A Bayesian Framework of Deep Reinforcement Learning for Joint O-RAN/MEC Orchestration

Fahri Wisnu Murti; Samad Ali; Matti Latva-aho

Home/Archive/arXiv

arXiv · 2312.16142

A Bayesian Framework of Deep Reinforcement Learning for Joint O-RAN/MEC Orchestration

Fahri Wisnu Murti·Samad Ali·Matti Latva-aho

View original source ↗Read source document ↗Export metadata ↓

Abstract

Multi-access Edge Computing (MEC) can be implemented together with Open Radio Access Network (O-RAN) over commodity platforms to offer low-cost deployment and bring the services closer to end-users. In this paper, a joint O-RAN/MEC orchestration using a Bayesian deep reinforcement learning (RL)-based framework is proposed that jointly controls the O-RAN functional splits, the allocated resources and hosting locations of the O-RAN/MEC services across geo-distributed platforms, and the routing for each O-RAN/MEC data flow. The goal is to minimize the long-term overall network operation cost and maximize the MEC performance criterion while adapting possibly time-varying O-RAN/MEC demands and resource availability. This orchestration problem is formulated as Markov decision process (MDP). However, the system consists of multiple BSs that share the same resources and serve heterogeneous demands, where their parameters have non-trivial relations. Consequently, finding the exact model of the underlying system is impractical, and the formulated MDP renders in a large state space with multi-dimensional discrete action. To address such modeling and dimensionality issues, a novel model-free RL agent is proposed for our solution framework. The agent is built from Double Deep Q-network (DDQN) that tackles the large state space and is then incorporated with action branching, an action decomposition method that effectively addresses the multi-dimensional discrete action with linear increase complexity. Further, an efficient exploration-exploitation strategy under a Bayesian framework using Thomson sampling is proposed to improve the learning performance and expedite its convergence. Trace-driven simulations are performed using an O-RAN-compliant model. The results show that our approach is data-efficient (i.e., converges faster) and increases the returned reward by 32\% than its non-Bayesian version.

Explore related subjects

cs.NI cs.LG

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Fahri Wisnu Murti, Samad Ali, Matti Latva-aho. 2023-12-26. A Bayesian Framework of Deep Reinforcement Learning for Joint O-RAN/MEC Orchestration. https://arxiv.org/abs/2312.16142

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

KEEP EXPLORING

Related papers

arXiv2026

CSI Simulation: Why Additive Noise Fails and How to Fix It

Channel State Information (CSI) has become a widely used wireless channel sensing modality for applications such as indoor localization, activity recognition, and respiration monitoring. Because collecting labeled data under every target condition is impractical, training CSI-based models often relies on simulated data produced by adding noise or perturbations to recorded channel estimates, most commonly additive white Gaussian noise (AWGN). This practice assumes that the receiver chain between the antenna and the channel estimator is linear and gain-invariant. We test this assumption empirically using RF jamming as a controlled perturbation on 6 commodity receivers across 2 indoor environments. The assumption does not hold. Automatic gain control compresses the channel estimate multiplicatively before digitization, producing amplitude distributions that no additive noise variance can reproduce. To close the resulting fidelity gap, we propose M_QTC, a measurement-calibrated model that learns the per-subcarrier distribution transformation through quantile mapping, temporal filtering, and copula-based cross-subcarrier reordering. M_QTC reduces amplitude error 8-fold and closes 89% of the aggregate fidelity gap across four complementary dimensions. The improvement transfers directly to downstream tasks, where 5 classifiers from different families trained on M_QTC-simulated data recover 93% of real-data jamming detection performance, while AWGN-trained classifiers remain near random decision.

cs.NI↗

arXiv2026

BALANCE: Hybrid Autoregressive-Speculative LLM Inference at the Network Edge

Edge inference is a promising paradigm to provide large language model (LLM) inference services in next-generation mobile networks. LLM inference mainly relies on two approaches: Autoregressive decoding (AD) generates output tokens sequentially, resulting in long latency; Speculative decoding (SD) accelerates inference by using a small language model (SLM) to generate multiple draft tokens for LLM verification, but incurs extra memory costs. Due to this latency-memory tradeoff, neither approach alone can efficiently serve users with heterogeneous demands under limited edge computing resources. To address this challenge, we propose a hybrid autoregressive-speculative inference (BALANCE) framework for edge LLM inference. In BALANCE, an edge server hosts both an SLM and an LLM, admits users, assigns each admitted user to the AD or SD mode, and performs the two modes simultaneously. To maximize the number of served users, we formulate a task throughput maximization problem to jointly determine user admission and computing resource allocation between AD and SD under user latency requirements and server memory constraints. Since the problem is NP-hard, we develop a polynomial-time algorithm that transforms the original problem into two sub-problems and obtains a sub-optimal solution with a constant approximation guarantee. Experiments demonstrate that BALANCE consistently outperforms conventional AD and SD and significantly improves task throughput.

cs.NI↗

arXiv2026

Zero-Knowledge Remote Adversarial Attack against Wi-Fi-based Human Activity Recognition for Privacy Protection

The growing capability of Wi-Fi devices to identify human activities using channel state information (CSI) raises privacy concerns. To counter this threat, we propose GRAW, an adversary system, acting as a privacy defender, that degrades the human activity recognition (HAR) system at the user device by perturbing the router's signals that the device uses to estimate CSI. GRAW employs generative adversarial imitation learning (GAIL) to construct perturbation signals, and thereby eliminates the need for any information on the target HAR systems and their inputs (i.e., zero-knowledge operation). We evaluate GRAW against seven representative HAR models, using datasets collected in five environments, including our own dataset. We observe that GRAW is the only remote attack scheme that degrades every tested HAR model to a random-selection level. At the same perturbation level, GRAW achieves an attack success ratio up to 76.7% higher than comparison methods, while maintaining over 99% packet success rate on regular Wi-Fi communication. We demonstrate the feasibility of GRAW through real-time, over-the-air experiments with software-defined radios.

cs.NI↗