A Latency‐Prediction‐Based Speculative Multipath Routing Method for SDN

Construction of a Distributed Control Plane in SDN Based on Speculative Prediction and Random Early Migration Control

This study addresses the Switch Migration Problem (SMP) in distributed Software‐Defined Networking (SDN) control planes and proposes a speculative predictive control‐based load balancing approach. Conventional methods usually migrate switches only after controllers are overloaded, leading to response delays and network inefficiencies. To mitigate this issue, this study introduces a time‐series forecasting model based on the Adaptive Exponential Smoothing Moving Average (AESMA) method, enabling proactive switch migration through the forecasting of controller load variations. The proposed method adopts an orchestration‐based architecture, categorizing controller loads into three states: Green (no migration required), Yellow (stochastic migration), and Red (immediate migration). This adaptive approach minimizes unnecessary switch migrations while maintaining efficient load distribution. Additionally, by leveraging Little's Law for load estimation, the proposed method anticipates overload conditions and initiates switch migration preemptively. Performance evaluations confirm that the proposed method improves network throughput, reduces response time, enhances load balancing fairness, and stabilizes migration behavior under dynamic traffic conditions. These improvements are achieved through the synergistic integration of AESMA‐based prediction and Random Early Migration (REM)‐based probabilistic control, enabling both proactive responsiveness and migration stability. © 2026 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

PPO-MS: Confidence-Aware and Collaborative Traffic Management for Multimedia Streaming in SDN

The rapid growth of multimedia streaming poses critical challenges, including bursty traffic and congestion, leading to playback delays. The existing separate prediction and control mechanisms for multimedia traffic scheduling, which are based on software-defined networks (SDN), are unable to proactively manage bursty traffic under uncertain conditions. This limitation is particularly evident in SDN-enabled backbone and multimedia-aware access networks, which typically assume centralized control and stable topologies. They lack integration of traffic prediction, traffic shaping, and real-time perception scheduling through reinforcement learning, resulting in low efficiency when exploring multiple paths in dynamic networks. To address this challenge, we propose PPO-MS (Proximal Policy Optimization-based Multimedia Scheduler), an SDN-based multimedia traffic scheduling algorithm integrating three key innovations: 1) A novel LSTM+HTB synergy where LSTM’s confidence intervals dynamically adjust HTB (Hierarchical Token Bucket) shaping parameters, enabling adaptive rate control under prediction uncertainty and overcoming the limitations of static LSTM+HTB hybrids; 2) A Deep Reinforcement Learning (DRL)-optimized path pruning method that reduces state and action spaces by generating a constrained set of $k$ disjoint candidate paths via an improved redundant tree algorithm. Unlike traditional multi-path schemes, this method tightly couples path preselection with the RL decision loop for adaptive, context-aware routing; 3) Generalized Advantage Estimation (GAE)-accelerated PPO for stable convergence in dynamic environments. In contrast to prior works (e.g., LSTM+RL for QoE or standalone tree algorithms), PPO-MS uniquely unifies these modules through confidence-aware traffic shaping and hierarchical decision-making, validated via comparative experiments. Results demonstrate that PPO-MS, through the synergistic integration of confidence-aware traffic shaping and DRL-optimized path pruning, significantly outperforms decoupled baselines. In particular, via isolation studies against simpler alternatives (e.g., mean-prediction and fixed-margin shaping), the confidence-aware shaping mechanism is validated to be superior under bursty traffic conditions. Overall, PPO-MS reduces end-to-end latency by 17.3% and packet loss by 32.4% while achieving 24.4% better load balancing during traffic bursts.

Rule-Aware VNE for SDN Resource Management

SDN-based hierarchically enhanced regularized routing optimization algorithm in space–ground–sea integrated network

Simulation results demonstrate that the proposed HRRO algorithm outperforms the conventional Dijkstra, OSPF, and RRO algorithms in reducing end-to-end latency, lowering packet loss rates, and improving network throughput.

Intelligent Link Failure Prediction and Optimization-Based QoS Routing in MANETs

This paper proposes an Intelligent Link Failure Prediction and QoS-Aware Routing framework for Mobile Ad Hoc Networks (MANETs) using the Harris Hawk Optimization (HHO) algorithm to achieve reliable and efficient data transmission under highly dynamic network conditions. The proposed model integrates proactive link failure prediction with HHO-based multi-objective route optimization to select stable, energy-efficient, and QoS-compliant paths. The framework is implemented and evaluated using the SimPy simulation environment under a realistic node mobility and traffic workload generated using Random Waypoint mobility with CBR and VBR traffic patterns, which is widely adopted for MANET performance evaluation. The proposed method is compared with Multi-Agent Deep Learning (MADL), Multi-Agent Deep Reinforcement Learning (MADRL), and the Communication-Aware Hierarchical Routing Framework (CAHRF). Experimental results demonstrate that the HHO-based approach significantly improves network performance by increasing the Packet Delivery Ratio (PDR) by 9.8-15.6%, reducing Link Failure Recovery Time by 21.4-34.7%, extending Network Lifetime by 18.2-27.9%, and decreasing Control Packet Cost by 16.5-25.3% compared to the benchmark methods. These improvements confirm that the proposed HHO-driven intelligent routing framework provides a robust, scalable, and QoS-aware solution for reliable communication in highly dynamic MANET environments.

Priority‐based contention‐avoidance resource allocation algorithm for disaggregated data centers

In this study, we propose a priority‐based contention‐avoidance (PCA) resource‐allocation method for disaggregated data centers (dDCs) that achieves a round‐trip time (RTT) of under 1 μs. The proposed scheme employs the disaggregated resource manager (dRM), which applies both the contention‐avoidance method and the best‐fit allocation (BFA) method, depending on whether an application is memory‐intensive (MI) or CPU‐intensive (CI), to ensure lower memory‐access delays for delay‐sensitive, higher‐priority services while promoting efficient resource allocation. This approach reduces contention and maintains priority balance by minimizing traffic concentration and prioritizing higher‐priority services across specific memory locations. We evaluate the performance of the proposed scheme in terms of RTT, memory‐access queuing delay, and end‐to‐end (ETE) delay using the OPNET simulator. The results demonstrate that the PCA scheme achieves the lowest latency, with a maximum of 0.89 μs, compared with maximum latencies of approximately 2.6 and 1.2 μs for the first‐fit allocation (FFA) and BFA schemes, respectively, when the offered load is 0.9.