.png){kind=icon}
返回
Deep Reinforcement Learning Acceleration for Real-Time Edge Computing Mixed Integer Programming Problems
.png){kind=icon}
OA
AI
DOI：10.1109/ACCESS.2022.3147674.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
In this work, we present the design and implementation of an ultra-low latency Deep Reinforcement Learning (DRL) FPGA based accelerator for addressing hard real-time Mixed Integer Programming problems. The accelerator exhibits ultra-low latency performance for both training and inference operations, enabled by training-inference parallelism, pipelined training, on-chip weights and replay memory, multi-level replication-based parallelism and DRL algorithmic modifications such as distribution of training over time. The design principles can be extended to support hardware acceleration for other relevant DRL algorithms (embedding the experience replay technique) with hard real time constraints. We evaluate the accuracy of the accelerator in a task offloading and resource allocation problem stemming from a Mobile Edge Computing (MEC/5G) scenario. The design has been implemented on a Xilinx Zynq Ultrascale+ MPSoC ZCU104 evaluation kit using High Level Synthesis. The accelerator achieves near optimal performance and exhibits a 10-fold decrease in training-inference execution latency when compared to a high-end CPU-based implementation.
Keyword:
Training
Inference algorithms
Real-time systems
Artificial neural networks
Task analysis
Resource management
Field programmable gate arrays
Accelerator
deep reinforcement learning
edge computing
FPGA
high level synthesis
mixed integer programming
5G
期刊
IF:
3.6
论文数:
9.8W
被引数:
29.4W
机构
引用论文
.png){kind=icon}
Long-term Quality of Life After Intensive Care Unit Admission (a Single-Center Observational Study)OAAI
OAAI分享收藏Deep Reinforcement Learning for Online Computation Offloading in Wireless Powered Mobile-Edge Computing Networks用于无线供电的移动边缘计算网络中在线计算卸载的深度强化学习
OAAI
OAAI分享收藏Edge QoE: Computation Offloading With Deep Reinforcement Learning for Internet of Things边缘QoE: 物联网深度强化学习的计算卸载
PREAI
分享收藏
查看更多内容