledge, this is the first work that considers DRL for MANO of VNFs' physical resources.

Elastic Virtual Network Function Orchestration Policy Based on Workload Prediction

By separating network functions from hardware-dependent middleboxes, network function virtualization (NFV) is expected to lead to significant cost reduction and the flexibility improvement in network management. Elastic orchestration of virtual network functions (VNF) is a key factor to achieve NFV goals. However, most existing VNF orchestration researches are limited to offline policy, ignoring the dynamic characteristics of the workload. To reduce the operational expenditure of NFV providers, this paper proposes an Elastic Virtual Network Function Orchestration (EVNFO) policy based on workload prediction. We adapt the online learning algorithm for predicting the flows rate of service function chains (SFC), which can help to obtain the VNF scaling decision. We further design the online instance provisioning strategy (OIPS) to accomplish the deployment of VNF instances according to the decision. The simulation proves that EVNFO can provide good performance with dynamic resource provision. The throughput of VNF is improved by 11.1%–22.9%, and the total operational expenditure can be reduced by 13.8% compared with other online approaches.