GymD2D: A Device-to-Device Underlay Cellular Offload Evaluation Platform

• URL: http://arxiv.org/abs/2101.11188v1
• Date: Wed, 27 Jan 2021 03:50:22 GMT
• Title: GymD2D: A Device-to-Device Underlay Cellular Offload Evaluation Platform
• Authors: David Cotton, Zenon Chaczko
• Abstract summary: GymD2D is a framework for experimentation with physical layer resource allocation problems in device-to-device communication. It allows users to simulate a variety of cellular offload scenarios and to extend its behaviour to meet their research needs. We evaluate GymD2D with state-of-the-art deep reinforcement learning and demonstrate these algorithms provide significant efficiency improvements.
• Score: 1.5863809575305414
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Cellular offloading in device-to-device communication is a challenging optimisation problem in which the improved allocation of radio resources can increase spectral efficiency, energy efficiency, throughout and reduce latency. The academic community have explored different optimisation methods on these problems and initial results are encouraging. However, there exists significant friction in the lack of a simple, configurable, open-source framework for cellular offload research. Prior research utilises a variety of network simulators and system models, making it difficult to compare results. In this paper we present GymD2D, a framework for experimentation with physical layer resource allocation problems in device-to-device communication. GymD2D allows users to simulate a variety of cellular offload scenarios and to extend its behaviour to meet their research needs. GymD2D provides researchers an evaluation platform to compare, share and build upon previous research. We evaluated GymD2D with state-of-the-art deep reinforcement learning and demonstrate these algorithms provide significant efficiency improvements.

Related papers

• Task-Oriented Real-time Visual Inference for IoVT Systems: A Co-design Framework of Neural Networks and Edge Deployment [61.20689382879937]
  Task-oriented edge computing addresses this by shifting data analysis to the edge. Existing methods struggle to balance high model performance with low resource consumption. We propose a novel co-design framework to optimize neural network architecture.
  arXiv  Detail & Related papers  (2024-10-29T19:02:54Z)
• Generalization of Fitness Exercise Recognition from Doppler Measurements by Domain-adaption and Few-Shot Learning [12.238586191793997]
  In previous works, a mobile application was developed using an unmodified commercial off-the-shelf smartphone to recognize whole-body exercises. Applying such a lab-environment trained model on realistic application variations causes a significant drop in performance. This paper presents a database with controlled and uncontrolled subsets of fitness exercises.
  arXiv  Detail & Related papers  (2023-11-20T16:40:48Z)
• DLAS: An Exploration and Assessment of the Deep Learning Acceleration Stack [3.7873597471903935]
  We combine machine learning and systems techniques within the Deep Learning Acceleration Stack (DLAS) We evaluate the impact on accuracy and inference time when varying different parameters of DLAS across two datasets. Overall we make 13 key observations, including that speedups provided by compression techniques are very hardware dependent.
  arXiv  Detail & Related papers  (2023-11-15T12:26:31Z)
• Filling the Missing: Exploring Generative AI for Enhanced Federated Learning over Heterogeneous Mobile Edge Devices [72.61177465035031]
  We propose a generative AI-empowered federated learning to address these challenges by leveraging the idea of FIlling the MIssing (FIMI) portion of local data. Experiment results demonstrate that FIMI can save up to 50% of the device-side energy to achieve the target global test accuracy.
  arXiv  Detail & Related papers  (2023-10-21T12:07:04Z)
• Energy Minimization for Federated Asynchronous Learning on Battery-Powered Mobile Devices via Application Co-running [14.169614178617664]
  Energy is an essential, but often forgotten aspect in large-scale federated systems. In this paper, we design and implement an online optimization framework by connecting asynchronous execution of federated training with application co-running. Experiments demonstrate that the online optimization framework can save over 60% energy with 3 times faster convergence speed compared to the previous schemes.
  arXiv  Detail & Related papers  (2022-04-29T04:34:06Z)
• Dynamic Network-Assisted D2D-Aided Coded Distributed Learning [59.29409589861241]
  We propose a novel device-to-device (D2D)-aided coded federated learning method (D2D-CFL) for load balancing across devices. We derive an optimal compression rate for achieving minimum processing time and establish its connection with the convergence time. Our proposed method is beneficial for real-time collaborative applications, where the users continuously generate training data.
  arXiv  Detail & Related papers  (2021-11-26T18:44:59Z)
• PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics [89.81550748680245]
  We introduce a new differentiable physics benchmark called PasticineLab. In each task, the agent uses manipulators to deform the plasticine into the desired configuration. We evaluate several existing reinforcement learning (RL) methods and gradient-based methods on this benchmark.
  arXiv  Detail & Related papers  (2021-04-07T17:59:23Z)
• To Talk or to Work: Flexible Communication Compression for Energy Efficient Federated Learning over Heterogeneous Mobile Edge Devices [78.38046945665538]
  federated learning (FL) over massive mobile edge devices opens new horizons for numerous intelligent mobile applications. FL imposes huge communication and computation burdens on participating devices due to periodical global synchronization and continuous local training. We develop a convergence-guaranteed FL algorithm enabling flexible communication compression.
  arXiv  Detail & Related papers  (2020-12-22T02:54:18Z)
• Learning Centric Wireless Resource Allocation for Edge Computing: Algorithm and Experiment [15.577056429740951]
  Edge intelligence is an emerging network architecture that integrates sensing, communication, computing components, and supports various machine learning applications. Existing methods ignore two important facts: 1) different models have heterogeneous demands on training data; 2) there is a mismatch between the simulated environment and the real-world environment. This paper proposes the learning centric wireless resource allocation scheme that maximizes the worst learning performance of multiple tasks.
  arXiv  Detail & Related papers  (2020-10-29T06:20:40Z)
• A Data and Compute Efficient Design for Limited-Resources Deep Learning [68.55415606184]
  equivariant neural networks have gained increased interest in the deep learning community. They have been successfully applied in the medical domain where symmetries in the data can be effectively exploited to build more accurate and robust models. Mobile, on-device implementations of deep learning solutions have been developed for medical applications. However, equivariant models are commonly implemented using large and computationally expensive architectures, not suitable to run on mobile devices. In this work, we design and test an equivariant version of MobileNetV2 and further optimize it with model quantization to enable more efficient inference.
  arXiv  Detail & Related papers  (2020-04-21T00:49:11Z)
• MDLdroid: a ChainSGD-reduce Approach to Mobile Deep Learning for Personal Mobile Sensing [14.574274428615666]
  Running deep learning on devices offers several advantages including data privacy preservation and low-latency response for both model robustness and update. Personal mobile sensing applications are mostly user-specific and highly affected by environment. We present MDLdroid, a novel decentralized mobile deep learning framework to enable resource-aware on-device collaborative learning.
  arXiv  Detail & Related papers  (2020-02-07T16:55:21Z)

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.