Click the blue text above to follow us
📋📋📋 The content of this article is as follows: 🎁🎁🎁
Table of Contents
💥1 Overview
📚2 Results
🎉3 References
🌈4 Download Matlab Code, Data, and Article
1 Overview
Source of literature:
Abstract: Mobile Edge Computing (MEC) utilizes the computational power at the network edge to perform computation-intensive tasks in various IoT applications. At the same time, Unmanned Aerial Vehicles (UAVs) have great potential to flexibly expand coverage and enhance network performance. Therefore, utilizing UAVs to provide edge computing services for a large number of IoT devices has become a promising paradigm. This paper studies the path planning problem of UAV-assisted edge computing networks, where a UAV deploys an edge server to execute computation tasks offloaded from multiple devices. We consider the mobility of devices and adopt a Gaussian Markov random mobility model. Considering the energy consumed by the UAV during dynamic flight and task execution, we formulate a path planning problem aimed at maximizing the amount of data bits offloaded from devices while minimizing the energy consumption of the UAV. To handle the dynamic changes in complex environments, we apply a Deep Reinforcement Learning (DRL) method and develop an online path planning algorithm based on a Double Deep Q-Network (DDQN). Extensive simulation results validate the effectiveness of the proposed DRL-based path planning algorithm in terms of convergence speed and system rewards.
Mobile Edge Computing (MEC) enables the computational power at the network edge to be flexibly and rapidly deployed for innovative applications and services for a large number of IoT devices. With the deployment of MEC, devices can offload computation-intensive tasks to nearby powerful edge servers to reduce latency and save energy. Unlike fixed edge servers, recent works have focused on the research of mobile edge servers, which can provide more flexible, economical, and efficient computing services in harsh environments. Recent literature has proposed the use of UAVs to improve the connectivity of ground IoT devices. UAV-assisted wireless communication has advantages in flexible deployment, fully controllable mobility, and enhanced network performance, thus attracting increasing research interest. Therefore, UAV-assisted edge computing networks are a natural choice and a promising paradigm, where optimizing the flight path of UAVs to meet the communication and computation needs of a large number of devices becomes an important and challenging problem. Recently, some existing literature has studied the path planning problem in UAV-assisted mobile edge computing networks. In [4], the trajectory and bit allocation of UAVs were jointly optimized under constraints of delay and energy consumption. However, in these works, devices were assumed to be fixed, and mobility was not considered. In practice, devices may change dynamically over time, thus UAVs need to adjust their trajectories accordingly based on the time-varying positions of mobile devices. Meanwhile, the aforementioned works mainly focused on traditional optimization-based path planning algorithms, but as the number of UAVs and devices increases, the efficiency of this method may not be high due to the explosion of optimization variables. In [6], it has been shown that Deep Reinforcement Learning (DRL) is effective in approximating Q-values by using Deep Neural Networks (DNN) for function approximation. Since then, DRL has been applied to online resource allocation and scheduling design in wireless networks [7] – [9]. Specifically, in [7], the total system cost of execution delay and energy consumption in multi-user MEC networks was minimized by optimizing offloading decisions and computing resource allocation. An online offloading algorithm was proposed in [8] to maximize the weighted sum computation rate of wireless energy harvesting MEC networks. In [9], the computation offloading strategy of IoT devices based on deep reinforcement learning was studied. However, to our knowledge, there are currently few existing works that explore how to intelligently design the flight trajectories of UAVs in mobile edge computing networks to serve a large number of devices, especially considering the dynamic mobility of devices and the dynamic association between UAVs and devices. The use of mobile data processing technology in the communication industry is increasing. With this technology, IoT devices with large computational capabilities can launch unique applications and services in a flexible and timely manner. When edge servers are used to offload computation-intensive tasks, latency is reduced, and energy consumption is lowered. In recent years, UAVs have been utilized as multi-access edge computing servers for end users. Due to their flexible deployment, comprehensive control, and network performance, UAV-assisted wireless communication has attracted widespread research interest. UAV-assisted edge computing networks are meaningful and an interesting concept when addressing the communication and processing needs of massive devices. Aerial UAVs have long been used as network processors in mobile networks, but they are now being used as mobile servers in mobile edge computing (MEC). Due to their flexibility, portability, strong line-of-sight communication links, and low-cost, adaptable usage, they have become increasingly popular in research and commercial applications. A wide range of civil services can now be supported due to their fundamental characteristics, including transportation and industrial monitoring, agriculture, as well as forest fire and wireless services. This project studies a UAV-based mobile edge computing network, where UAVs (UAVs) provide computation to mobile terminal users. To ensure the quality of service (QoS) for each TU, the UAV dynamically selects its route based on the location of mobile TUs. Detailed articles can be found in Section 4.
