Data-driven trajectory prediction of grid power frequency based on neural models

Keyphrases

• Adequate Margin 50%
• Data-driven Approach 50%
• Error Index 50%
• Frequency Estimation 50%
• Frequency Features 50%
• Frequency-based Approach 100%
• Grid Electricity 100%
• Inertia Reduction 50%
• Input Time 50%
• Long Short-term Memory Network 50%
• Machine Learning Techniques 50%
• Neural Model 100%
• Noise Signal 50%
• Non-synchronous Generation 50%
• Nonlinear Autoregressive Network 50%
• Nordic Power System 50%
• Phasor Measurement Unit 100%
• Power Frequency 100%
• Power System 50%
• Prediction Method 50%
• Robustness Index 50%
• Root Mean Square Error 50%
• System Frequency 50%
• System Frequency Response 50%
• System Security 50%
• Time Information 50%
• Time Series Data 50%
• Trajectory Prediction 100%

Engineering

• Collected Data 50%
• Data Series 50%
• Frequency Response 50%
• Input Frequency 50%
• Lstm 50%
• Machine Learning Technique 50%
• Neural Model 100%
• Noisy Signal 50%
• Phasor Measurement Unit 100%
• Power Engineering 100%
• Power Grid 100%
• Root-Mean-Squared Error 50%
• System Frequency 100%
• Test System 50%