Optimal deployment of the spoke of a largesized transformable reflector according to the hierarchy of criteria

The article discusses the process of controlling the angular motion of the spoke of a large-sized space-based reflector, taking into account bending vibrations. Currently, large antennas are actively used for receiving and transmitting data. When launching large structures into space, the problem arises of reliably deployment the spokes, since they are packed in a small volume to be able to be installed in a launch vehicle. Due to the possibility of various abnormal situations, such as jamming of elements, engagement of the net, it is necessary to re-deployment the antenna. Therefore, it is important to develop control algorithms that can reliably solve the problems of direct and reverse motion. In the process of deployment and bringing together the elements of the reflector, various deformations appear in the structure. When the antenna spokes are brought together, lateral oscillations make the largest contribution to the oscillatory of the transient process. Currently, elastically deformed elements are used to deployment large-sized reflectors, and a control program is also used. This prevents the control from being adjusted when the deployment conditions change. The paper investigates the possibility of minimizing the vibrations of a structure during its deployment by using optimal control algorithms in real time. The forward and reverse motion of the antenna elements is performed by means of a two-criteria hierarchy optimization. The results of numerical simulation of the optimal rotation of the reflector spoke are presented. The proposed algorithm allows you to choose the optimal control in emergency situations for various types of large reflectors.

Designing Automated Deployment Strategies of Face Recognition Solutions in Heterogeneous IoT Platforms

In this paper, we tackle the problem of deploying face recognition (FR) solutions in heterogeneous Internet of Things (IoT) platforms. The main challenges are the optimal deployment of deep neural networks (DNNs) in the high variety of IoT devices (e.g., robots, tablets, smartphones, etc.), the secure management of biometric data while respecting the users’ privacy, and the design of appropriate user interaction with facial verification mechanisms for all kinds of users. We analyze different approaches to solving all these challenges and propose a knowledge-driven methodology for the automated deployment of DNN-based FR solutions in IoT devices, with the secure management of biometric data, and real-time feedback for improved interaction. We provide some practical examples and experimental results with state-of-the-art DNNs for FR in Intel’s and NVIDIA’s hardware platforms as IoT devices.

Deep Reinforcement Learning for UAV Trajectory Design Considering Mobile Ground Users

A network composed of unmanned aerial vehicles (UAVs), serving as base stations (UAV-BS network), is emerging as a promising component in next-generation communication systems. In the UAV-BS network, the optimal positioning of a UAV-BS is an essential requirement to establish line-of-sight (LoS) links for ground users. A novel deep Q-network (DQN)-based learning model enabling the optimal deployment of a UAV-BS is proposed. Moreover, without re-learning of the model and the acquisition of the path information of ground users, the proposed model presents the optimal UAV-BS trajectory while ground users move. Specifically, the proposed model optimizes the trajectory of a UAV-BS by maximizing the mean opinion score (MOS) for ground users who move to various paths. Furthermore, the proposed model is highly practical because, instead of the locations of individual mobile users, an average channel power gain is used as an input parameter. The accuracy of the proposed model is validated by comparing the results of the model with those of a mathematical optimization solver.

Optimal Deployment of Cordon Sanitaire with Available Testing Capacity

During the COVID-19 pandemic, authorities in many places have implemented various countermeasures, including setting up a cordon sanitaire to restrict population movement. This paper proposes a bi-level programming model to deploy a limited number of parallel checkpoints at each entry link around the cordon sanitaire to achieve a minimum total waiting time for all travelers. At the lower level, it is a transportation network equilibrium with queuing for a fixed travel demand and given road network. The feedback process between trip distribution and trip assignment results in the predicted waiting time and traffic flow for each entry link. For the lower-level model, the method of successive averages is used to achieve a network equilibrium with queuing for any given allocation decision from the upper level, and the reduced gradient algorithm is used for traffic assignment with queuing. At the upper level, it is a queuing network optimization model. The objective is the minimization of the system’s total waiting time, which can be derived from the predicted traffic flow and queuing delay time at each entry link from the lower-level model. Since it is a nonlinear integer programming problem that is hard to solve, a genetic algorithm with elite strategy is designed. An experimental study using the Nguyen-Dupuis road network shows that the proposed methods effectively find a good heuristic optimal solution. Together with the findings from two additional sensitivity tests, the proposed methods are beneficial for policymakers to determine the optimal deployment of cordon sanitaire given limited resources.