Ke Lv

Mr. Ke Lv

orcid

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
15 April 2023 in Drones
Verified
Journal Article
Open access
PDF file
Yuanyuan YaoYuanyuan Yao
Yuanyuan Yao
KLKe Lv
Ke Lv
Sai HuangSai Huang
Sai Huang
XLXuehua Li
Xuehua Li
Wei XiangWei Xiang
Wei Xiang
An air-to-ground downlink communication network consisting of a reconfigurable intelligent surface (RIS) and unmanned aerial vehicle (UAV) is proposed. In conjunction with a resource allocation strategy, the system’s energy efficiency is improved. Specifically, the UAV equipped with a RIS starts from an initial location, and an energy-efficient unmanned aerial vehicle deployment (EEUD) algorithm is deployed to jointly optimize the UAV trajectory, RIS phase shifts, and BS transmit power, so as to obtain a quasi-optimal deployment location and hence improve the energy efficiency. First, the RIS phase shifts are optimized by using the block coordinate descent (BCD) algorithm to deal with the nonconvex inequality constraint, and then integrated with the Dinkelbach algorithm to address the resource allocation problem of the BS transmit power. Finally, for solving the UAV trajectory optimization problem, the complex objective function is transformed into a convex function, and the optimal UAV flight trajectory is obtained. Our simulation results show that the quasi-optimal deployment location obtained by the EEUD algorithm is superior to other deployment strategies in energy efficiency. Moreover, the instantaneous energy efficiency of the UAVs along the trajectory of searching the deployment location is better than other comparison trajectories. Furthermore, the RIS-assisted multi-user air-to-ground communication network can offer up to 145% improvement in energy efficiency over the traditional amplify-and-forward (AF) relay.

27 May 2024 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
Yuanyuan YaoYuanyuan Yao
Yuanyuan Yao
KLKe Lv
Ke Lv
Sai HuangSai Huang
Sai Huang
Wei XiangWei Xiang
Wei Xiang
Research indicates that replacing relays with the reconfigurable intelligent surface (RIS) can effectively reduce energy consumption under certain conditions. Therefore, introducing RIS into unmanned aerial vehicle (UAV) assisted airto- ground communication networks can further enhance communication performance. In this paper, we propose a RISUAV- assisted communication network scenario that utilizes the zero-forcing (ZF) precoding method to eliminate multi-user interference, and then optimize the BS transmit power by using the Dinkelbach algorithm. To address the optimization problem of bandwidth allocation, RIS phase shifts, and threedimensional (3D) coordinates of the RIS-UAV, we propose two deep reinforcement learning (DRL) algorithms, which are termed D3QN-MM and D3QN-Pure, respectively. Both D3QN-MM and D3QN-Pure utilize the dueling double deep Q-network (D3QN) for optimizing bandwidth allocation and the 3D coordinates of the RIS-UAV. However, D3QN-MM employs the traditional majorizeminimization (MM) algorithm for RIS phase shifts optimization, while D3QN-Pure utilizes the D3QN. By comparing them with other algorithms, such as the DRL algorithm, the advantages of the algorithms proposed in this paper are highlighted. Furthermore, compared to the amplify-and-forward (AF) relay, the RIS can achieve a 48% energy efficiency improvement. Besides, the D3QN-Pure algorithm provided up to 14.3% energy effciency improvement compared to the D3QN-MM algorithm.

17 December 2025 in IEEE Transactions on Cognitive Communications and Networking
Verified
Journal Article
Closed access
KLKe Lv
Ke Lv
Sai HuangSai Huang
Sai Huang
Yuanyuan YaoYuanyuan Yao
Yuanyuan Yao
Weiwei JiangWeiwei Jiang
Weiwei Jiang
YHYuzhen Huang
Yuzhen Huang
ZhiYong FengZhiYong Feng
ZhiYong Feng
The artificial general intelligence (AGI) based on large language models (LLMs) and deep reinforcement learning (DRL) possesses cross-domain empowerment capabilities, offering task scheduling and resource allocation in mobile edge computing (MEC), presenting significant potential. This paper proposes an LLM-driven DRL framework named L2D2, which autonomously generates reward functions for DRL through LLMs and enables dynamic model optimization through a self-refinement loop mechanism. The reward function within the L2D2 framework can adjust the strategy based on environmental feedback, eliminating the need for manual redesign in complex low-altitude scenarios and reducing debugging costs. To validate the performance of L2D2, the framework is utilized in a multi-unmanned aerial vehicle (UAV)-assisted MEC heterogeneous network operating in the low-altitude airspace to enhance system energy efficiency. A novel dueling double deep Q-network (D3QN) is utilized as the DRL method within L2D2, named the L2D2-D3QN algorithm. To evaluate its effectiveness in enhancing system energy efficiency, a comprehensive comparison is conducted across various LLMs, including Deepseek-R1, GPT-4o, Llama-3.1-70B, Claude-3.7-Sonnet, and Qwen-2.5. The simulation results demonstrate that the L2D2-D3QN algorithm achieves up to 56% higher energy efficiency compared to DRL with human-designed reward function. Furthermore, the influence of LLM tokenization strategies on the performance of LLM-driven DRL is also explored.

27 April 2026 in IEEE Transactions on Consumer Electronics
Verified
Journal Article
Closed access
KLKe Lv
Ke Lv
Sai HuangSai Huang
Sai Huang
YHYuzhen Huang
Yuzhen Huang
YXYu Xue
Yu Xue
Weiwei JiangWeiwei Jiang
Weiwei Jiang
Yuanyuan YaoYuanyuan Yao
Yuanyuan Yao
The future sixth generation (6G) mobile network will be a highly heterogeneous system that integrates diverse technologies and communication paradigms, encompassing diverse consumer electronics (CE) devices, including human-type user devices and various internet of things (IoT) devices utilizing different protocols. In this paper, a novel cognitive unmanned aerial vehicle (UAV)-assisted mobile edge computing (MEC) heterogeneous network (HetNet) is proposed, where multiple cognitive UAVs equipped with MEC servers assist human-type users within the same signal modulation scheme, establishing one communication link, while selectively collecting data transmitted by the constrained application protocol (CoAP)-based IoT devices within different signal modulations, forming another communication link. Moreover, automatic modulation classification (AMC) technologies enable cognitive UAVs to communicate efficiently with multiple CoAP-based IoT devices. In this work, the reparameterization causal convolutional network (RepCCNet) is innovatively utilized to enable each cognitive UAV to achieve AMC for IoT devices. To fulfill the demand for high uplink data rate while minimizing overall system energy consumption, a superior multi-agent algorithm (RepCCNet-D3QN) is proposed to solve the problem of maximizing average energy efficiency, dueling double deep Q-network (D3QN) is applied to optimize user association factors and the three-dimensional (3D) trajectory of UAVs. Compared with other recent deep reinforcement learning (DRL) algorithms, the RepCCNet-D3QN algorithm can provide 45% energy efficiency improvement.

1 January 2026 in IEEE Vehicular Technology Magazine
Verified
Journal Article
Closed access
Sai HuangSai Huang
Sai Huang
Wanli NiWanli Ni
Wanli Ni
KLKe Lv
Ke Lv
PZPengcheng Zhang
Pengcheng Zhang
YZYurui Zheng
Yurui Zheng
ZhiYong FengZhiYong Feng
ZhiYong Feng