Learning to Continuously Optimize Wireless Resource in Episodically Dynamic Environment

Sun, Haoran; Pu, Wenqiang; Zhu, Minghe; Fu, Xiao; Chang, Tsung-Hui; Mei, Hong

doi:10.1109/icassp39728.2021.9413503

Cited by 18 publications

(9 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, due to the distribution shift for system parameters in episodically dynamic environment, the trained model may suffer from performance deterioration when the dataset follows a different distribution in the inference stage [22]. Transfer learning [103] and continual learning [277] have recently been adopted to address such task mismatch issue in the "learning to optimize" framework considering the system distribution dynamics.…”

Section: ) Mixed-combinatorial Optimizationmentioning

confidence: 99%

Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications

Letaief

Shi

et al. 2022

IEEE J. Select. Areas Commun.

352

143

View full text Add to dashboard Cite

The thriving of artificial intelligence (AI) applications is driving the further evolution of wireless networks. It has been envisioned that 6G will be transformative and will revolutionize the evolution of wireless from "connected things" to "connected intelligence". However, state-of-the-art deep learning and big data analytics based AI systems require tremendous computation and communication resources, causing significant latency, energy consumption, network congestion, and privacy leakage in both of the training and inference processes. By embedding model training and inference capabilities into the network edge, edge AI stands out as a disruptive technology for 6G to seamlessly integrate sensing, communication, computation, and intelligence, thereby improving the efficiency, effectiveness, privacy, and security of 6G networks. In this paper, we shall provide our vision for scalable and trustworthy edge AI systems with integrated design of wireless communication strategies and decentralized machine learning models. New design principles of wireless networks, service-driven resource allocation optimization methods, as well as a holistic end-to-end system architecture to support edge AI will be described. Standardization, software and hardware platforms, and application scenarios are also discussed to facilitate the industrialization and commercialization of edge AI systems.

show abstract

Section: ) Mixed-combinatorial Optimizationmentioning

confidence: 99%

Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications

Letaief

Shi

et al. 2022

IEEE J. Select. Areas Commun.

352

143

View full text Add to dashboard Cite

show abstract

“…In this section, we illustrate the performance of the proposed CL framework using two different applications: 1) power control for weighted sum-rate (WSR) maximization problem with single-input single-output (SISO) interference channel defined in (1), where the end-to-end learning based DNN is used; see [11] for details about the architecture; 2) beamforming for WSR maximization problem with multi-input singleoutput (MISO) interference channel, where deep unfolding based DNN architecture is used; see [17] for details about the architecture. By demonstrating the effectiveness of the proposed methods on these two approaches, we believe that our approach can be extended to many other related problems as well.…”

Section: Resultsmentioning

confidence: 99%

Learning to Continuously Optimize Wireless Resource In Episodically Dynamic Environment

Sun,

Pu,

Zhu

et al. 2020

Preprint

Self Cite

View full text Add to dashboard Cite

There has been a growing interest in developing data-driven and in particular deep neural network (DNN) based methods for modern communication tasks. For a few popular tasks such as power control, beamforming, and MIMO detection, these methods achieve state-of-the-art performance while requiring less computational efforts, less channel state information (CSI), etc. However, it is often challenging for these approaches to learn in a dynamic environment where parameters such as CSIs keep changing.This work develops a methodology that enables data-driven methods to continuously learn and optimize in a dynamic environment. Specifically, we consider an "episodically dynamic" setting where the environment changes in "episodes", and in each episode the environment is stationary. We propose to build the notion of continual learning (CL) into the modeling process of learning wireless systems, so that the learning model can incrementally adapt to the new episodes, without forgetting knowledge learned from the previous episodes. Our design is based on a novel min-max formulation which ensures certain "fairness" across different data samples. We demonstrate the effectiveness of the CL approach by customizing it to two popular DNN based models (one for power control and one for beamforming), and testing using both synthetic and real data sets. These numerical results show that the proposed CL approach is not only able to adapt to the new scenarios quickly and seamlessly, but importantly, it maintains high performance over the previously encountered scenarios as well.

show abstract

“…The analog beamformers obtained by offline training can well adapt to CSI statistics when it does not change [21]. When it changes, we obtain channel samples and employ transfer learning [47] to fine tune the parameters of the deep-unfolding NN, where the analog beamformers are updated to better fit the change of CSI statistics [48].…”

Section: B the Training And The Data Transmission Stagementioning

confidence: 99%

Mixed-Timescale Deep-Unfolding for Joint Channel Estimation and Hybrid Beamforming

Kang

et al. 2022

IEEE J. Select. Areas Commun.

View full text Add to dashboard Cite

In massive multiple-input multiple-output (MIMO) systems, hybrid analog-digital beamforming is an essential technique for exploiting the potential array gain without using a dedicated radio frequency chain for each antenna. However, due to the large number of antennas, the conventional channel estimation and hybrid beamforming algorithms generally require high computational complexity and signaling overhead. In this work, we propose an end-to-end deep-unfolding neural network (NN) joint channel estimation and hybrid beamforming (JCEHB) algorithm to maximize the system sum rate in time-division duplex (TDD) massive MIMO. Specifically, the recursive least-squares (RLS) algorithm and stochastic successive convex approximation (SSCA) algorithm are unfolded for channel estimation and hybrid beamforming, respectively. In order to reduce the signaling overhead, we consider a mixed-timescale hybrid beamforming scheme, where the analog beamforming matrices are optimized based on the channel state information (CSI) statistics offline, while the digital beamforming matrices are designed at each time slot based on the estimated low-dimensional equivalent CSI matrices. We jointly train the analog beamformers together with the trainable parameters of the RLS and SSCA induced deep-unfolding NNs based on the CSI statistics offline. During data transmission, we estimate the low-dimensional equivalent CSI by the RLS induced deep-unfolding NN and update the digital beamformers. In addition, we propose a mixed-timescale deep-unfolding NN where the analog beamformers are optimized online, and extend the framework to frequency-division duplex (FDD) systems where channel feedback is considered. Simulation results show that the proposed algorithm can significantly outperform conventional algorithms with reduced computational complexity and signaling overhead.

show abstract

Learning to Continuously Optimize Wireless Resource in Episodically Dynamic Environment

Cited by 18 publications

References 25 publications

Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications

Edge Artificial Intelligence for 6G: Vision, Enabling Technologies, and Applications

Learning to Continuously Optimize Wireless Resource In Episodically Dynamic Environment

Mixed-Timescale Deep-Unfolding for Joint Channel Estimation and Hybrid Beamforming

Contact Info

Product

Resources

About