Joint Computation Offloading, Channel Access and Scheduling Optimization in UAV Swarms: A Game-Theoretic Learning Approach

Abstract

Coalition-based unmanned aerial vehicle (UAV) swarms have been widely used in urgent missions. To fasten the completion, mobile edge computing (MEC) has been introduced into UAV networks where coalition leaders act as servers to help members with data computing. This paper investigates a relative delay optimization in MEC-assisted UAV swarms. Considering that the scheduling methods have great impact on the delay, some theoretical analysis are made and a scheduling method based on shortest effective job first (SEJF) is proposed. Based on the coupled relationship between scheduling and resource allocation, the computation offloading and channel access problem are then jointly optimized. To solve the problem in distributed UAV networks, the optimization problem is formulated as an offloading game. It is proved that the game is an exact potential game (EPG) and it has at least one pure strategy Nash Equilibrium (PNE). To reach the PNE, a distributed offloading algorithm based on concurrent best-better response (CBBR) is designed. Finally, the simulations show that the performance of the proposed CBBR algorithm is better than traditional algorithms. Compared with other scheduling methods, the proposed scheduling method based on SEJF reduces the delay by up to 30%.

Stackelberg game‐based task offloading in mobile edge computing‐enabled hierarchical multi‐coalition unmanned aerial vehicle networks

“…(1) In Step 1, the selection of a UAV heads is implemented by contention mechanism. 47 The complexity is OðC1Þ, where C1 is a small constant 37 and is affected by the number of UAV heads. (2) In Step 2, the selected UAV head h q computes the utility of all possible positions in the strategy space and finds the optimal position deployment with computational complexity OðC2Þ, where C2 is constant affected by the number of available positions in the UAV head's strategy space and the Equation ( 14).…”

“…Zhang et al 36 minimize the response latency of UAVs in MEC‐enabled UAV swarm networks by jointly optimizing communication and computation resources. Chen et al 37 investigated the joint optimization of scheduling, channel selection, and computation offloading in MEC‐enabled multi UAV swarm and ultimately optimized the relative latency of the networks. However, it ignored UAVs' maneuverability and intra‐coalition interference.…”

“…The detailed analysis is given as follows: In Step 1, the selection of a UAV heads is implemented by contention mechanism 47 . The complexity is , where is a small constant 37 and is affected by the number of UAV heads. In Step 2, the selected UAV head computes the utility of all possible positions in the strategy space and finds the optimal position deployment with computational complexity , where is constant affected by the number of available positions in the UAV head's strategy space and the Equation (). In Step 3, an updating UAV member is randomly selected in each time slot by contention mechanism with complexity , where is a small constant affected by the number of UAV members. The complexity of updating UAV member estimate the received utility is , where is a small constant determined by the UAV member's strategy space and Equation ().…”

AI-Enabled UAV Communications: Challenges and Future Directions

“…It optimized UAV under several constraints but with ideal assumptions which are not practical. In [32], the authors suggested MEC as a UAV network where coalition leaders serve as servers to aid members with data computation. They looked into relative delay optimization in MEC-assisted UAV swarms.…”

“…Unsupervised Learning [71] V2X, 6G, IoV [101] Vehicular ad hoc network [107] UAV Trajectory [73] Video+dataset [74] Maximizing the sum mean [121] Optimal path [113] UAV+Disaster NOMA [122] Beamforming & Beamsteering CH optimization+UAV [109] Microwave Power Transfer [123] UAV+Disaster & Resource allocation "CH" Supervised Learning [14] UAV+NOMA [26] UAV Trajectory [80] IRS with MIMO CH [124] UAV Trajectory [72] UAV in 6G [70] UAV Design [28] UAV Energy constrains [32] Mobile edge computing [90] Access to the cloud computing [110] Multiple UAVs [74] Maximizing the sum mean [89] Mobile edge computingDesign UAV [124] UAV Optimize the energy efficiency [30] Mobile edge computing…”