Zhichao Gao

Zhichao Gao

Auto-generated profile, based on publicly available information

Zhichao Gao

School of Information Science and Engineering, Shandong University, Qingdao, China

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
11 April 2024 in IEEE Communications Letters
Verified
Journal Article
Closed access
ZGZhichao Gao
Zhichao Gao
QZQian Zhang
Qian Zhang
JLJu Liu
Ju Liu
ZDZhengfeng Du
Zhengfeng Du
YLYunxiao Li
Yunxiao Li
Cell-free massive multiple-input multiple-output (MIMO) network includes numerous geographically distributed access points (APs) serving users through coherent transmission and reception. To achieve scalability, each user should be assigned a personalized cluster of APs. In this letter, we propose a deep reinforcement learning (DRL)-based approach to determine the cluster of APs for each user while satisfying constraints on minimum rates for all users, considering practical concerns such as pilot contamination and statistical channel state information (CSI). Simulation results demonstrate that the proposed DRL-based AP selection scheme outperforms other conventional schemes.

25 December 2025 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
ZGZhichao Gao
Zhichao Gao
RZRuikang Zhong
Ruikang Zhong
XMXidong Mu
Xidong Mu
ZDZhengfeng Du
Zhengfeng Du
JLJu Liu
Ju Liu
YLYuanwei Liu
Yuanwei Liu
Multiple simultaneously transmitting and reflecting reconfigurable intelligent surfaces (STAR-RISs)-aided cell-free massive multiple-input–multiple-output (CF mMIMO) network is investigated. A long-term sum-rate maximization problem is formulated to jointly optimize the active beamforming at each access point (AP) and the passive beamforming at each STAR-RIS while satisfying the quality-of-service (QoS) requirements. To address this nonconvex problem with challenges caused by user mobility and high-dimensional optimization variables, two deep reinforcement learning (DRL)-based beamforming algorithms are proposed. First, a soft actor–critic (SAC)-based centralized joint beamforming algorithm is proposed, which adds maximum entropy term to the objective function and provides an exceptional exploration–exploitation tradeoff. However, since the centralized scheme might suffer from high communication loads and latency, we generalize the proposed approach into a distributed control. A multi-agent SAC (MASAC)-based distributed beamforming algorithm is further proposed, which employs the centralized training and decentralized execution (CTDE) framework, where each AP plays the role of an agent and makes decisions based on local observations. Simulation results demonstrate that: 1) the multiple STAR-RISs can effectively improve the performance of the CF mMIMO networks compared with other baseline schemes; 2) Both SAC-based and MASAC-based beamforming algorithms can maximize the sum-rate and guarantee the QoS of users in the long term; and 3) the MASAC-based beamforming algorithm performs better and converges faster than the SAC-based beamforming algorithm, as it reduces the overall complexity and alleviates pressure on the fronthaul link transmission by making decentralized decisions.

7 July 2023
Verified
Conference Paper
Closed access
Xinghua LiuXinghua Liu
Xinghua Liu
TMTianyu Ma
Tianyu Ma
Jiaqiang TianJiaqiang Tian
Jiaqiang Tian
ZGZhichao Gao
Zhichao Gao
GCGuoyi Chang
Guoyi Chang
RZRui Zhang
Rui Zhang
Inconsistency of battery has an impact on service life and safety of the system. Many switched capacitive equalization topologies have been proposed to cope with this issue. Most switched capacitive equalization topologies are improved based on traditional capacitive equalization topologies and do not pay attention to the impact of different state of charge (SOC) distributions on the equalization performance. In order to solve this problem, this paper designs three evaluation criteria (the degree of voltage equalization, the degree of SOC equalization, and energy loss) and compares them with the equalization performance of Conventional Switched-capacitor Cell Equalizer, Series-parallel SC Cell Equalizer and Optimized SC Cell Equalizer under four cases of different SOC distribution. The experimental results show that the impact of different SOC distributions on the SPSCE is minimal in three topologies. This provides experimental basis for the capacitive switching topologies to solve the SOC distribution inconsistency in the future.

7 July 2023
Verified
Conference Paper
Closed access
Xinghua LiuXinghua Liu
Xinghua Liu
ZGZhichao Gao
Zhichao Gao
Jiaqiang TianJiaqiang Tian
Jiaqiang Tian
TMTianyu Ma
Tianyu Ma
SIqi LiSIqi Li
SIqi Li
RZRui Zhang
Rui Zhang
The condition of lithium-ion batteries (LIBs), commonly referred to as the state of health (SOH), holds a critical role in ensuring the safety of the entire system. A precise estimation of SOH is crucial.This paper introduces the SSAGRU network, a battery SOH estimation method that utilizes the sparrow search algorithm and an improved gated recurrent unit. The current curve is used to extract three different features related to battery aging during the constant voltage stage, and their correlation with SOH is analyzed through grey correlation analysis. The proposed SSA-improved GRU model proves to be effective in achieving accurate and stable SOH estimation, outperforming two other algorithms tested.