Weiqi Liu

Dr. Weiqi Liu

Computer Science & Computer Information Systems, Auburn University at Montgomery, Montgomery, Alabama, USA
orcid

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

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

Representative Publications

View All Publications
16 January 2024 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
MHMohammad Arif Hossain
Mohammad Arif Hossain
WLWeiqi Liu
Weiqi Liu
NANirwan Ansari
Nirwan Ansari
Due to the proliferation of devices and the availability of computing servers, mobile edge computing (MEC) has gained popularity in executing various computational tasks. MEC offers computing services at the network’s edge, providing user equipment (UE) with reduced latency for their applications. However, determining a suitable offloading policy for UEs in MEC, considering wireless resource allocation and power management, is computationally demanding. Additionally, the problem is NP-hard, making it challenging to find an optimal solution within a reasonable time frame. In this work, we propose a meta-reinforcement learning (MRL) based computational task offloading and power control mechanism for UEs in a resource-constrained environment of a MEC network to tackle the NP-hardness of the problem. We first develop an optimization problem to maximize UE computation efficiency by minimizing their power consumption for local computing and uplink transmission of UEs in the MEC network. We propose to use both binary offloading (full offloading or full local computing) and partial offloading schemes in the system. Our proposed MRL algorithm can figure out a suitable offloading policy for UEs within a short time. Unlike the traditional deep-reinforcement learning algorithms, our approach can resolve the issue of obtaining proper solutions in a new environment. Extensive simulation results prove the feasibility of our proposed work.

13 July 2022 in IEEE Internet of Things Journal
Verified
Journal Article
Closed access
SZShuai Zhang
Shuai Zhang
WLWeiqi Liu
Weiqi Liu
NANirwan Ansari
Nirwan Ansari
Internet of Things (IoT) devices usually lack perpetual power supply since they are generally deployed at remote areas with limited battery capacities. Moreover, the computing power of the IoT devices is usually limited and the generated data need to be offloaded to a more powerful computing server for further processing. In this article, we study a novel unmanned aerial vehicle (UAV)-enabled IoT network, where the UAV delivers energy to the ground IoT devices by employing wireless power transfer (WPT) in the downlink and collects data in the uplink. In our work, we try to minimize the total energy consumption of the UAV by determining the trajectory and charging power of the UAV, the resource allocation, and the transmission scheme subject to task collection and resource budget requirements. To make the formulated problem more tractable, we decompose the primal problem into three subproblems (i.e., the transmission association problem, the trajectory design problem, and the resource allocation problem) and utilize the block coordinate descent (BCD) method to solve them alternately. Since the trajectory design problem is still highly nonconvex, we further transform it into a convex one by leveraging the successive convex approximation (SCA) technique. In the simulation, we provide extensive numerical results to corroborate the effectiveness of our proposed algorithm.

21 February 2024 in IEEE Transactions on Network and Service Management
Verified
Journal Article
Closed access
WLWeiqi Liu
Weiqi Liu
MHMohammad Arif Hossain
Mohammad Arif Hossain
NANirwan Ansari
Nirwan Ansari
AKAbbas Kiani
Abbas Kiani
TSTony Saboorian
Tony Saboorian
An end-to-end (E2E) network slicing (NS) scheme for heterogeneous network (HetNet) is proposed in which the number of slices and instances of various network functions (NFs) are optimized contingent on the number of users (UEs) and their quality of service (QoS) requirements. The objective of the scheme is to empower future generation networks by considering control signaling in the control plane as well as the UE traffic in the user plane of the core network (CN). We formulate a joinT UE assOciation, wiReless bandwidth allocation, sliCe formation, slice assignment, virtual network function (VNF) placement, computing resource allocation, link assignment, and link bandwidtH allocation (TORCH) problem to minimize the E2E task completion time of all UEs while considering both control signaling and UEs’ traffic. Since TORCH is a mixed-integer nonlinear problem, to tackle the problem, we decompose it into two sub-problems: the link assignment problem and the UE Association, resource allocation, Slice formation, Slice AssIgnment, and VNF pLacement (ASSAIL) problem. The ASSAIL problem comprises both the core network (CN) and radio access network (RAN), and they do not compete for resources, so we decompose it into two sub-problems: the RAN problem and the CN problem. We use Dijkstra’s algorithm and a deep Q-learning network (DQN) based reinforcement learning method to iteratively solve the two sub-problems. Simulation results have confirmed the effectiveness of our proposed scheme in tackling the TORCH problem.

