Design and Evaluation of Deep Reinforcement Learning for Energy Saving in Open RAN

Matteo Bordin; Andrea Lacava; Michele Polese; Sai Satish; Manoj AnanthaSwamy Nittoor; Rajarajan Sivaraj; Francesca Cuomo; Tommaso Melodia

arXiv · 2410.14021

Design and Evaluation of Deep Reinforcement Learning for Energy Saving in Open RAN

Matteo Bordin·Andrea Lacava·Michele Polese·Sai Satish·Manoj AnanthaSwamy Nittoor·Rajarajan Sivaraj·Francesca Cuomo·Tommaso Melodia

View original source ↗Read source document ↗Export metadata ↓

Abstract

Next-generation wireless systems, already widely deployed, are expected to become even more prevalent in the future, representing challenges in both environmental and economic terms. This paper focuses on improving the energy efficiency of intelligent and programmable Open Radio Access Network (RAN) systems through the near-real-time dynamic activation and deactivation of Base Station (BS) Radio Frequency (RF) frontends using Deep Reinforcement Learning (DRL) algorithms, i.e., Proximal Policy Optimization (PPO) and Deep Q-Network (DQN). These algorithms run on the RAN Intelligent Controllers (RICs), part of the Open RAN architecture, and are designed to make optimal network-level decisions based on historical data without compromising stability and performance. We leverage a rich set of Key Performance Measurements (KPMs), serving as state for the DRL, to create a comprehensive representation of the RAN, alongside a set of actions that correspond to some control exercised on the RF frontend. We extend ns-O-RAN, an open-source, realistic simulator for 5G and Open RAN built on ns-3, to conduct an extensive data collection campaign. This enables us to train the agents offline with over 300,000 data points and subsequently evaluate the performance of the trained models. Results show that DRL agents improve energy efficiency by adapting to network conditions while minimally impacting the user experience. Additionally, we explore the trade-off between throughput and energy consumption offered by different DRL agent designs.

Explore related subjects

cs.NI

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Matteo Bordin, Andrea Lacava, Michele Polese, Sai Satish, Manoj AnanthaSwamy Nittoor, Rajarajan Sivaraj, Francesca Cuomo, Tommaso Melodia. 2024-10-17. Design and Evaluation of Deep Reinforcement Learning for Energy Saving in Open RAN. https://arxiv.org/abs/2410.14021

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

KEEP EXPLORING

Related papers

arXiv2026

Semord: Learned Semantic-Preserving Placement and Low-Fanout Routing for Distributed Vector Search

Vector databases are increasingly deployed in distributed settings where different users, sites, or domains maintain vector data. Existing vector databases rely on a coordinator to record which shards store which parts of the vector space and to route each query to those shards. In a decentralized setting, peers may join, leave, or move data without a trusted node tracking every change, and outdated routing information can therefore send queries to the wrong peers or require contacting many peers, reducing vector retrieval recall and increasing network latency. We present Semord, a decentralized vector search overlay system that achieves high recall by routing each ANN query to a small set of relevant peers, without relying on a centralized coordinator. Semord addresses this problem by making semantic locality routable: 1) We propose VHash to place semantically related vectors near each other in the overlay key space while avoiding load imbalance, so that each query only needs to contact a small neighborhood of peers for distributed local ANN ranking. 2) We design VecDHT, a communication protocol that maintains decentralized routing, region metadata, churn resilience, and VHash updates under membership and workload changes. Our extensive experiments on a real testbed show that Semord improves recall by more than 15% and reduces contacted peers by over 60% compared with decentralized baselines. Semord also approaches the recall and latency of a centralized oracle baseline while reducing peak peer-local ANN index memory by more than 2X. Controlled large-scale simulations further show that Semord scales across real-world embedding workloads and remains robust under churn for scoped vector retrieval as a decentralized overlay.

cs.NI↗

arXiv2026

Lizard: Bandwidth-Adaptive Real-Time Video Analytics through Content-Aware Packet Discarding at Last-Mile Edge Routers

The timeliness and accuracy of edge-based video analytics can be hindered by drastic reductions in available bandwidth (ABW) at last-mile edge routers, causing prolonged queuing delays. This work proposes Lizard, a system that leverages video-content-aware packet discarding to mitigate the negative effects of drastic ABW degradation that may frequently occur at a last-mile edge router by judiciously discarding packets that contain frame blocks less important to the analytics at the destination. To achieve this, we first devise a frame-block-aware RTP header extension to effectively decouple packet dependencies to encode frame blocks. Second, Lizard uses a priority-based feedback mechanism that dynamically evaluates packet priorities based on relative accuracy impacts. Third, we develop an adaptive phase-transition-based packet discarding strategy at the router to discard packets that represent unimportant blocks. Our evaluation of Lizard shows improvements over existing methods are substantial: 53.2% reduction in latency and 27.1% increase in analysis accuracy.

cs.NI↗

arXiv2026

Flux: Optimal Scheduling of Optical Circuit Switches for LLM Training

Optical Circuit Switching (OCS) offers high bandwidth density and energy efficiency for LLM training, but incurs a non-negligible reconfiguration delay. Prior work typically schedules optical circuit switches independently of compute, using aggregate traffic demand to determine which circuits to provision and when. We argue that this separation creates a fundamental inefficiency: reconfigurations that ignore the compute timeline can stall communication, resulting in low circuit utilization and large buffer requirements. In this paper, we present Flux, a scheduler that optimally schedules optical circuit switches based on the structure of the entire workload. Flux remains effective across a wide range of switching speeds by reusing circuits and amortizing reconfiguration delay behind compute and communication. We show that Flux reduces training iteration time by up to $10\times$ and peak NIC buffer requirements by more than three orders of magnitude compared to traditional periodic schedulers.

cs.NI↗