In this work, we propose an approach for the autonomous navigation of mobile robots using fusion the of sensor data by a Double Deep Q-Network with collision avoidance by detecting moving people via computer vision techniques. We evaluate two data fusion methods for the proposed autonomous navigation approach: Interactive and Late Fusion strategy. Both are used to integrate mobile robot sensors through the following sensors: GPS, IMU, and an RGB-D camera. The proposed collision avoidance module is implemented along with the sensor fusion architecture in order to prevent the autonomous mobile robot from colliding with moving people. The simulation results indicate a significant impact on the success of completing the proposed mission by the mobile robot with the fusion of sensors, indicating a performance increase (success rate) of ≈27% in relation to navigation without sensor fusion. With the addition of moving people in the environment, deploying the people detection and collision avoidance security module has improved about the success rate by 14% when compared to that of the autonomous navigation approach without the security module.

In this paper, we present an approach for resource scheduling in wireless networks based on the Network Slicing (NS) paradigm using Double Deep Q-Network (DDQN) Reinforcement Learning (RL) algorithm. More specifically, we propose a joint power and Scheduling Block (SB) allocation algorithm for networks with NS. The reinforcement learning algorithm applied to the resource allocation problem is formulated using state transitions regarding the system dynamics. We also present an algorithm, namely Network Slicing based on Reinforcement Learning (NSRL) that combines the proposed reinforcement learning based resource allocation with an approach based on reservation and sharing of resources among the slices where each RL agent acts in one slice. Simulations are carried out considering User Equipments (UEs) within a small cell coverage area - (Small Cells) with different Modulation and Coding Schemes (MCS) standardized by the 3rd Generation Partnership Project (3GPP) based on a simplified NS scenario with fifth generation wireless network (5G) characteristics. In the simulations, two slices are considered for the UEs: one considering Ultra-reliable and Low Latency Communications (URLLC) and other related to enhanced Mobile Broadband (eMBB) services. Simulation results show that the NSRL algorithm efficiently allocates power and SBs, outperforming other algorithms in the literature.

The problemof voltage control (VC) by means of inverter reactive support in distribution grids with photovoltaic (PV) generation is addressed. A novel decentralized approach for VC is proposed, which consists in heuristic specification of a distributed reactive support cooperative partially observable Markov decision process (DRS-C-POMDP) whose agents control groups of PV nodes clustered according to voltage correlation. The proposed method employs offline policy optimization, which yields closed-form reactive power setpoint control laws. Hence, the online processing time required by most VC methods is avoided and controller implementation is simplified. The method is validated via simulation on a 123-bus feeder, in which it is compared to other decentralized heuristic methods from the literature. The results indicate that, for identical local inverter controls, the proposed method yields superior performance.

A novel explicit model for the current-voltage (I-V) characteristic of solar cells is proposed, consisting of two quadratic equation segments associated with inverse orthogonal coordinate systems and joined at the maximum powerpoint. Salient features of the proposed model are its high accuracy and simple parameter computation solely from the cell notable points. Comparison carried out against the most relevant explicit I-V models suggests the proposed method has greater flexibility in fitting a wide range of I-V characteristic fill factors with high accuracy. It is also shown that the model enables explicit and precise computation of the solar cell operating point in terms of load and ambient conditions, which is a major advantage when carrying out simulations.

This paper deals with the reduction in electrical losses and the minimization of voltage deviation in electrical power grids. To this end, a novel heuristic-based approach is proposed for controlling reactive power injections along an electrical grid with distributed generation using distributed photovoltaic (PV) generation. The proposed approach consists of applying a heuristic, namely a genetic or firefly algorithm, to solve the loss and voltage deviation optimization problem by controlling PV reactive power injections. The proposed method was tested on a radial 100-bus network with an intense penetration of PV generation. The obtained results indicate that the proposed method consistently yields superior grid performance when compared to algorithms previously proposed in the literature. In fact, it led to a reduction in the active power supplied by the reference bus to the grid, thereby alleviating the burden imposed on the most upstream parts of the distribution network. As a consequence, the proposed method contributes to a power-efficient network, enhancing its loss performance and voltage stability.