Abstract
Due to the massive Internet of Things (IoT) connectivity and substantial growth of communication traffic, Virtual Network Function (VNF) orchestration scheme is anticipated to function promptly, dynamically, and intelligently for next-generation networks. Hence, we urge the necessity to move beyond the traditional paradigm and employ VNFs on the network edge located cloudlet. Overall, multi-access edge computing can intensify the performance of delay-sensitive IoT applications compared to the core cloud based VNF deployments. In this paper, we intend to investigate how to simultaneously leverage the ensembling of multiple deep learning models for proper calibration to provide real-time VNF placement solutions. We also address the challenges associated with state-of-the-art approaches to deal with dynamic network traffic and topology patterns. Our envisioned methods, based on Convolutional Neural Networks and Artificial Neural Networks named as E-ConvNets and E-ANN respectively, suggest two proactive VNF deployment strategies. These ensembled VNF deployment strategies demonstrate encouraging performance (optimality gap nearly 7%) in terms of minimizing relocation and communication costs, and high scalability intelligence factor (around 0.93) through simulation results compared to standalone deep learning models. Furthermore, the presented results indicate the potentialities of applying deep learning-based strategies into similar research enigmas for future telecommunication network researches.
Highlights
The deployment of these Virtual Network Function (VNF) requires a highly efficient and scalable strategy to deal with the continu- B 2ASED on the expectations to fulfill the demands of ultra- ally evolving network dynamic patterns and the large volume high processing speed and low communication delay of traffic emerging from value-added services [8]
We propose the employment of intelligent VNF orches- enhance the efficiency regarding scaling [17], allocation of tration using two ensemble deep learning techniques that VNFs [18], task scheduling [19] [20], and migration of are ensemble artificial neural networks (E-Artificial Neural Networks (ANN)) and VNFs [21], etc
The reason being that only this specific The Virtual Network Functions (VNFs) are run on different 85 literature among others that have been listed in Table I cloudlet data centers (DCs), where each DC has a restricted capability of integrates both VNF allocation and migration resembling our supporting service oriented or application VNFs
Summary
The deployment of these VNFs requires a 33 highly efficient and scalable strategy to deal with the continu- 34. Vision towards future telecommunication networks anticipates In distinction to the existing works, we have aimed to 60 that the third parties will designate the content-aware and user- propose lightweight and dynamic deep learning [13] aided specific services along with their corresponding specifications, strategies for the VNF orchestration and deployment that for example, the highest tolerable latency or least throughput facilitates both users and services provides exclusively by limits, to the network administrator, expedited by NFV and collaborative minimization of communication, relocation delay software-defined networking (SDN) [7]. To enhance the Quality-of-Experience (QoE) strates that E-ANN and E-ConvNets are capable of pro- of the users, massive computation time critical applications viding near optimal real-time solutions for large-scale IoT require a large volume of communication resources. The based methods show a significant escalation in the perfor- authors of [26] have proposed distributed VNF deployment iii by caching resources, yet this mechanism is unable to manage existing works suggested the use of ensemble deep learning 59 dynamic network situations. The main focus has been deviated away from communication delay that may affect the overall user experience
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
