Energy Conservation for Internet of Things Tracking Applications Using Deep Reinforcement Learning

Abstract

The Internet of Things (IoT)-based target tracking system is required for applications such as smart farm, smart factory, and smart city where many sensor devices are jointly connected to collect the moving target positions. Each sensor device continuously runs on battery-operated power, consuming energy while perceiving target information in a particular environment. To reduce sensor device energy consumption in real-time IoT tracking applications, many traditional methods such as clustering, information-driven, and other approaches have previously been utilized to select the best sensor. However, applying machine learning methods, particularly deep reinforcement learning (Deep RL), to address the problem of sensor selection in tracking applications is quite demanding because of the limited sensor node battery lifetime. In this study, we proposed a long short-term memory deep Q-network (DQN)-based Deep RL target tracking model to overcome the problem of energy consumption in IoT target applications. The proposed method is utilized to select the energy-efficient best sensor while tracking the target. The best sensor is defined by the minimum distance function (i.e., derived as the state), which leads to lower energy consumption. The simulation results show favorable features in terms of the best sensor selection and energy consumption.

Augmentation of Fingerprints for Indoor BLE Localization Using Conditional GANs

“…3. The LSTM unit is essential for maintaining longterm dependencies, thereby improving overall outcomes [51]. Both the discriminator and the generator employ the rectified linear unit (ReLU) activation function for all layers, except the last one, to disregard the negative weighted values.…”

Powering UAV with Deep Q-Network for Air Quality Tracking

“…In the proposed DUPT, we used a binary reward strategy [22] to evaluate the performance of the DQN-based UAV agent. The main reason for using binary reward is that it is simple to estimate without any computational complexity.…”

Energy saving on IoT using LoRa: a systematic literature review

“…But the easiest scheme to do is harvesting like Solar because energy sources can be taken from anywhere and the most difficult is to save energy using transfer. Review Network Energy conservation Optimization techniques [43] Sensor Energy conservation Best sensor selection [44] Ambient electric field Energy harvesting Self-configuring [45] Solar Energy harvesting WSN lifetime [46] Solar Energy harvesting Utilize MPPT [10] Solar Energy harvesting Charging solar and wireless [11] Energy-aware Energy harvesting Help Lorawan transmit data [47] Wind Energy harvesting Changing wind direction [48] Thermal Energy harvesting Enhance efficiency [50] Power loss shifted Energy transfer Design inductive Energy Transfer [49] Data transmission Energy transfer Transmission contactless [51] Time scheduling and transmission Energy harvesting Effectiveness [52] Electrical devices Energy harvesting Maximizing MPPT…”