Task Oriented Channel State Information Quantization
This work addresses the challenge of efficient CSI feedback in wireless systems, offering a novel method that could reduce overhead and improve performance, though it appears incremental as it builds on existing quantization concepts with a task-specific twist.
The paper tackles the problem of quantizing channel state information (CSI) for wireless communication by proposing a task-oriented approach that tailors the feedback to the transmitter's decision task, such as power allocation. For an energy-efficient power control problem, they derive an optimal quantizer analytically and use neural networks for general utility functions, achieving significant compression rate improvements in simulations.
In this paper, we propose a new perspective for quantizing a signal and more specifically the channel state information (CSI). The proposed point of view is fully relevant for a receiver which has to send a quantized version of the channel state to the transmitter. Roughly, the key idea is that the receiver sends the right amount of information to the transmitter so that the latter be able to take its (resource allocation) decision. More formally, the decision task of the transmitter is to maximize an utility function u(x;g) with respect to x (e.g., a power allocation vector) given the knowledge of a quantized version of the function parameters g. We exhibit a special case of an energy-efficient power control (PC) problem for which the optimal task oriented CSI quantizer (TOCQ) can be found analytically. For more general utility functions, we propose to use neural networks (NN) based learning. Simulations show that the compression rate obtained by adapting the feedback information rate to the function to be optimized may be significantly increased.