報告時間：2021年7月1日周四14：30-17:00
報告地點(diǎn)：8A207
報告題目一：Model-based Deep Off-Grid Channel Estimation for Millimeter Wave Cellular Systems（劉開暉博士）
報告人簡介：劉開暉，通信工程系博士，主要研究方向數(shù)學(xué)數(shù)據(jù)科學(xué)，特別是凸優(yōu)化和非凸優(yōu)化、 統(tǒng)計學(xué)習(xí)、 信號處理以及在無線通信和計算成像中的應(yīng)用。
報告內(nèi)容簡介：In this talk, a model-based deep off-grid channel estimation algorithm is proposed in mmWave cellular systems, in which both the base station (BS) and mobile station (MS) gain directional beamforming by employing large antenna arrays. We consider the off-grid (OG) mmWave channel estimation and propose a deep network architecture for solving this problem, which is different from most existing work concerning the compressed sensing (CS)-based channel estimation. First, the off-grid channel model is used to relieve the basis mismatch issue by exploiting first-order Taylor-series approximation of the array manifold taken on a fixed grid of both BS and MS \deleted {taken on a fixed grid}. Second, a new formulation of this off-grid channel estimation problem is solved by using a low computational complexity alternating direction method of multipliers (ADMM)-based algorithm, dubbed ADMM-OG algorithm. Third, the idea of algorithm unrolling guides us to design a deep network architecture ADMM-OGChannelNet corresponding to the ADMM-OG algorithm for the mmWave channel estimation \deleted{problem}. Based on the interpretability of this deep network architecture, the optimal parameters of this network can be learned without tuning them in a hand-crafted way. The Cram\'{e}r-Rao bound (CRB) of the off-grid channel model is derived for performance comparison as well. Finally, from the simulation results, we can verify that the ADMM-OGChannelNet has better estimation accuracy with relatively low computational complexity compared with the state-of-the-art algorithms.
報告題目二：基于組合拍賣的Cybertwin-6G網(wǎng)絡(luò)分布式資源交易機(jī)制設(shè)計（梁輝副教授）
報告人簡介：梁輝，通信工程系副教授，主要從事通信系統(tǒng)分布式資源管理，利用優(yōu)化理論、經(jīng)濟(jì)學(xué)博弈理論及機(jī)制設(shè)計理論，人工智能等多種理論方法，構(gòu)建基于未來網(wǎng)絡(luò)多智能體的資源自主交易平臺，顯著提升網(wǎng)絡(luò)資源利用率。
報告內(nèi)容簡介：針對未來6G網(wǎng)絡(luò)用戶個性化需求，不完全信息環(huán)境下分布式多維資源聯(lián)合分配問題，提出了一種基于漸進(jìn)自適應(yīng)用戶選擇環(huán)境的分布式組合拍賣方法解決網(wǎng)絡(luò)孿生多方多維資源分配問題，顯著提升以用戶個性化需求為核心的通信、計算、存儲等各類網(wǎng)絡(luò)資源聯(lián)合分配效率。
（初審：李艷霞；復(fù)審：任斌；終審：胡耀華）
