Reliability Analysis and Repair Activity for the Components of 350 kW Inverters in a Large Scale Grid-Connected Photovoltaic System

The reliability of photovoltaic (PV) generators is strongly affected by the performance of Direct Current/Alternating Current (DC/AC) converters, being the major source of PV underperformance. However, generally, their reliability is not investigated at component level: thus, the present work presents a reliability analysis and the repair activity for the components of full bridge DC/AC converters. In the first part of the paper, a reliability analysis using failure rates from literature is carried out for 132 inverters (AC rated power of 350 kW each) with global AC power of 46 MW in a large scale grid-connected PV plant. Then, in the second part of the work, results from literature are compared with data obtained by analyzing industrial maintenance reports in the years 2015–2017. In conclusion, the yearly energy losses involved in the downtime are quantified, as well as their availability.

Non-Communication Decentralized Multi-Robot Collision Avoidance in Grid Map Workspace with Double Deep Q-Network

This paper presents a novel decentralized multi-robot collision avoidance method with deep reinforcement learning, which is not only suitable for the large-scale grid map workspace multi-robot system, but also directly processes Lidar signals instead of communicating between the robots. According to the particularity of the workspace, we handcrafted a reward function, which considers both the collision avoidance among the robots and as little as possible change of direction of the robots during driving. Using Double Deep Q-Network (DDQN), the policy was trained in the simulation grid map workspace. By designing experiments, we demonstrated that the learned policy can guide the robot well to effectively travel from the initial position to the goal position in the grid map workspace and to avoid collisions with others while driving.