Linked e-resources
Details
Table of Contents
Intro
Preface
Organization
Contents
Big Data and New Method
Data-Driven Energy Efficiency Evaluation and Energy Anomaly Detection of Multi-type Enterprises Based on Energy Consumption Big Data Mining
1 Introduction
2 Determination of the Optimal Number of Clusters
3 Energy Consumption Pattern Recognition Based on K-Means Clustering
4 Abnormal Analysis of Energy Consumption Data
4.1 LOF Algorithm
4.2 CEEMDAN Algorithm
5 Example Simulation and Analysis
5.1 Enterprise Energy Consumption Mode Division
5.2 Abnormal Energy Consumption Detection for Enterprises
6 Conclusion
References
Research on Data-Driven AGC Instruction Execution Effect Recognition Method
1 Introduction
2 Independent Recurrent Neural Network
2.1 Recurrent Neural Network
2.2 Improvement of Deep Recurrent Neural Network
3 KPCA Preprocessing Process
4 Identification Process of AGC Instruction Execution Effect
5 Example Analysis
5.1 Basic Information of the Example
5.2 Comparative Analysis of Training Set and Validation Set
5.3 Comparative Analysis of DIndRNN Model and MLP Model
5.4 Influence of Preprocessing Strategy on Model Prediction Accuracy
6 Conclusion
References
Research on Day-Ahead Scheduling Strategy of the Power System Includes Wind Power Plants and Photovoltaic Power Stations Based on Big Data Clustering and Filling
1 The Introduction
2 K-Means Clustering Method for Massive Power Grid Data
3 Missing Data Processing Strategy Based on Historical Data Assisted Scene Analysis
4 Construction of Power System Optimization Model Including Wind Power Plant and Optical Power Station
4.1 Doubly-Fed Asynchronous Fan
4.2 Photovoltaic Power Array
4.3 The Objective Function
4.4 The Constraint
5 Example Analysis
5.1 The Example Described
5.2 Analysis of Optimization Results
References
Day-Ahead Scenario Generation Method for Renewable Energy Based on Historical Data Analysis
1 The Introduction
2 General Framework of Day-Ahead Scenario Generation Method for Renewable Energy
3 Cluster Analysis Based on Deep Embedding Clustering
3.1 Overall Framework of Deep Embedding Clustering Algorithm
3.2 Stacked Autoencoder
3.3 Initial Clustering of Low-Dimensional Features
3.4 Joint Optimization
4 Day-Ahead Scenario Generation Based on C-DCGAN
4.1 Conditional Deep Convolution GAN
4.2 Building Models Based on C-DCGAN
4.3 Training of the C-DCGAN Model
5 Determination and Evaluation of the Day-Ahead Value
5.1 Determination of the Day-Ahead Prediction Value
5.2 Evaluation of the Day-Ahead Prediction Value
6 Example Analysis
6.1 Day-Ahead Scenario Generation
6.2 Method Comparison
7 Conclusion
References
A High-Frequency Stock Price Prediction Method Based on Mode Decomposition and Deep Learning
1 Introduction
2 Related Work
Preface
Organization
Contents
Big Data and New Method
Data-Driven Energy Efficiency Evaluation and Energy Anomaly Detection of Multi-type Enterprises Based on Energy Consumption Big Data Mining
1 Introduction
2 Determination of the Optimal Number of Clusters
3 Energy Consumption Pattern Recognition Based on K-Means Clustering
4 Abnormal Analysis of Energy Consumption Data
4.1 LOF Algorithm
4.2 CEEMDAN Algorithm
5 Example Simulation and Analysis
5.1 Enterprise Energy Consumption Mode Division
5.2 Abnormal Energy Consumption Detection for Enterprises
6 Conclusion
References
Research on Data-Driven AGC Instruction Execution Effect Recognition Method
1 Introduction
2 Independent Recurrent Neural Network
2.1 Recurrent Neural Network
2.2 Improvement of Deep Recurrent Neural Network
3 KPCA Preprocessing Process
4 Identification Process of AGC Instruction Execution Effect
5 Example Analysis
5.1 Basic Information of the Example
5.2 Comparative Analysis of Training Set and Validation Set
5.3 Comparative Analysis of DIndRNN Model and MLP Model
5.4 Influence of Preprocessing Strategy on Model Prediction Accuracy
6 Conclusion
References
Research on Day-Ahead Scheduling Strategy of the Power System Includes Wind Power Plants and Photovoltaic Power Stations Based on Big Data Clustering and Filling
1 The Introduction
2 K-Means Clustering Method for Massive Power Grid Data
3 Missing Data Processing Strategy Based on Historical Data Assisted Scene Analysis
4 Construction of Power System Optimization Model Including Wind Power Plant and Optical Power Station
4.1 Doubly-Fed Asynchronous Fan
4.2 Photovoltaic Power Array
4.3 The Objective Function
4.4 The Constraint
5 Example Analysis
5.1 The Example Described
5.2 Analysis of Optimization Results
References
Day-Ahead Scenario Generation Method for Renewable Energy Based on Historical Data Analysis
1 The Introduction
2 General Framework of Day-Ahead Scenario Generation Method for Renewable Energy
3 Cluster Analysis Based on Deep Embedding Clustering
3.1 Overall Framework of Deep Embedding Clustering Algorithm
3.2 Stacked Autoencoder
3.3 Initial Clustering of Low-Dimensional Features
3.4 Joint Optimization
4 Day-Ahead Scenario Generation Based on C-DCGAN
4.1 Conditional Deep Convolution GAN
4.2 Building Models Based on C-DCGAN
4.3 Training of the C-DCGAN Model
5 Determination and Evaluation of the Day-Ahead Value
5.1 Determination of the Day-Ahead Prediction Value
5.2 Evaluation of the Day-Ahead Prediction Value
6 Example Analysis
6.1 Day-Ahead Scenario Generation
6.2 Method Comparison
7 Conclusion
References
A High-Frequency Stock Price Prediction Method Based on Mode Decomposition and Deep Learning
1 Introduction
2 Related Work