Robust Decentralized Joint Precoding using Team Deep Neural Network

By Paul de Kerret, David Gesbert. 2018

25 citations recorded by the source corpus.

Using Deep Neural Networks (DNNs) to tackle socalled Team Decision problems where the nodes aim at maximizing an expected common utility on the basis of different individual observations without any additional communications was recently introduced in a previous work and illustrated in the simple case of decentralized scheduling. In this work11D. Gesbert and P. de Kerret are supported by the European Research Council under the European Union's Horizon 2020 research and innovation program (Agreement no. 670896)., we apply this idea to design a decentralized robust precoding scheme in a Network MIMO configuration, which appears as a more challenging setting due to the continuous decision space and the required fine granularity of the precoding, in particular at high SNR. While the application remains fundamentally decentralized due to the decentralized nature of the channel state information (CSI), the training is done jointly. This is possible thanks to the common knowledge of the statistics (or equivalently the training data set) at all cooperating TXs. The joint training is done directly with respect to the desired figure-of-merit such that there is no need to generate labels using another method, and the precoding scheme obtained from the training does not only replicate a known scheme but is able to outperform state-of-the-art methods, as illustrated by simulations.

Subfields: Electrical and Electronic Engineering

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Electrical and Electronic Engineering

Citations in the corpus

Deep Learning for Distributed Optimization: Applications to Wireless Resource Management (2019, methodology): “individual transmitters equipped with their own DNN for the distributed computation in [9], [10], [21], [22].”
A Deep Learning Framework for Optimization of MISO Downlink Beamforming (2019, methodology): “However, with the exception of [39–42], there are no works focusing on beamforming design in multi-antenna communications based on DL.”
Machine Learning in the Air (2019, background): “2) Centralized Training of Decentralized Strategies: We will now discuss how the approach proposed in [62], [63] allows to leverage recent progresses in ML, and in particular deep learning, to solve the two main challenges, which are (i) achieving a strong form of cooperation and (ii) dealing with…”
Wireless Networks Design in the Era of Deep Learning: Model-Based, AI-Based, or Both? (2019, methodology): “2) Management of the Physical Layer: A second emerging application area is the use of deep learning to perform radio resource allocation at the physical layer, with minimum complexity and/or side-information requirements [156], [188]–[198].”