Yuqian Song

Internet service providers (ISPs) require modern networks to deliver high service satisfaction across diverse traffic types while maintaining minimal operational overhead. Traditional routing algorithms, although computationally efficient, rely on fixed heuristics and often fail to accommodate increasingly dynamic and heterogeneous network demands. In contrast, deep reinforcement learning (DRL)-based routing algorithms offer greater flexibility but typically introduce considerable computational cost. This issue is especially pronounced in prevalent centralized software-defined networking (SDN) architectures, resulting in excessive overhead and increased latency as the network grows. In this paper, we model a hybrid-traffic network scenario and propose a quality of service (QoS)-aware and low-cost routing algorithm based on graph reinforcement learning within a hybrid knowledge-defined networking (KDN) architecture. Routing decisions are jointly made by a global controller and distributed forwarding devices, with the unified objective of maximizing the minimum service satisfaction rate across the network. To reduce computational overhead and minimize disruptions from frequent route updates, we investigate two efficient implementation strategies: partial deployment (horizontal) and intermittent activation (vertical). Experimental results demonstrate that the proposed algorithm significantly outperforms benchmarks regarding the minimum service satisfaction rate, even under previously unseen topologies. Remarkably, our evaluation shows that 50% of the maximum achievable performance gain can be obtained through a lightweight implementation where just 28.5% of forwarding devices conduct policy inference, operating for only 60% of the total run time.

The rapid proliferation of end devices and their hosted applications has significantly increased the demand for data processing. However, lightweight edge endpoints often suffer from limited computational capabilities due to power and battery constraints. Consequently, computation-intensive tasks are typically offloaded to cloud servers located in data centers for processing. While existing studies often abstract the edge–cloud connection as a direct link, the actual backbone network features complex topologies and constrained bandwidth, which intensify as workload scales up. To address this challenge, this paper investigates routing optimization within the backbone network under task offloading scenarios, and proposes a workload-aware deep reinforcement learning (DRL)-based routing algorithm for joint minimization of transmission and processing delays. Specifically, we first develop a detailed system model using discrete event simulation. Then, we design an integrated DRL-based decision-making scheme that simultaneously determines optimal routing paths and target data centers. Extensive experiments on diverse real-world network topologies and heterogeneous task workloads demonstrate that the proposed algorithm significantly outperforms conventional baselines in reducing both transmission and processing delays.

The Internet today hosts a multitude of communication sessions from diverse vertical industries, each with distinct and increasingly stringent quality-of-service (QoS) requirements across multiple performance metrics. However, QoS-aware routing remains a significant challenge in traffic engineering, as existing solutions struggle to adapt to dynamic network conditions and meet these rigorous QoS demands. To address this issue, this paper proposes a multi-agent graph reinforcement learning-based routing algorithm that provides differentiated treatment for multiple services. First, we explore both node-based and link-based graph reinforcement learning paradigms for performance comparison. Second, two key mechanisms, i.e., a packet sacrifice mechanism and a Tchebycheff-based reward function, are designed to realize adaptive sacrifice behavior patterns, aiming to optimize the lower bound of service satisfaction rates and enhance fairness across services. Furthermore, to ensure practical applicability, we devise a distributed computing architecture featuring neighborhood-restricted data acquisition and asynchronous historical information retrieval. Extensive simulation results demonstrate that our proposed algorithms significantly outperform benchmark methods regarding the minimum service satisfaction rate, even under unseen networks. Besides, the distributed computing architecture is proven to incur no performance penalty, which can be generalized to other resource-constrained applications.

