Building on the previous chapter, this chapter delves deeper into the forecasting capabilities of the sequential ANN models. It presents a thorough analysis of the models’ performance in forecasting future harmonic distortions, considering a range of influencing factors such as variations in power injections and network topology. Sensitivity analysis sheds light on the key parameters affecting forecasting accuracy, offering insights into model optimization. The chapter also explores the models’ robustness through various case studies, including scenarios with limited PQ monitoring and increased harmonic orders. The findings demonstrate the models’ effectiveness in providing reliable harmonic forecasting, thereby supporting practical network management and the mitigation of potential harmonic-related issues.

错误:搜索内容不能为空,请输入英文关键词
错误:关键词超出字数限制,请精简
高级检索

Robustness of the Methodology for Harmonic Forecasting in Transmission Networks

  • Yuqi Zhao

摘要

Building on the previous chapter, this chapter delves deeper into the forecasting capabilities of the sequential ANN models. It presents a thorough analysis of the models’ performance in forecasting future harmonic distortions, considering a range of influencing factors such as variations in power injections and network topology. Sensitivity analysis sheds light on the key parameters affecting forecasting accuracy, offering insights into model optimization. The chapter also explores the models’ robustness through various case studies, including scenarios with limited PQ monitoring and increased harmonic orders. The findings demonstrate the models’ effectiveness in providing reliable harmonic forecasting, thereby supporting practical network management and the mitigation of potential harmonic-related issues.