Edge computing plays a critical role in the Internet of Things (IoT) environment as it potentially supports the time-critical IoT applications’ resources as well as latency requirements. In the near future, most edge service providers are envisioned to receive revenue from deploying these applications with the expenditures proportional to placing the offloaded requests from IoT devices and allocating the required resources. One way to maximize the edge profit and minimize the response latency is to integrate the edge nodes and form the edge federation. Therefore, edge service providers can have interoperability to distribute the IoT requests on the appropriate edge nodes in the light of providing satisfactory service levels to meet their objectives. Since the edge nodes are volatile and IoT time-critical applications are increasing, the edge nodes are envisioned to face massive traffic from IoT devices. Therefore, exploiting the traditional dynamic requests placement approaches cannot meet the SLA requirement of both IoT devices and edge service providers. In this article, we designed an intelligent reinforcement learning-based request service provisioning system (i.e., here, we call Edge-AI) as part of a smart edge orchestrator in the edge federation. We implement the proposed method, which is called DRL-Dispatcher, and compare it with greedy and random algorithms in edge federation. The experimental results show that the proposed DRL-Dispatcher performs better in terms of profit and low response latency as compared with the baseline approaches.

Network Function Virtualization (NFV), as a promising paradigm, speeds up the service deployment by separating network functions from proprietary devices and deploying them on common servers in the form of software. Any service in NFV-enabled networks is achieved as a Service Function Chain (SFC) which consists of a series of ordered Virtual Network Functions (VNFs). However, migration of VNFs for more flexible services within a dynamic NFV-enabled network is a key challenge to be addressed. Current VNF migration studies mainly focus on single VNF migration decisions without considering the sharing and concurrent migration of VNF instances. In this paper, we assume that each deployed VNF is used by multiple SFCs and deal with the optimal placement for the contemporaneous migration of VNFs based on the actual network situation. We formalize the VNF migration and SFC reconfiguration problem as a mathematical model, which aims to minimize the VNF migration between nodes or the total number of core changes per node. The approach is a two-stage MILP based on optimal order to solve the reconfiguration. Extensive evaluation shows that the proposed approach can reduce the change in terms of location or number of cores per node in a 6-node and 14-node networks while ensuring network latency compared with the model without reconfiguration.

5G technology offers numerous advantages, including high data rates, improved connectivity, reduced latency, and increased reliability. These benefits have favored the evolution of network architecture, particularly the disaggregation of radio access networks (RAN) into three distinct functional components: radio units (RU), distributed units (DU), and centralized units (CU). This modular segmentation directly affects deployment costs and energy consumption. In this study, we propose a mixed-integer linear programming (MILP) model to minimize the deployment costs of DU and CU functions while considering network indicators and resource constraints in the context of enhanced Mobile Broadband (eMBB) services. The model is evaluated based on a network topology in which radio units (RUs), candidate sites (CSs), and data centers (DCs) are distributed across a territory. The objective is to identify the optimal candidate sites for deploying the DU and CU functions to ensure a continuous service path from the RU to the DC. To ensure the scalability of the solution on large-scale networks and reduce computation time, we also developed a heuristic algorithm capable of providing solutions close to those obtained by the MILP solver. The simulation results indicate that the operator’s defined latency constraints and functional split type significantly influence deployment costs.

The complexity of modern microservice architectures has surpassed the capabilities of traditional orchestration tools, which rely on static, manual workflows. This limits scalability and adaptability, especially to dynamic workloads. This paper argues for a paradigm shift towards self-managing, intent-driven microservices orchestration systems, where human operators express high-level goals in natural language. As a foundational step towards this vision of autonomous orchestration agents, we introduce LEMON: a new architecture that leverages Large Language Models (LLMs) for intelligent microservice monitoring. We also propose a comprehensive classification to structure this emerging field. Our evaluation demonstrates that fine-tuning Small Language Models (SLMs) for intent classification significantly enhances accuracy while ensuring the model's output is reliably structured for automation. Furthermore, our analysis of the trade-offs between model size, precision, and latency provides a practical guide for deploying these systems. We foresee this monitoring capability as the critical ”sense” component toward autonomous microservices orchestration loops. By diagnosing performance bottlenecks from natural language queries, LEMON enables future systems to automatically suggest and execute solutions. This work lays the groundwork for truly self-managing, intent-driven systems.