《电力市场大数据分析=Data Analytics in Power Markets:英文》以电力市场领域近年来的研究工作成果为基础，力图系统性地介绍电力市场中的数据价值挖掘方法以支撑市场组织者和市场参与者的决策问题。《电力市场大数据分析=Data Analytics in Power Markets:英文》围绕电力市场中的公开数据和机器学习方法理论与应用展开，结合电力市场规则和物理特征，期望解决市场规则解析和数据结构化两大核心难点，并从负荷与电价预测、报价行为解析、金融衍生品投机等方面，构建了电力市场数据分析理论和技术方法体系。 《电力市场大数据分析=Data Analytics in Power Markets:英文》共13章，第1章介绍了世界各地的电力市场数据概况。除第1章外，剩余内容分为三部分。第一部分为负荷建模与预测，包括了基于智能电表数据的负荷预测方法等。第二部分为电价建模与预测，包括了节点电价数据的子空间特性建模等。第三部分为市场投标行为分析，包括了机组投标行为的特征提取方法等。
目錄：
Contents1 Introduction to Power Market Data 11.1 Overview of Electricity Markets 11.2 Organization and Data Disclosure of Electricity Market 41.2.1 Transaction Data 51.2.2 Price Data 71.2.3 Supply and Demand Data 71.2.4 System Operation Data 81.2.5 Forecast Data 81.2.6 Confidential Data 91.3 Conclusions 9References 9PartⅠ Load Modeling and Forecasting2 Load Forecasting with Smart Meter Data 132.1 Introduction 132.2 Framework 142.3 Ensemble Learning for Probabilistic Forecasting 162.3.1 Quantile Regression Averaging 172.3.2 Factor Quantile Regression Averaging 182.3.3 LASSO Quantile Regression Averaging 182.3.4 Quantile Gradient Boosting Regression Tree 192.3.5 Rolling Window-Based Forecasting 202.4 Case Study 202.4.1 Experimental Setups 22.4.2 Evaluation Criteria 212.4.3 Experimental Results 222.5 Conclusions 24References 243 Load Data Cleaning and Forecasting 273.1 Introduction 273.2 Characteristics of Load Profiles 293.2.1 Low-Rank Property of Load Profiles 293.2.2 Bad Data in Load Profiles 303.3 Methodology 313.3.1 Framework 313.3.2 Singular Value Thresholding (SVT) 323.3.3 Quantile RF Regression 343.3.4 Load Forecasting 353.4 Evaluation Criteria 353.4.1 Data Cleaning-Based Criteria 353.4.2 Load Forecasting-Based Criteria 353.5 Case Study 363.5.1 Result of Data Cleaning 363.5.2 Day Ahead Point Forecast 373.5.3 Day Ahead Probabilistic Forecast 383.6 Conclusions 40References 404 Monthly Electricity Consumption Forecasting 434.1 Introduction 434.2 Framework 464.2.1 Data Collection and Treatment 464.2.2 SVECM Forecasting 474.2.3 Self-adaptive Screening 484.2.4 Novelty and Characteristics of SAS-SVECM 484.3 Data Collection and Treatment 484.3.1 Data Collection and Tests 494.3.2 Seasonal Adjustments Based on X-12-ARIMA 494.4 SVECM Forecasting 494.4.1 VECM Forecasting 494.4.2 Time Series Extrapolation Forecasting 524.5 Self-adaptive Screening 534.5.1 Influential EEF Identification 534.5.2 Influential EEF Grouping 534.5.3 Forecasting Performance Evaluation Considering Different EEF Groups 554.6 Case Study 564.6.1 Basic Data and Tests 564.6.2 Electricity Consumption Forecasting Performance Without SAS 584.6.3 EC Forecasting Performance with SAS 614.6.4 SAS-SVECM Forecasting Comparisons with Other Forecasting Methods 654.7 Conclusions 67References 675 Probabilistic Load Forecasting 715.1 Introduction 715.2 Data and Model 735.2.1 Load Dataset Exploration 735.2.2 Linear Regression Model Considering Recency-Effects 735.3 Pre-Lasso Based Feature Selection 765.4 Sparse Penalized Quantile Regression (Quantile-Lasso) 775.4.1 Problem Formulation 775.4.2 ADMM Algorithm 785.5 Implementation 805.6 Case Study 815.6.1 Experiment Setups 815.6.2 Results 825.7 Concluding Remarks 86References 86Part Ⅱ Electricity Price Modeling and Forecasting6 Subspace Characteristics of LMP Data 916.1 Introduction 916.2 Model and Distribution of LMP 936.3 Methodology 6.3.1 Problem Formulation 966.3.2 Basic Framework 976.3.3 Principal Component Analysis 986.3.4 Recursive Basis Search (Bottom-Up) 986.3.5 Hyperplane Detection (Top-down) 1006.3.6 Short Summary 1036.4 Case Study 1036.4.1 Case 1: IEEE 30-Bus System 1046.4.2 Case 2: IEEE 118-Bus System 1066.4.3 Case 3: Illinois 200-Bus System 1066.4.4 Case 4: Southwest Power Pool (SPP) 1076.4.5 Time Consumption 1086.5 Discussion and Conclusion 1106.5.1 Discussion on Potential Applications 1106.5.2 Conclusion 110References 1117 Day-Ahead Electricity Price Forecasting 1137.1 Introduction 1137.2 Problem Formulation 1167.2.1 Decomposition of LMP 1167.2.2 Short-Term Forecast for Each Component 1177.2.3 Summation and Stacking of Individual Forecasts 1187.3 Methodology 1197.3.1 Framework 1197.3.2 Feature Engineering 1217.3.3 Regression Model Selection and Parameter Tuning 1227.3.4 Model Stacking with Robust Regression 1237.3.5 Metrics 1247.4 Case Study 1247.4.1 Model Selection Results 1257.4.2 Componential Results 1267.4.3 Stacking Results (Overall Improvements) 1287.4.4 Error Distribution Analysis 1297.5 Conclusion 132References 1328 Economic Impact of Price Forecasting Error 1358.1 Introduction 1358.2 General Bidding Models 1378.2.1 Deterministic Bidding Model 1388.2.2 Stochastic Bidding Model 1398.3 Methodology and Framework 1418.3.1 Forecasting Error Modeling 1418.3.2 Multiparametric Linear Programming (MPLP)Theory 1418.3.3 Error Impact Formulation 1428.3.4 Overall Framework 1448.4 Case Study 1458.4.1 Measurement of STPF Error Level 1458.4.2 Case 1: LSE with Deman
購物車/收銀台(0) | 在線留言板
| 付款方式
| 聯絡我們
| 運費計算
| 幫助中心 |
加入書簽
HOME
新書上架