2 Results
MATLAB | UAV Path Planning | Based on IRM and RRTstar for UAV Path Planning
2024-03-17
MATLAB | IoT UAV Base Station | Cuckoo Search, Elephant Herding Optimization, Grey Wolf Optimization, Monarch Butterfly Optimization, Shark Swarm Algorithm, and Particle Swarm Optimization
2024-03-13
MATLAB | UAV | Extended Kalman Filter from IMU and GPS Data | Sensor Fusion for Micro UAV State Estimation Using Invariant Extended Kalman Filter
2024-03-11
MATLAB | Koopman-MPC: Data-Driven Learning and Control for Quadrotor UAV Research
2024-03-03
MATLAB | [UAV] Research on Collision Avoidance Based on Koopman Operator Synthesized CBF
2024-03-01
MATLAB | Intelligent UAV-Assisted V2V Communication – Application in Smart Cities
2024-02-02
MATLAB | [Multirotor UAV] Modeling, Simulation, and Implementation of Asymmetric Multirotor UAV Linear Control
2024-02-01
MATLAB | UAV-Enabled Energy-Efficient Data Collection in Wireless Sensor Networks
2024-01-12
MATLAB | [Perfect Reproduction] Energy-Efficient Data Collection in Wireless Sensor Networks with UAVs
2023-12-30
MATLAB | UAV Energy-Efficient Data Collection in Wireless Sensor Networks
2023-12-14
MATLAB | Research on Trajectory Optimization of UAVs During Emergency Landing Based on Improved Simulated Annealing (HDSA)
2023-10-15
MATLAB | Multirotor UAV Combined Navigation System – Multi-Source Information Fusion Algorithm
2023-09-18
MATLAB | [UAV] Performance Analysis of Various Sensor Fusion Algorithms for Position Estimation Using Non-Moving GPS Interferers on UAV Platforms
2023-09-05
Python | Energy-Efficient Trajectory Planning for Multirotor Logistics UAVs
2023-08-20
MATLAB | [State Estimation] Estimating Terrain Height Based on Linear Kalman Filter and Particle Filter for UAVs
2023-08-06
MATLAB | [UAV] Research on UAV Path Planning Problem Based on Grey Wolf Optimization Algorithm
2023-07-25
MATLAB | UAV Energy-Efficient Data Collection in Wireless Sensor Networks
2023-07-03
MATLAB | Research on Safe and Minimum Energy Trajectory Planning for Quadrotor UAVs
2023-06-30
MATLAB | [UAV] Trajectory Planning Based on the Most Basic Free Space Path Loss Model Without Considering Small-Scale Fading (Multipath Doppler) for Fixed-Wing UAVs
2023-06-15
MATLAB | Energy-Efficient Multi-Access Edge Computing with NOMA for UAVs
2023-06-11
MATLAB | [UAV] Research on Robust Attitude Control of UAVs Based on Dynamic Inversion and Extended State Observer
2023-06-07
MATLAB | [UAV] Research on Shortest Path Based on Image Processing
2023-05-18
MATLAB | [UAV] Research on UAV Path Planning Problem Based on Grey Wolf Optimization Algorithm
2023-05-16
MATLAB | Improved Particle Filter for UAV Three-Dimensional Trajectory Prediction Method
2023-05-14
[UAV] Modeling, Simulation, and Implementation of Asymmetric Multirotor UAV Linear Control (Matlab Code Implementation)
2023-05-12
MATLAB | Research on Geometric Tracking Control of Quadrotor UAVs
2023-05-11
MATLAB | [UAV] Research on PID Controller Gain Adjustment Based on Genetic Algorithm (PID Controller Used on UAVs)
2023-05-08
[UAV] Research on Task Scheduling Path Planning Based on Ant Optimization Algorithm (Matlab Code Implementation)
2023-04-24
[UAV] Research on UAV Cruise Simulation Based on PID Control (Matlab Code Implementation)
2023-04-22
[UAV] Research on Control, Path Planning, and Trajectory Optimization of Quadrotor UAVs (Matlab Code Implementation)
2023-04-21
[UAV] Research on Adaptive Path Tracking in Time-Varying Unknown Wind Environments Based on Vector Field Method (Matlab Code Implementation)
2023-04-13
[UAV] Research on Air-to-Ground Path Loss in Dense Urban Environments (Matlab Code Implementation)
2023-04-11
[State Estimation] UAV Trajectory Prediction Based on EKF, UKF, PF, and Improved PF Filtering Algorithms (Matlab Code Implementation)
2023-04-06
[UAV] Research on Solar UAV Considering Payload Power (Matlab Code Implementation)
2023-01-14
[Path Planning] Research on Task Planning Method Based on RRT Algorithm and Improved Artificial Potential Field Method for UAVs (Python Code Implementation)
2023-01-08
[UAV Path Planning] Research on UAV Path Planning Based on IRM and RRTstar (Matlab Code Implementation)
2023-01-07
[UAV] Visualization and Animation Processing of Trajectories for Quadrotor UAVs (Matlab Code Implementation)
2022-11-30
Improved Particle Filter for UAV Three-Dimensional Trajectory Prediction Method (Based on Matlab Code Implementation)
2022-11-24
Based on Intelligent Optimization Algorithms for UAV Path Planning (Matlab Code Implementation)
2022-11-15
[UAV] Implementation of Sphere Vector Particle Swarm Optimization (SPSO) Algorithm in UAV Path Planning (Matlab Code Implementation)
2022-11-10
New Probability Density Model Based on Artificial Bee Colony Algorithm for UAV Path Planning (Matlab Code Implementation)
2022-11-04
Research on the Traveling Salesman Problem for Trucks and Two UAVs Based on Improved Genetic Algorithm (Matlab Code Implementation)
2022-10-31
Research on Path Planning and Trajectory Algorithm for UAVs Based on Particle Swarm Optimization Algorithm (Matlab Code Implementation)
2022-10-20
[UAV] Research on Trajectory Prediction Based on EKF, UKF, PF, and Improved PF Filtering Algorithms (Matlab Code Implementation)
2022-10-20
[UAV] Global Path Planning and Local Path Planning for Quadrotor UAVs (Matlab Code Implementation)
2022-10-18
[UAV] Research on Control, Path Planning, and Trajectory Optimization of Quadrotor UAVs (Matlab Code Implementation)
2022-10-18
[UAV] Visualization and Animation Processing of Trajectories for Quadrotor UAVs (Matlab Code Implementation)
2022-10-17
[UAV] Research on Motion Target of UAVs Based on Motion Encoding Particle Swarm Optimization (Matlab Code Implementation)
2022-10-16
