A comparative study of surrogate based learning methods in solving power flow problem

Keyphrases

• Surrogate-based 100%
• Power Flow Problem 100%
• Learning Methods 100%
• Power System 66%
• Noise Measurement 33%
• Learning Model 33%
• Measurement Error 33%
• Nonlinear Systems 33%
• Learning Approaches 33%
• Phase Angle 33%
• Regression Model 33%
• Numerical Results 33%
• Smart Grid 33%
• Least Squares Support Vector Regression (LSSVR) 33%
• Power Grid 33%
• Extreme Learning Machine 33%
• Voltage Magnitude 33%
• Gaussian Process Regression 33%
• Machine Learning-based Approach 33%
• Power Flow Equation 33%
• Process Support 33%
• Popular 33%
• Regression Vectors 33%
• IEEE-14 33%
• Voltage Phase 33%

Engineering

• Power Flow 100%
• Flow Problem 100%
• State Variable 100%
• Measurement Noise 33%
• Test System 33%
• Input Data 33%
• Measurement Error 33%
• Gaussians 33%
• Flow Equation 33%
• Power Grid 33%
• Extreme Learning Machine 33%
• Learning Approach 33%
• Learning System 33%
• Phase Shift 33%
• Nonlinear System 33%
• Support Vector Machine 33%
• Smart Grid 33%