Indoor Emergency Path Planning Based on the Q-Learning Optimization Algorithm

The internal structure of buildings is becoming increasingly complex. Providing a scientific and reasonable evacuation route for trapped persons in a complex indoor environment is important for reducing casualties and property losses. In emergency and disaster relief environments, indoor path planning has great uncertainty and higher safety requirements. Q-learning is a value-based reinforcement learning algorithm that can complete path planning tasks through autonomous learning without establishing mathematical models and environmental maps. Therefore, we propose an indoor emergency path planning method based on the Q-learning optimization algorithm. First, a grid environment model is established. The discount rate of the exploration factor is used to optimize the Q-learning algorithm, and the exploration factor in the ε-greedy strategy is dynamically adjusted before selecting random actions to accelerate the convergence of the Q-learning algorithm in a large-scale grid environment. An indoor emergency path planning experiment based on the Q-learning optimization algorithm was carried out using simulated data and real indoor environment data. The proposed Q-learning optimization algorithm basically converges after 500 iterative learning rounds, which is nearly 2000 rounds higher than the convergence rate of the Q-learning algorithm. The SASRA algorithm has no obvious convergence trend in 5000 iterations of learning. The results show that the proposed Q-learning optimization algorithm is superior to the SARSA algorithm and the classic Q-learning algorithm in terms of solving time and convergence speed when planning the shortest path in a grid environment. The convergence speed of the proposed Q- learning optimization algorithm is approximately five times faster than that of the classic Q- learning algorithm. The proposed Q-learning optimization algorithm in the grid environment can successfully plan the shortest path to avoid obstacle areas in a short time.

Review of deaths and behavior of large birds of prey on power grid facilities in Tatarstan and Udmurtia (Russia), problems of modernization of 6–10 kV overhead power lines

The report analyzes the deaths of large birds of prey on power grid facilities of Tatarstan previously published in the literature since 2012 and additional ones, identified since 2019, including in the neighboring region – Udmurt Republic. Analysis of the data shows that immature Imperial Eagles (Aquila heliaca) up to 3 years old (n=11) died on the 6–10 kV power lines dangerous for birds. The percentage of fledglings that died near breeding territories after leaving their nests was 81.8% (n=9); one bird died in its second year of life and one bird died in its third year. The death of fledglings was identified in 8 breeding areas (in one of them twice), which is 3.9% of all known breeding areas of the Imperial Eagle in Tatarstan by the end of 2021 (n=205) and about 7.2% of 111 breeding areas in 16 administrative districts of southeastern Tatarstan where oil production is taking place. Two out of six fledglings, for which a time interval of death was established, died in the second half of August, and 2 eagles also died in the first and second halves of September. Distances from precisely known nests to locations where the fledglings died ranged from 0.26 to 11.7 km, 2.56 km on average (n=7). In 57.1% of cases deaths occurred at distances less than 1 km (from 260 to 600 m), and in 28.6% of cases at distances from 2 to 3 km. Observations of the behavior of imperial eagles in breeding grounds show a certain selectivity, namely avoidance of the most dangerous power lines. Adaptation of imperial eagles to the electric grid environment continues – 3 new breeding territories on the electric poles of high-voltage power lines were found. Two cases of death of immature White-Tailed Eagles (Haliaeetus albicilla) were identified on 6–10 kV power lines dangerous for birds deep in the forestland on narrow forest cleared strips in Tatarstan and Udmurtia, as well as the Steppe Eagle (Aquila nipalensis) in Udmurtia. Illegal exploitation and even construction of new 6–10 kV power lines dangerous for birds continues. Despite the measures taken to protect birds from death in the electric grid environment, the rate and quality of these measures are such that in the near future power lines will have a negative impact on eagles in the native area as they do now.

The development of the system for arc nordugrid based grid-computing organization using virtual environments of the docker platform

The study of modern frameworks and means of using virtualization in a grid environment confirmed the relevance of the task of automated configuration of the environment for performing tasks in a grid environment. Setting up a task execution environment using virtualization requires the implementation of appropriate algorithms for scheduling tasks and distributed storage of images of virtual environments in a grid environment. Existing cloud infrastructure solutions to optimize the process of deploying virtual machines on computing resources do not have integration with the Arc Nordugrid middleware, which is widely used in grid infrastructures. An urgent task is to develop tools for scheduling tasks and placing images of virtual machines on the resources of the grid environment, taking into account the use of virtualization tools. The results of the implementation of services of the framework are presented that allow to design and perform computational tasks in a grid environment based on ARC Nordugrid using the virtual environment of the Docker platform. The presented results of the implementation of services for scheduling tasks in a grid environment using a virtual computing environment are based on the use of a scheduling algorithm based on the dynamic programming method. Evaluations of the effectiveness of the solutions developed on the basis of a complex of simulation models showed that the use of the proposed algorithm for scheduling and replicating virtual images in a grid environment can reduce the execution time of a computational task by 88 %. Such estimates need further refinement; it is predicted that planning efficiency will increase over time with an increase in the number of running tasks due to the redistribution of the storage of virtual images

Voltage-Based Load Recognition in Low Voltage Distribution Grids with Deep Learning

Due to the increasing penetration of renewable energies in lower voltage level, there is a need to develop new control strategies to stabilize the grid voltage. For this, an approach using deep learning to recognize electric loads in voltage profiles is presented. This is based on the idea to classify loads in the local grid environment of an inverter’s grid connection point to provide information for adaptive control strategies. The proposed concept uses power profiles to systematically generate training data. During hyper-parameter optimizations, multi-layer perceptron (MLP) and convolutional neural networks (CNN) are trained, validated, and evaluated to determine the best task configurations. The approach is demonstrated on the example recognition of two electric vehicles. Finally, the influence of the distance in a test grid from the transformer and the active load to the measurement point, respectively, onto the recognition accuracy is investigated. A larger distance between the inverter and the transformer improved the recognition, while a larger distance between the inverter and active loads decreased the accuracy. The developed concept shows promising results in the simulation environment for adaptive voltage control.

Control Strategy Research of Based on Resonance Feedforward and Current Estimate of the Photovoltaic Grid Inverter

Due to poor quality of grid-connected current and large impedance value of grid are caused in weak grid environment. Therefore, a control strategy combining multiple resonant feedforward and current estimation method is adopted in this paper. Firstly, in order to make the positive feedback channel have the feedback effect only at the main background harmonics, the low-order harmonics of the grid are extracted by using the method of multi-resonance feedforward control. At the same time, under the premise that the suppression effect of LCL natural resonant frequency remains unchanged, the current estimation method is added into the control strategy, so as to reduce the system cost. Finally, the simulation results show that thus verifying the correctness and effectiveness of the control strategy.

A Scenario-Based Approach To Predict Energy Demand And Carbon Emission of Electric Vehicles On The Electric Grid

UK plans to ban the sale of new diesel and petrol cars by 2030 to be replaced by electric vehicles (EVs). However, motoring experts warn that this demand for electricity will increase by 50 % which will place unprecedented strain on the UK’s National Grid. The question is, will the UK’s electric grid infrastructure ready for this change? This comparative study investigates into the effect of UK green vehicles have on the electricity grid and will present a new insight into improving their environmental impact to the electric grid. This work is carried out with relevant data from 2014 to 2030 and addresses the carbon dioxide emissions produced on the natural environment and how EVs can help to reduce such pollution. This investigation will assess the effects on the electricity grid with or without EVs from an environmental, economic and social viewpoint. Recommendations from this work will help the industry to make key decisions of how to cope with demand and requirements to make a smart grid environment work.