Packet routing in modern communication networks faces increasing challenges due to evolving network dynamics and stringent quality-of-service (QoS) requirements. Traditional rule-based and model-based routing methods, constrained by pre-defined rules and static network assumptions, often fail to address these complexities. This paper presents an experience-driven, model-free routing algorithm grounded in deep reinforcement learning (DRL), offering adaptive and efficient forwarding decisions. For practical deployment, we incorporate GraphTransformer networks into the DRL decision framework to enhance generalization under diverse and unseen network conditions. Specifically, we explore two element-level mapping paradigms, node-based and edge-based, to identify the optimal configuration. In addition, we design a hybrid action space that effectively incorporates domain-specific knowledge, thereby contributing to a more robust DRL agent in dynamic routing environments. Simulation results indicate that our proposed algorithms demonstrate significant robustness and generalization capabilities, revealing key principles for designing an optimal GNN-enhanced DRL-based routing algorithm.

The Third Generation Partnership Project has standardized new-radio vehicle-to-everything (NR-V2X) to facilitate advanced use cases for safety-critical message conveyance. However, there is a paucity of resource allocation research for high-performance NR-V2X communications. In this article, we investigate an adaptive optimization issue of energy efficiency (EE) and Quality of Service (QoS) in NR-V2X networks inspired by the Tchebycheff function. To address this issue, we first formulate the resource allocation task as a time-variant mixed-integer nonlinear programming (MINLP) problem. Then, we propose a fully decentralized multiagent deep reinforcement learning (MADRL)-based algorithm characterized by a multitask-actor shared-critic (MTA-SC) architecture and a localized training and distributed execution (LTDE) framework to promote efficient learning and minimize information exchange. Finally, we implement the proposed algorithm in a three-lane highway NR-V2X scenario. Numerical results demonstrate that the proposed algorithm comprehensively outperforms benchmarks in terms of convergence performance, scalability, and robustness.

Mobile edge computing (MEC) is an enabling technology for next-generation network architectures to deliver more diversified communication services and meet more demanding quality-of-service (QoS) requirements. However, owing to the growing scale and heterogeneity of the networks, energy-efficient resource allocation in heterogeneous MEC (Het-MEC) networks faces great challenges. As an emerging research area, multi-agent deep reinforcement learning (MADRL) is expected to realize autonomous resource allocation in Het-MEC networks by learning from trial and error. Nevertheless, existing MADRL-based solutions are usually not applicable to practical scenarios by the limitations of centralized control schemes or massive signaling overhead. To address the issue, we first formulate the energy-efficient resource allocation problem in Het-MEC networks as a time-variant mixed-integer nonlinear programming (MINLP) problem. Then, we propose a fully decentralized collaborative MADRL-based algorithm featuring the multi-actor shared-critic (MASC) architecture and the regional training distributed execution (RTDE) framework, which effectively stabilizes model training and reduces information exchange, respectively. Finally, we conduct extensive simulations to evaluate the performance of the proposed algorithm. Numerical results demonstrate that the proposed algorithm comprehensively outperforms several mainstream baseline methods in terms of convergence performance, scalability, and robustness.

As a promising technology in the 5G era, the artificial intelligence (AI) enabled Internet of controllable things (IoCT) is expected to be an integral part of heterogeneous networks (HetNets) in the future. However, the realization of ultra-reliable low-latency communications (URLLC) in IoCT communications underlaid HetNet has stringent quality of service (QoS) requirements, resulting in unprecedented challenges for existing wireless resource allocation methods. In this paper, we first describe a cellular HetNet model with uplink IoCT communications, then formulate a dynamic mixed-integer nonlinear programming (MINLP) resource allocation problem for maximizing the long-term average energy efficiency under URLLC requirements including reliability, latency, and transmission rate. To solve the problem, we propose a decentralized MADRL-based resource allocation algorithm with a decentralized partially observable Markov decision process (dec-POMDP) and a mixed-centralized-decentralized (MCD) framework to address the partial observability and the scalability issues, respectively. In addition, we design a reward function featuring the objective decomposition, baseline-guided scaling, and QoS violation penalty so that the agents are coordinated. Extensive experiments demonstrate the convergence, scalability, and robustness of the proposed algorithm. Besides, the proposed algorithm substantially outperforms conventional resource allocation methods and different agent communication mechanisms in terms of maximizing energy efficiency.