2 June 2023 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
SZShuai Zhang
Shuai Zhang
WLWeiqi Liu
Weiqi Liu
NANirwan Ansari
Nirwan Ansari
In this paper, we study the completion time minimization in an unmanned aerial vehicle (UAV)-enabled Internet of Things (IoT) network, where the UAV tries to collect all the data generated by the ground IoT devices for further processing. To simplify the analysis, the continuous time horizon is discretized into several time slots. The duration of each time slot is set to be less than the pre-defined threshold such that the UAV's location can be considered as unchanged during each time slot. In our work, we aim to minimize the completion time of the UAV by optimizing the association scheme of the IoT devices, the location (i.e., the trajectory) and velocity of the UAV at each time slot. However, the formulated problem is challenging to solve by traditional optimization methods considering the unknown number of time slots (which leads to the unknown number of decision variables) and non-convex functions. We thus reformulate it as a Markov decision process (MDP) and propose a deep deterministic policy gradient (DDPG)-based method to efficiently solve it. The DDPG-based algorithm uses deep function approximators instead of finding the action that maximizes the state-action value, and is therefore well suited to solve high-dimensional, continuous control problems. Extensive numerical results are presented to validate the effectiveness of our proposed algorithm.

23 November 2021 in IEEE Transactions on Vehicular Technology
Verified
Journal Article
Closed access
SZShuai Zhang
Shuai Zhang
WLWeiqi Liu
Weiqi Liu
NANirwan Ansari
Nirwan Ansari
Unmanned aerial vehicle (UAV)-assisted heterogeneous network has drawn great research interests as it can significantly improve the capacity and coverage of cellular networks. An UAV can act as a flying base station (BS) or a relay when the regular terrestrial infrastructure is malfunctioned or overloaded. However, the deployment of UAV-mounted communication infrastructure is confined by the limited on-board energy and short battery life. To prolong the lifetime of each UAV, connecting it with a ground charging station (GCS) through a tether could be a promising and feasible solution. In this paper, we aim to maximize the sum rate of all users by jointly optimizing the user association, resource allocation and placement of the GCSs and the aerial UAVs. In addition, the constraint of each user's quality of service (QoS) requirement and total available resource are considered. To tackle this problem, we propose a cyclic iterative algorithm to efficiently obtain suboptimal solutions. Specifically, the primal problem is decomposed into three subproblems, i.e., the TUAV placement problem, the resource allocation problem and the user association problem. Then, the three sub-problems are alternately and iteratively optimized by using the outputs of the first two as the input for the third. Numerical experiments demonstrate that our proposed algorithm outperforms baseline algorithms under different setups.

7 August 2023 in IEEE Networking Letters
Verified
Journal Article
Closed access
AHAbdullah Ridwan Hossain
Abdullah Ridwan Hossain
WLWeiqi Liu
Weiqi Liu
NANirwan Ansari
Nirwan Ansari
AKAbbas Kiani
Abbas Kiani
TSTony Saboorian
Tony Saboorian
3GPP envisions exploiting AI-Native for the day-to-day operations of 6G core networks (CNs). As opposed to 5G CNs whose uses for artificial intelligence (AI) are limited and not yet standardized, 6G CNs seek a revolutionary redesign where AI will no longer simply be an overlaid service but rather the foundation upon which all network functions run, i.e., AI-Native. By leveraging knowledge of the CN control plane, we utilize an AI framework to optimize our three proposed CN configurations and minimize the CN execution time which is imperative for end-to-end routing in the user plane.