RL-TIME: Reinforcement Learning-based Task Replication in Multicore Embedded Systems

• URL: http://arxiv.org/abs/2503.12677v1
• Date: Sun, 16 Mar 2025 22:31:25 GMT
• Title: RL-TIME: Reinforcement Learning-based Task Replication in Multicore Embedded Systems
• Authors: Roozbeh Siyadatzadeh, Mohsen Ansari, Muhammad Shafique, Alireza Ejlali,
• Abstract summary: Task replication can improve reliability by duplicating a task's execution to handle transient and permanent faults.<n>Existing design-time methods typically choose the number of replicas based on worst-case conditions.<n>We present RL-TIME, a reinforcement learning-based approach that dynamically decides the number of replicas according to actual system conditions.
• Score: 6.184592401883041
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Embedded systems power many modern applications and must often meet strict reliability, real-time, thermal, and power requirements. Task replication can improve reliability by duplicating a task's execution to handle transient and permanent faults, but blindly applying replication often leads to excessive overhead and higher temperatures. Existing design-time methods typically choose the number of replicas based on worst-case conditions, which can waste resources under normal operation. In this paper, we present RL-TIME, a reinforcement learning-based approach that dynamically decides the number of replicas according to actual system conditions. By considering both the reliability target and a core-level Thermal Safe Power (TSP) constraint at run-time, RL-TIME adapts the replication strategy to avoid unnecessary overhead and overheating. Experimental results show that, compared to state-of-the-art methods, RL-TIME reduces power consumption by 63%, increases schedulability by 53%, and respects TSP 72% more often.

Related papers

• Improving the Efficiency of a Deep Reinforcement Learning-Based Power Management System for HPC Clusters Using Curriculum Learning [1.1380162891529537]
  Machine learning has shown promise in determining optimal times to switch nodes on or off.<n>In this study, we enhance the performance of a deep reinforcement learning (DRL) agent for HPC power management by integrating curriculum learning (CL)<n> Experimental results confirm that an easy-to-hard curriculum outperforms other training orders in terms of reducing wasted energy usage.
  arXiv  Detail & Related papers  (2025-02-27T18:19:22Z)
• RS-vHeat: Heat Conduction Guided Efficient Remote Sensing Foundation Model [59.37279559684668]
  We introduce RS-vHeat, an efficient multi-modal remote sensing foundation model.<n>Specifically, RS-vHeat applies the Heat Conduction Operator (HCO) with a complexity of $O(N1.5)$ and a global receptive field.<n>Compared to attention-based remote sensing foundation models, we reduce memory usage by 84%, FLOPs by 24% and improves throughput by 2.7 times.
  arXiv  Detail & Related papers  (2024-11-27T01:43:38Z)
• VinePPO: Unlocking RL Potential For LLM Reasoning Through Refined Credit Assignment [66.80143024475635]
  We propose VinePPO, a straightforward approach to compute unbiased Monte Carlo-based estimates. We show that VinePPO consistently outperforms PPO and other RL-free baselines across MATH and GSM8K datasets.
  arXiv  Detail & Related papers  (2024-10-02T15:49:30Z)
• Event-Triggered Reinforcement Learning Based Joint Resource Allocation for Ultra-Reliable Low-Latency V2X Communications [10.914558012458425]
  6G-enabled vehicular networks face the challenge ensuring low-latency communication (URLLC) for delivering safety-critical information in a timely manner. Traditional resource allocation schemes for vehicle-to-everything (V2X) communication systems rely on traditional decoding-based algorithms.
  arXiv  Detail & Related papers  (2024-07-18T23:55:07Z)
• REBEL: Reinforcement Learning via Regressing Relative Rewards [59.68420022466047]
  We propose REBEL, a minimalist RL algorithm for the era of generative models.<n>In theory, we prove that fundamental RL algorithms like Natural Policy Gradient can be seen as variants of REBEL.<n>We find that REBEL provides a unified approach to language modeling and image generation with stronger or similar performance as PPO and DPO.
  arXiv  Detail & Related papers  (2024-04-25T17:20:45Z)
• Deployable Reinforcement Learning with Variable Control Rate [14.838483990647697]
  We propose a variant of Reinforcement Learning (RL) with variable control rate. In this approach, the policy decides the action the agent should take as well as the duration of the time step associated with that action. We show the efficacy of SEAC through a proof-of-concept simulation driving an agent with Newtonian kinematics.
  arXiv  Detail & Related papers  (2024-01-17T15:40:11Z)
• Hybrid Reinforcement Learning for Optimizing Pump Sustainability in Real-World Water Distribution Networks [55.591662978280894]
  This article addresses the pump-scheduling optimization problem to enhance real-time control of real-world water distribution networks (WDNs) Our primary objectives are to adhere to physical operational constraints while reducing energy consumption and operational costs. Traditional optimization techniques, such as evolution-based and genetic algorithms, often fall short due to their lack of convergence guarantees.
  arXiv  Detail & Related papers  (2023-10-13T21:26:16Z)
• Fair and Efficient Distributed Edge Learning with Hybrid Multipath TCP [62.81300791178381]
  The bottleneck of distributed edge learning over wireless has shifted from computing to communication. Existing TCP-based data networking schemes for DEL are application-agnostic and fail to deliver adjustments according to application layer requirements. We develop a hybrid multipath TCP (MP TCP) by combining model-based and deep reinforcement learning (DRL) based MP TCP for DEL.
  arXiv  Detail & Related papers  (2022-11-03T09:08:30Z)
• Analysis of Reinforcement Learning for determining task replication in workflows [0.0]
  Executing on volunteer computing resources leads to unpredictability and often significantly increases execution time. This comes at the expense of a potentially significant increase in system and energy consumption. We propose the use of Reinforcement Learning (RL) such that a system may learn' the best' number of replicas to run to increase the number of load which complete promptly whilst minimising the additional workload on the system when replicas are not beneficial.
  arXiv  Detail & Related papers  (2022-09-14T12:53:21Z)
• Effective Multi-User Delay-Constrained Scheduling with Deep Recurrent Reinforcement Learning [28.35473469490186]
  Multi-user delay constrained scheduling is important in many real-world applications including wireless communication, live streaming, and cloud computing. We propose a deep reinforcement learning (DRL) algorithm, named Recurrent Softmax Delayed Deep Double Deterministic Policy Gradient ($mathttRSD4$) $mathttRSD4$ guarantees resource and delay constraints by Lagrangian dual and delay-sensitive queues, respectively. It also efficiently tackles partial observability with a memory mechanism enabled by the recurrent neural network (RNN) and introduces user-level decomposition and node-level
  arXiv  Detail & Related papers  (2022-08-30T08:44:15Z)
• Critic Regularized Regression [70.8487887738354]
  We propose a novel offline RL algorithm to learn policies from data using a form of critic-regularized regression (CRR) We find that CRR performs surprisingly well and scales to tasks with high-dimensional state and action spaces.
  arXiv  Detail & Related papers  (2020-06-26T17:50:26Z)
• Conservative Q-Learning for Offline Reinforcement Learning [106.05582605650932]
  We show that CQL substantially outperforms existing offline RL methods, often learning policies that attain 2-5 times higher final return. We theoretically show that CQL produces a lower bound on the value of the current policy and that it can be incorporated into a policy learning procedure with theoretical improvement guarantees.
  arXiv  Detail & Related papers  (2020-06-08T17:53:42Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.