2 results
Search Results
Now showing 1 - 2 of 2
Conference Object Citation - WoS: 4Citation - Scopus: 6A Reinforcement Learning Algorithm for Data Collection in Uav-Aided Iot Networks With Uncertain Time Windows(Ieee, 2021) Cicek, Cihan TugrulUnmanned aerial vehicles (UAVs) have been considered as an efficient solution to collect data from ground sensor nodes in Internet-of-Things (IoT) networks due to their several advantages such as flexibility, quick deployment and maneuverability. Studies on this subject have been mainly focused on problems where limited UAV battery is introduced as a tight constraint that shortens the mission time in the models, which significantly undervalues the UAV potential. Moreover, the sensors in the network are typically assumed to have deterministic working times during which the data is uploaded. In this study, we revisit the UAV trajectory planning problem with a different approach and revise the battery constraint by allowing UAVs to swap their batteries at fixed stations and continue their data collection task, hence, the planning horizon can be extended. In particular, we develop a discrete time Markov process (DTMP) in which the UAV trajectory and battery swapping times are jointly determined to minimize the total data loss in the network, where the sensors have uncertain time windows for uploading. Due to the so-called curse-of-dimensionality, we propose a reinforcement learning (RL) algorithm in which the UAV is trained as an agent to explore the network. The computational study shows that our proposed algorithm outperforms two benchmark approaches and achieves significant reduction in data loss.Article Citation - WoS: 32Citation - Scopus: 39Backhaul-Aware Optimization of Uav Base Station Location and Bandwidth Allocation for Profit Maximization(Ieee-inst Electrical Electronics Engineers inc, 2020) Cicek, Cihan Tugrul; Gultekin, Hakan; Tavli, Bulent; Yanikomeroglu, HalimUnmanned Aerial Vehicle Base Stations (UAV-BSs) are envisioned to be an integral component of the next generation Wireless Communications Networks (WCNs) with a potential to create opportunities for enhancing the capacity of the network by dynamically moving the supply towards the demand while facilitating the services that cannot be provided via other means efficiently. A significant drawback of the state-of-the-art have been designing a WCN in which the service-oriented performance measures (e.g., throughput) are optimized without considering different relevant decisions such as determining the location and allocating the resources, jointly. In this study, we address the UAV-BS location and bandwidth allocation problems together to optimize the total network profit. In particular, a Mixed-Integer Non-Linear Programming (MINLP) formulation is developed, in which the location of a single UAV-BS and bandwidth allocations to users are jointly determined. The objective is to maximize the total profit without exceeding the backhaul and access capacities. The profit gained from a specific user is assumed to be a piecewise-linear function of the provided data rate level, where higher data rate levels would yield higher profit. Due to high complexity of the MINLP, we propose an efficient heuristic algorithm with lower computational complexity. We show that, when the UAV-BS location is determined, the resource allocation problem can be reduced to a Multidimensional Binary Knapsack Problem (MBKP), which can be solved in pseudo-polynomial time. To exploit this structure, the optimal bandwidth allocations are determined by solving several MBKPs in a search algorithm. We test the performance of our algorithm with two heuristics and with the MINLP model solved by a commercial solver. Our numerical results show that the proposed algorithm outperforms the alternative solution approaches and would be a promising tool to improve the total network profit.
