Year: 2025
Type: article
Abstract: The increasing complexity and demand for reliability in power systems necessitate advanced fault detection mechanisms. This research focuses on implementing real-time fault detection using Power BI dashboards, which enhance operational decision-making through low-latency data handling. The primary objective is to develop a monitoring solution that not only detects faults promptly but also visualizes data effectively for stakeholders. This study employs a combination of real-time data collection techniques, advanced data processing, and visualization methodologies. By integrating various data sources, including sensors and historical data repositories, the proposed solution provides a comprehensive overview of system health. The effectiveness of Power BI dashboards in this context is explored, demonstrating significant improvements in fault detection rates and response times. Through experimental validation, the research presents compelling evidence that the Power BI solution outperforms traditional fault detection methods, both in speed and accuracy. The findings indicate detection rates of over 90% for critical fault types, with reduced response times compared to conventional approaches. Furthermore, user feedback highlights the intuitive design of the dashboards, reinforcing their role as a crucial tool in operational environments. Ultimately, this research contributes valuable insights into leveraging business intelligence tools for enhanced decision-making in power systems. The implications extend beyond fault detection, suggesting that similar methodologies can be adapted for other industries where real-time data processing is essential. This manuscript serves as a foundational work for future research aimed at optimizing power system management and enhancing reliability through technological innovations.
Author: Dr Anand Singh
Language: English
Subfield: Control and Systems Engineering
Field: Engineering
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4414829398
FWCI:
Cites:
Cited by:
Related to: