The energy consumption of the routing protocol can affect the lifetime of a wireless sensor network (WSN) because tiny sensor nodes are usually difficult to recharge after they are deployed. Generally, to save energy, data aggregation is used to minimize and/or eliminate data redundancy at each node and reduce the amount of the overall data transmitted in a WSN. Furthermore, energy-efficient routing is widely used to determine the optimal path from the source to the destination, while avoiding the energy-short nodes, to save energy for relaying the sensed data. In most conventional approaches, data aggregation and routing path selection are considered separately. In this study, we consider the degrees of the possible data aggregation of neighbor nodes when a node needs to determine the routing path. We propose a novel Q-learning-based data-aggregation-aware energy-efficient routing algorithm. The proposed algorithm uses reinforcement learning to maximize the rewards, defined in terms of the efficiency of the sensor-type-dependent data aggregation, communication energy and node residual energy, at each sensor node to obtain an optimal path. We used sensor-type-dependent aggregation rewards. Finally, we performed simulations to evaluate the performance of the proposed routing method and compared it with that of the conventional energy-aware routing algorithms. Our results indicate that the proposed protocol can successfully reduce the amount of data and extend the lifetime of the WSN.

The use of unmanned aerial vehicles (UAVs) has been considered to be an efficient platform for monitoring critical infrastructures spanning over geographical areas. UAVs have also demonstrated exceptional feasibility when collecting data due to the wide wireless sensor networks in which they operate. Based on environmental information such as prohibited airspace, geo-locational conditions, flight risk, and sensor deployment statistics, we developed an optimal flight path planning mechanism by using multiobjective bio-inspired algorithms. In this paper, we first acquire data sensing points from the entire sensor field, in which UAV communicates with sensors to obtain sensor data, then we determine the best flight path between neighboring acquisition points. Using the proposed joint genetic algorithm and ant colony optimization from possible UAV flight paths, an optimal one is selected in accordance with sensing, energy, time, and risk utilities. The simulation results show that our method can obtain dynamic environmental adaptivity and high utility in various practical situations.

Ever-increasing demands for portable and flexible communications have led to rapid growth in networking between unmanned aerial vehicles often referred to as flying ad-hoc networks (FANETs). Existing mobile ad hoc routing protocols are not suitable for FANETs due to high-speed mobility, environmental conditions, and terrain structures. In order to overcome such obstacles, we propose a combined omnidirectional and directional transmission scheme, together with dynamic angle adjustment. Our proposed scheme features hybrid use of unicasting and geocasting routing using location and trajectory information. The prediction of intermediate node location using 3-D estimation and directional transmission toward the predicted location, enabling a longer transmission range, allows keeping track of a changing topology, which ensures the robustness of our protocol. In addition, the reduction in path re-establishment and service disruption time to increase the path lifetime and successful packet transmissions ensures the reliability of our proposed strategy. Simulation results verify that our proposed scheme could significantly increase the performance of flying ad hoc networks.

In this paper, we propose a dynamic unmanned aerial vehicle (UAV) positioning method to maximize the value of the sensor data information acquired from multiple UAVs in wireless sensor networks. In operations of UAVs to monitor environmental disasters or perform military missions, the value of the acquired sensing information depends on the sensor types and the elapsed time after the previous sensing time. To support real-time sensor data monitoring, the sensed data should be successfully delivered to the ground base station (or sink node) using a UAV flying ad-hoc network; herein, it is important to maintain the connectivity between the UAVs and to consider the reliability of the communication links. In this study, particle swarm optimization (PSO) is used to derive optimum UAV locations. For a specified wireless sensor network, at each time instance, new UAV locations are updated that guarantee complete connectivity of the UAVs and maximize the value of the aggregated sensor data information. In this paper, we have formulated the UAV location search model as a constrained optimization problem with multi-objective utility functions using PSO-based bio-inspired algorithm. The simulation results demonstrate that by maximizing the intended multi-objective utility function, the proposed method can dynamically derive the optimal locations of multiple UAVs and achieve better sensing information acquisition compared to other methods.

In order to evacuate people safely and quickly in indoor disaster environments, it is necessary to estimate the current location of the individuals, detect disaster situations, predict disaster propagation, derive optimal individual escape paths, and implement a user-friendly and intuitive guidance system. In this study, we propose a machine-learning-based indoor augmented reality (AR) navigation and emergency evacuation system that can guide an optimal escape path for individual users. To detect emergency events and deliver sensing data, an Internet of Things (IoT)-enabled ad hoc network is considered. To deliver the sensing data safely and reliably to the server, we present a hybrid reinforcement-learning-based routing algorithm that combines direct and indirect $Q$ -learning methods. Prediction of disaster propagation at multiple time scales is important to prevent dangerous situations. We propose a simple disaster area prediction method that ensembles elementary component gradient boosting machine models. User location is estimated by a deep neural network using the received signal strength from beacon nodes. To derive the optimum evacuation path for each individual, we propose a novel model-based $Q$ -learning method, in which we consider the building structural model and disaster context information. The performance of the proposed system is experimentally evaluated for various disaster scenarios.