A semi-supervised learning method was designed using a graph model for proactive learning in smart grids. The method starts by labeling the unlabeled grid voltage data using information from the partially labeled grid voltage data. Then, it evaluates the score of the labeling and predicts the system stability by using correlation matrices. The method is applied for five power system test cases including the IEEE 14 bus, 30 bus, 39 bus, 57 bus, and 118 bus systems. The results confirm a high degree of correlation between the predicted results and the actual values of the terminal voltages of all the nodes in the experimental systems. The method can be used to predict the effects of disturbances in smart grids and related systems of systems.
The state-estimation and optimal control of wide-area systems are challenging where there are numerous distributed automatic voltage regulators (AVR). This project implemented a Q-learning method and algorithm that aimed to improve the convergence of the approach and enhance the dynamic response and stability of the terminal voltage of various test systems. One large-scale experimental test-bed consisted of a six-area, 39-bus system having ten generators that are connected to ten AVRs. The implementation showed promising results in providing stable terminal voltage profiles and other system parameters across a wide range of AVR systems under different test scenarios including N-1 contingency and fault conditions. The approach could provide significant stability improvement for wide-area systems as compared to the implementation of conventional methods such as using standalone AVR and/or power system stabilizers (PSS) for the wide-area control of power systems.
The project presented an integrated approach involving computer vision, activity monitoring and contextual information. The project can be used to detect rogue autonomous vehicles using sensors installed on observer vehicles that are used to monitor and identify the behavior of other autonomous vehicles operating on the road. The safe braking distance and the safe following time are computed to identify if an autonomous vehicle is behaving properly. There is a wide variation in both the safe following time and the safe braking distance recorded using three autonomous vehicles in a test-bed. The initial results showed significant progress for the future efforts to coordinate the operation of autonomous, semi-autonomous and non-autonomous vehicles
The safety and security of autonomous systems including unmanned vehicles is challenging considering large types of sensors and computational requirements. This project focuses on finding a method of identifying the optimal use of sensing systems to be used in various autonomous systems such as unmanned aerial vehicles, self-driving vehicles, robotic arms, etc. Various methods and algorithms have been designed for safe lane keeping and cruise control functionality of self-driving vehicles. Moreover, an adaptive model predictive control (AMPC) approach is presented that incorporates an optimal number of sensors to improve the performance of such systems. The resulted indicated that the presented approach could improve the safety of lane keeping and cruise control functionality as compared to other approaches.
Copyright © 2024 Abegaz Group - All Rights Reserved.