Online Adaptive Learning for Runtime Resource Management of
Heterogeneous SoCs
- URL: http://arxiv.org/abs/2008.09728v1
- Date: Sat, 22 Aug 2020 01:39:32 GMT
- Title: Online Adaptive Learning for Runtime Resource Management of
Heterogeneous SoCs
- Authors: Sumit K. Mandal, Umit Y. Ogras, Janardhan Rao Doppa, Raid Z. Ayoub,
Michael Kishinevsky, Partha P. Pande
- Abstract summary: This paper describes the use of predictive models for online control using two modern approaches: imitation learning (IL) and an explicit nonlinear model predictive control (NMPC)
Evaluations on a commercial mobile platform with 16 benchmarks show that the IL approach successfully adapts the control policy to unknown applications.
The explicit NMPC provides 25% energy savings compared to a state-of-the-art algorithm for multi-variable power management of modern GPU sub-systems.
- Score: 15.523246628432654
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Dynamic resource management has become one of the major areas of research in
modern computer and communication system design due to lower power consumption
and higher performance demands. The number of integrated cores, level of
heterogeneity and amount of control knobs increase steadily. As a result, the
system complexity is increasing faster than our ability to optimize and
dynamically manage the resources. Moreover, offline approaches are sub-optimal
due to workload variations and large volume of new applications unknown at
design time. This paper first reviews recent online learning techniques for
predicting system performance, power, and temperature. Then, we describe the
use of predictive models for online control using two modern approaches:
imitation learning (IL) and an explicit nonlinear model predictive control
(NMPC). Evaluations on a commercial mobile platform with 16 benchmarks show
that the IL approach successfully adapts the control policy to unknown
applications. The explicit NMPC provides 25% energy savings compared to a
state-of-the-art algorithm for multi-variable power management of modern GPU
sub-systems.
Related papers
- A Dynamic Feedforward Control Strategy for Energy-efficient Building
System Operation [59.56144813928478]
In current control strategies and optimization algorithms, most of them rely on receiving information from real-time feedback.
We propose an engineer-friendly control strategy framework that embeds dynamic prior knowledge from building system characteristics simultaneously for system control.
We tested it in a case for heating system control with typical control strategies, which shows our framework owns a further energy-saving potential of 15%.
arXiv Detail & Related papers (2023-01-23T09:07:07Z) - Efficient Learning of Voltage Control Strategies via Model-based Deep
Reinforcement Learning [9.936452412191326]
This article proposes a model-based deep reinforcement learning (DRL) method to design emergency control strategies for short-term voltage stability problems in power systems.
Recent advances show promising results in model-free DRL-based methods for power systems, but model-free methods suffer from poor sample efficiency and training time.
We propose a novel model-based-DRL framework where a deep neural network (DNN)-based dynamic surrogate model is utilized with the policy learning framework.
arXiv Detail & Related papers (2022-12-06T02:50:53Z) - Active Learning of Discrete-Time Dynamics for Uncertainty-Aware Model
Predictive Control [49.60520501097199]
We present a self-supervised learning approach that actively models the dynamics of nonlinear robotic systems.
Our approach showcases high resilience and generalization capabilities by consistently adapting to unseen flight conditions.
arXiv Detail & Related papers (2022-10-23T00:45:05Z) - Meta-Reinforcement Learning for Adaptive Control of Second Order Systems [3.131740922192114]
In process control, many systems have similar and well-understood dynamics, which suggests it is feasible to create a generalizable controller through meta-learning.
We formulate a meta reinforcement learning (meta-RL) control strategy that takes advantage of known, offline information for training, such as a model structure.
A key design element is the ability to leverage model-based information offline during training, while maintaining a model-free policy structure for interacting with new environments.
arXiv Detail & Related papers (2022-09-19T18:51:33Z) - Fully Decentralized Model-based Policy Optimization for Networked
Systems [23.46407780093797]
This work aims to improve data efficiency of multi-agent control by model-based learning.
We consider networked systems where agents are cooperative and communicate only locally with their neighbors.
In our method, each agent learns a dynamic model to predict future states and broadcast their predictions by communication, and then the policies are trained under the model rollouts.
arXiv Detail & Related papers (2022-07-13T23:52:14Z) - Real-time Neural-MPC: Deep Learning Model Predictive Control for
Quadrotors and Agile Robotic Platforms [59.03426963238452]
We present Real-time Neural MPC, a framework to efficiently integrate large, complex neural network architectures as dynamics models within a model-predictive control pipeline.
We show the feasibility of our framework on real-world problems by reducing the positional tracking error by up to 82% when compared to state-of-the-art MPC approaches without neural network dynamics.
arXiv Detail & Related papers (2022-03-15T09:38:15Z) - Learning to Continuously Optimize Wireless Resource in a Dynamic
Environment: A Bilevel Optimization Perspective [52.497514255040514]
This work develops a new approach that enables data-driven methods to continuously learn and optimize resource allocation strategies in a dynamic environment.
We propose to build the notion of continual learning into wireless system design, so that the learning model can incrementally adapt to the new episodes.
Our design is based on a novel bilevel optimization formulation which ensures certain fairness" across different data samples.
arXiv Detail & Related papers (2021-05-03T07:23:39Z) - Scheduling and Power Control for Wireless Multicast Systems via Deep
Reinforcement Learning [33.737301955006345]
Multicasting in wireless systems is a way to exploit the redundancy in user requests in a Content Centric Network.
Power control and optimal scheduling can significantly improve the wireless multicast network's performance under fading.
We show that power control policy can be learnt for reasonably large systems via this approach.
arXiv Detail & Related papers (2020-09-27T15:59:44Z) - Learning High-Level Policies for Model Predictive Control [54.00297896763184]
Model Predictive Control (MPC) provides robust solutions to robot control tasks.
We propose a self-supervised learning algorithm for learning a neural network high-level policy.
We show that our approach can handle situations that are difficult for standard MPC.
arXiv Detail & Related papers (2020-07-20T17:12:34Z) - An Energy-Aware Online Learning Framework for Resource Management in
Heterogeneous Platforms [16.94738988958929]
Mobile platforms must satisfy the contradictory requirements of fast response time and minimum energy consumption.
To address this need, system-on-chips provide a variety of control knobs, such as the number of active cores and their voltage/frequency levels.
Control policies designed offline are at best sub-optimal since many potential new applications are unknown at design-time.
arXiv Detail & Related papers (2020-03-20T22:59:35Z) - Information Theoretic Model Predictive Q-Learning [64.74041985237105]
We present a novel theoretical connection between information theoretic MPC and entropy regularized RL.
We develop a Q-learning algorithm that can leverage biased models.
arXiv Detail & Related papers (2019-12-31T00:29:22Z)
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.