Improving Short Term Load Forecasting with a Novel Hybrid Model Approach as a Precondition for Algorithmic Trading
-
Abstract
Considering the changing European power market, accurate electric load forecasts are of significant importance for power traders to reduce costs for ancillary services by leveling their position on continuous intradaypower markets. The first part of the following case study, based on publicly available load data, focuses on a novel approach to combine different forecasting methodologies and techniques from the area of computational intelligence. The proposed hybrid model blends input forecasts from artificial neuronal networks, multi variable linear regression and support vector regression machine models with fuzzy sets to intraday and day-ahead forecasts. The forecasts are evaluated with commonly used metrics (mean average percentage error - MAPE & normalized rooted mean square error - NRMSE) to allow comparisons with other case studies. Results from input forecasting models range from a yearly MAPE of 2.36% for the linear regression model to 2.1%for the support vector machine. Blended forecast from proposed hybrid models results in a MAPE of 1.46%for one hour and a MAPE of 1.72% for 24 hours ahead forecasts. In the outlook section of the paperwe show how to use blended forecasts as an input source for automatized intraday power trading with algorithms. Besides outlining use cases, model structure of trading algorithms and back testing approaches, the paper offers a state of the art insight on algorithmic trading in the power industry.
Abstract
Considering the changing European power market, accurate electric load forecasts are of significant importance for power traders to reduce costs for ancillary services by leveling their position on continuous intradaypower markets. The first part of the following case study, based on publicly available load data, focuses on a novel approach to combine different forecasting methodologies and techniques from the area of computational intelligence. The proposed hybrid model blends input forecasts from artificial neuronal networks, multi variable linear regression and support vector regression machine models with fuzzy sets to intraday and day-ahead forecasts. The forecasts are evaluated with commonly used metrics (mean average percentage error - MAPE & normalized rooted mean square error - NRMSE) to allow comparisons with other case studies. Results from input forecasting models range from a yearly MAPE of 2.36% for the linear regression model to 2.1%for the support vector machine. Blended forecast from proposed hybrid models results in a MAPE of 1.46%for one hour and a MAPE of 1.72% for 24 hours ahead forecasts. In the outlook section of the paperwe show how to use blended forecasts as an input source for automatized intraday power trading with algorithms. Besides outlining use cases, model structure of trading algorithms and back testing approaches, the paper offers a state of the art insight on algorithmic trading in the power industry.
Kapitel in diesem Buch
- Frontmatter I
- Preface of the Editors V
- Advances in Systems, Signals and Devices VII
- Editorial Board Members VIII
- Advances in Systems, Signals and Devices XI
- Contents XIII
- Improving Short Term Load Forecasting with a Novel Hybrid Model Approach as a Precondition for Algorithmic Trading 1
- Comparison of three Loss Optimization Techniques of FOC Induction Motor Drive 19
- PWM Modulation Technique of Three-Phase Indirect Matrix Converter 35
- Modeling of Unbalanced Radial Distribution System and Backward – Forward Power Flow Analysis 47
- Complex Dynamics in a Two-cell DC/DC Buck Converter using a Dynamic Feedback Controller 61
- Degradation Analysis of the Lead Acid Battery Plates in the Manufacturing Process Based on SADT and Causal Tree Analysis 89
- Modeling and Analysis of the Open-End Stator Winding Permanent Magnet SM with Salient-Poles fed by VSI 105
- A FC/UC Hybrid Source Energy Management Algorithm with Optimal Parameters 123
- Power System State Estimation Using PMU Technology 139
- A NewWavelet−ANN Approach Based on Feature Extraction for a FAST Wind Turbine Model Diagnosis System 155
- Implementation of a Temperature Measurement Method for Condition Monitoring of IGBT Converter Modules in Online-Mode 179
Kapitel in diesem Buch
- Frontmatter I
- Preface of the Editors V
- Advances in Systems, Signals and Devices VII
- Editorial Board Members VIII
- Advances in Systems, Signals and Devices XI
- Contents XIII
- Improving Short Term Load Forecasting with a Novel Hybrid Model Approach as a Precondition for Algorithmic Trading 1
- Comparison of three Loss Optimization Techniques of FOC Induction Motor Drive 19
- PWM Modulation Technique of Three-Phase Indirect Matrix Converter 35
- Modeling of Unbalanced Radial Distribution System and Backward – Forward Power Flow Analysis 47
- Complex Dynamics in a Two-cell DC/DC Buck Converter using a Dynamic Feedback Controller 61
- Degradation Analysis of the Lead Acid Battery Plates in the Manufacturing Process Based on SADT and Causal Tree Analysis 89
- Modeling and Analysis of the Open-End Stator Winding Permanent Magnet SM with Salient-Poles fed by VSI 105
- A FC/UC Hybrid Source Energy Management Algorithm with Optimal Parameters 123
- Power System State Estimation Using PMU Technology 139
- A NewWavelet−ANN Approach Based on Feature Extraction for a FAST Wind Turbine Model Diagnosis System 155
- Implementation of a Temperature Measurement Method for Condition Monitoring of IGBT Converter Modules in Online-Mode 179
