Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2611.07390

Deep reinforcement learning-based optimization of multi-RAT handovers

Pavan Kumar Mangipudi·Satya Krishna Pothapragada·Alina Zare·Janise McNair
View original source ↗Read source document ↗Export metadata ↓

Abstract

A major evolutionary goal and challenge for next-generation wireless systems is seamless multiple radio access technology (multi-RAT) mobility. In a multi-RAT environment, handover decisions must account for both user quality of service and network priorities, including signal quality, resource availability, energy consumption, latency, and security. Although WiFi/cellular mobility is well explored in research and standardization, many conventional handover mechanisms continue to rely primarily on received signal strength. Such decisions may overlook link delay, congestion, and the distinct operating characteristics of heterogeneous RATs. In this work, we present the Reinforced Flexible Multi-RAT Selection framework (ReFlexMRS), a configurable Deep Reinforcement Learning (DRL)-based approach for multi-criteria handover target selection. ReFlexMRS is evaluated using an SDN-enabled multi-RAT testbed. The decision problem is formulated as a Markov Decision Process with a finite action space and is addressed using a Deep Q-Network (DQN) with convolutional layers that extract relationships among network measurement features. The agent is trained offline from collected network observations using reward guided Q-value updates, then used to select handover targets during inference. A 5G-WiFi case study demonstrates that ReFlexMRS can trade a small amount of throughput for substantial improvements in link delay, handover stability, and WiFi offloading. Compared with RSSI-based selection, the proposed formulations retain approximately 90-95% of the baseline throughput while reducing total handovers by up to 18% and WiFi-to-5G handovers by up to 13%, while maintaining the required RSSI levels.

Explore related subjects

cs.NI

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Pavan Kumar Mangipudi, Satya Krishna Pothapragada, Alina Zare, Janise McNair. 2026-11-05. Deep reinforcement learning-based optimization of multi-RAT handovers. https://arxiv.org/abs/2611.07390

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Worst-Case Discovery and Runtime Protection for RL-Based Network Controllers

RL-based controllers achieve strong average-case performance in networking tasks such as congestion control and adaptive bitrate streaming. Yet their performance can degrade severely under network conditions where strong performance is still achievable. Identifying such conditions and quantifying the resulting performance gap is intractable by enumeration, while the sequential and closed-loop nature of RL controllers makes formal verification methods impractical. We present ReGuard, a framework that discovers worst-case scenarios for a given RL controller and protects it against them at inference time without retraining. ReGuard formulates scenario discovery as a bilevel regret-maximization problem, certifying a lower bound on the controller's worst-case performance gap. ReGuard then analyzes the discovered counterfactual trajectories and compiles them into lightweight logic rules that intervene only when a risky state is detected, leaving the controller's behavior unchanged otherwise. We evaluate ReGuard across three RL-based network controllers: Pensieve, Sage, and Park. ReGuard discovers scenarios in which each controller suffers a 43-64% performance loss relative to what is achievable under the same conditions. ReGuard exposes performance gaps 57% to 6 times larger than those found by the strongest baselines and shrinks those gaps by 79-85% in its first iteration via lightweight rule-based protection, iteratively driving the remaining gap toward nominal levels. ReGuard's protection extends beyond the scenarios it discovers, improving performance across a wide range of network conditions.

cs.NI↗
arXiv2026

Understanding Self-Supervised Representation Learning for Encrypted Traffic

SSL has been adopted for encrypted traffic classification to learn representations from unlabeled traces and reduce reliance on manual feature engineering. However, recent studies show that data leakage can inflate reported performance and that pretrained models can underperform shallow classifiers once leakage is controlled. These findings raise questions about what information SSL can learn from encrypted traffic and how different pretraining mechanisms exploit this information. In this paper, we systematically investigate these questions by examining the sources of learnable information, the effectiveness of contextual pretraining, alternative self-supervision mechanisms, and the limits of representation learning. We first find that visible protocol fields retain contextual dependencies that are strongest between adjacent bytes, while payload interventions establish the classification value of retained plaintext structure. Guided by these insights, we investigate byte-level contextual learning through ByteBERT and TrafficDCNet, showing that aligning prediction granularity with local dependencies produces more discriminative representations. We further examine cross-view contrastive learning through AlignTraffic and find that complementary supervision improves representation quality beyond contextual prediction alone. Across four public classification tasks, AlignTraffic outperforms shallow learning by 5.97% to 30.70%, with additional evaluations on industrial traffic demonstrating its effectiveness in broader settings. Finally, evaluations on Tor traffic and individual packets reveal limitations when application information is concealed or unevenly distributed. These findings provide a systematic understanding of how observable information and self-supervision mechanisms shape the effectiveness and scope of representation learning for encrypted traffic.

cs.NI↗
arXiv2026

When Does Blockwise Additivity Break? Diagnosing and Repairing the Additive Assumption in Distillation-Based Architecture Search

Blockwise distillation methods for architecture search, such as DNA, DONNA, LANA and Puzzle, score each candidate replacement block in isolation and assemble a child network by minimizing the sum of per-block scores. We test this additive assumption on DeiT-S and DeiT-B with seven replacement blocks per layer, seven block-latency budgets from 70% to 40%, three fine-tuning seeds and paired bootstrap confidence intervals. (i) At mild compression the additive integer linear program (ILP) is close to a pairwise integer quadratic program (IQP) that models block interactions, but the post-fine-tuning gap widens sharply between the 60% and 55% budgets: at 55%-40% the ILP trails the IQP by 3.3-16.6 top-1 points on ImageNet-100. (ii) We split the KL additivity error into a metric component, caused by the non-linearity of the KL in summed logit changes and computable from cached single-block logits, and a functional component, the score-level effect of non-additive logit changes. The metric component accounts for most of the error on DeiT-S (59-65%), the functional component for most of it on DeiT-B (73-76%). (iii) A hybrid search ranks moves with the logit-sum predictor and measures only the best ones. It needs no dedicated pair measurements, costs 13-27% of the IQP's pair stage, and on ImageNet-100 significantly outperforms the IQP in 7 of 14 settings, with no significant difference in 6 and a significant loss in 1. Further reducing the pre-fine-tuning KL, or scoring after a short fine-tune, gives no consistent gain. On full ImageNet-1k with 1000-class fine-tuning, the sharp widening between 60% and 55% (5.8-17.5 points at 55%-40%), the model-dependent decomposition and the hybrid's advantage (significantly better than the IQP in 13 of 14 settings, no the other) are reproduced.

cs.NI↗