Search

Power transmission networks physically connect the power generators to the electric consumers. Such systems extend over hundreds of kilometers. There are many components in the transmission infrastructure that require a proper inspection to guarantee flawless performance and reliable delivery, which, if done manually, can be very costly and time consuming. One essential component is the insulator. Its failure can cause an interruption of the entire transmission line or a widespread power failure. Automated fault detection could significantly decrease inspection time and related costs. Recently, several works have been proposed based on convolutional neural networks, which address the issue mentioned above. However, existing studies focus on a specific type of insulator faults. Thus, in this study, we introduce a two-stage model that segments insulators from their background to then classify their states based on four different categories, namely: healthy, broken, burned/corroded and missing cap. The test results show that the proposed approach can realize the effective segmentation of insulators and achieve high accuracy in detecting several types of faults.

The fast growth of communication technology within the concept of smart grids can provide data and control signals from/to all consumers in an online fashion. This could foster more participation for end-user customers. These types of customers do not necessarily have powerful prediction tools or capability of storing a large amount of historical data. Besides, the relevant information is not always known a priori, while decisions need to be made fast within a very limited time. These limitations and also the novel structure of decision making, which comes from the necessities to make the decision very fast with a limited amount of information, implies a requirement for investigating a novel framework: online decision-making. In this study, we propose an online constrained convex optimization framework for operating responsive end-user electrical customers in real-time. Within this online-decision-making framework, algorithms are proposed for two cases: no prediction data is available at the moment of decision-making, and a limited number of forward time periods predictions of uncertain parameters are available. The simulation results exhibit the capability of the model to achieve considerable profits in an easy-to-implement procedure. Comprehensive numerical test cases are performed for comparison with existent alternative models.