Trajectory and Resource Optimization in OFDM based UAV-Powered IoT Network

Abstract : The Internet of Things (IoT) is playing an increasingly vital role in multiple industries and our everyday life. A pressing practical problem of IoT devices (IoT-Ds) is their explosive growth of connectivity which leads to large energy consumption. One of the most promising solutions to achieve a sustainable green IoT network is unmanned aerial vehicle (UAV) enabled wireless power transfer (WPT) due to its flexibility, mobility and cost advantage. In this paper, we propose an UAV-powered IoT network based on Orthogonal Frequency Division Multiplexing (OFDM). In the proposed network, two ground nodes (GNs) are powered by two UAVs through down link WPT. In the uplink, the data collected by GNs are transmitted to the corresponding UAVs with the harvested energy by utilizing orthogonal subcarriers, which can effectively avoid the interference. UAVs’ trajectories and resource allocation are optimized to maximize the sum average transmission rate of two GNs while ensuring the minimum average transmission rate of each GN. In this paper, we utilize successive convex programming (SCP) technique to solve the proposed optimization problem. Simulation results show that our proposed scheme achieves larger sum average transmission rate than the benchmark schemes.
 EXISTING SYSTEM :
 ? Our main initiatives are applying a multi-agent-based DRL model, round robin with K-means for user request queue, and clustering tasks. ? However, the existing works do not consider the use of the actual dataset and focus only on the request queue of the user service. ? The existing Q-learning method works for a limited environment, action, and decision or reward. ? If the existing RM process is not finished, add the existing request to the end of the queue. ? The unmanned aerial vehicles (UAVs) are used in largescale applications such as security inspection, aerial patrol, and traffic assessment.
 DISADVANTAGE :
 ? In, an optimization problem is formulated and solved to minimize the total hovering and traveling time of data aggregation and field estimation missions. ? To reduce the complexity of the optimization problem, some works model the UAV working process as sub-optimal problems. ? The algorithm decomposition breaks the optimization into three subproblems addressed by a distributed matching-based association, a modified version of the K-means algorithm, and a game-theoretic algorithm with a local utility function. ? The problem of docking/charging station (DS/CS) placement is investigated in, and then a UAV scheduling program is formulated based on the optimized locations of CSs.
 PROPOSED SYSTEM :
 • The Tensor Flow (python) programming tool is used to test the overall capability of the proposed method. • The proposed DRL learning architecture can learn user data from the grid points, clusters, and UAV altitudes. • The proposed learning architecture can automatically learn the characteristics of the environment based on the learning input sequences with different time scales. • The DRL techniques with neuron activation mechanisms are used to compare and evaluate the impact of neuron activation on the convergence of the proposed system. • Our proposed system has the benefit of extracting the most representative features from datasets better than conventional approaches.
 ADVANTAGE :
 ? The intelligent algorithms should thereby fully consider the trade-off between the communication performance, the total energy consumption, and the battery outage probability. ? The influence of variable is studied through the performance evaluation of the cumulative reward, the energy outage ratio, and the trajectory of the UAV. ? The off-policy scheme exhibits better performance by virtue of the access to causal knowledge. ? The performance reveals that higher altitude results in a lower data rate but a higher level of harvested energy. ? Pursuing high throughput while taking energy efficiency, channel condition, and quality of service (QoS) into consideration is another significant challenge, especially for IoT terminals working in the discontinuous reception (DRX) mode.

We have more than 145000 Documents , PPT and Research Papers

Have a question ?

Mail us : info@nibode.com