MACHINE LEARNING BASED GRID SAFETY ASSESSMENT THROUGH SIMULATION OF UNEXPECTED CONTINGENCIES DURING MAINTENANCE

Abstract

Effective maintenance coordination has become essential to ensuring a reliable electricity supply in power systems primarily powered by renewable sources. On the other hand, the computational complexity of the operational security standards presents difficulties for the existing planning tools. To solve this problem, a research paper suggests applying the machine learning (ML) method known as lightning search optimised random forest (LSORF) to anticipate the results of contingency analyses rapidly and effectively. The entire regional transmission system of Belgium (BE), which includes voltage ranges of 200 kV to 50 kV, is the subject of the study. Results show that LSORF regularly outperforms other benchmarks. The results demonstrate that LSORF consistently outperforms other benchmark methods. Furthermore, the study highlights the impact of projected growth in renewable energy on maintenance feasibility. This strategy provides useful insights for improving maintenance planning in renewable energy systems.

Keywords

• renewable energy
• machine learning (ml)
• lightning search optimised random forest (lsorf)
• contingency