GAI-Based Resource and QoE Aware Service Placement in Next-Generation Multi-Domain IoT Networks

Network Function Virtualization (NFV) has recently emerged as a highly cost-effective paradigm for flexibly provisioning services in next-generation Internet of Things (IoT) networks, by introducing Service Function Chain (SFC) technology. However, the rapid expansion of network scales and increasing diversification of service requirements in recent years pose significant challenges to ensuring the Quality of Experience (QoE) of users in Next-generation Multi-domain IoT (NMIoT) networks. The effective deployment of SFCs in NMIoT networks to satisfy diversified resource demands while enhancing QoE of users is crucial. The recent breakthroughs in Generative Artificial Intelligence (GAI) technologies bring a new opportunity to deliver customized services and guarantee enhanced service quality in NMIoT networks. To tackle the challenges, in this paper, we investigate the problem of Resource and QoE aware SFC Placement (RQSP) in NMIoT networks. Firstly, we formulate the RQSP problem as a mixed integer linear programming model, taking into account resource demands and Quality of Service (QoS) constraints, aiming to minimize the service cost, which is composed of resource consumption cost, cross-domain operational cost and penalty cost for unsuccessful placement. Then, we prove that the RQSP problem is NP-hard. To solve it, we incorporate GAI technology to devise a novel Generative genetic Algorithm based heuristic SFC Placement (GAP) method. Furthermore, we devise a greedy strategy based population initialization mechanism as well as an elitist and roulette wheel joint selection strategy, to speed up algorithm convergence and reduce runtime overhead. Finally, simulation results demonstrate that compared to benchmark algorithms, the proposed GAP algorithm can achieve better performances on service acceptance ratio, service cost, server utilization and average service delay.

I. Introduction

In recent years, the rapid development of mobile communication technologies, including 5G and mobile edge computing, has fueled the widespread adoption of next-generation Internet of Things (IoT). This has facilitated extensive interconnections among a large number of devices, such as sensors, portable devices, wearable devices, VR devices and smart devices. The surge in the number of next-generation IoT devices has led to a deluge of service requests and a variety of diverse applications, encompassing face recognition and interactive online games [1]. The service requests of IoT applications are often computationally extensive or latency sensitive. However, traditional service provisioning methods struggle to efficiently guarantee service performance and meet the diversified service requirements of IoT applications, since middleboxes are heavily dependent on specific hardware devices. Network Function Virtualization (NFV), a technology enabler for next-generation IoT networks, has garnered significant attention from academics and industries [2]. The crux of NFV lies in decoupling network functions and hardware devices, allowing network functions to be replaced by software based Virtual Network Functions (VNFs). In NFV-enabled next-generation IoT networks, each IoT service can be perceived as a Service Function Chain (SFC), which comprises an ordered sequence of VNFs [3]. By leveraging SFC technology, IoT users can define a sequence of heterogeneous VNF instances (such as IDS, NAT and FW) in a specified order to flexibly process the massive data flows generated by IoT applications. NFV empowers next-generation IoT networks to provide flexible and scalable services to a diverse range of IoT users.