Improving the Electricity Price Prediction Accuracy by Applying Combined Prediction Models

Vestnik MEI ◽  
2020 ◽  
Vol 6 (6) ◽  
pp. 119-128
Author(s):  
Anna V. Shikhina ◽  
◽  
Tatyana V. Yagodkina ◽  
Keyword(s):  
Electricity Markets ◽  
Prediction Accuracy ◽  
Regression Models ◽  
Prediction Models ◽  
Free Market ◽  
Moving Average ◽  
Market Price ◽  
Electricity Price ◽  
Multifactor Models ◽  
Price Prediction

The solution of problems concerned with predicting a free market price for electricity through constructing different prediction models is considered. In so doing, a shift is made from an analysis of conventional regression and auto-regression models of the moving average to the proposed combined multifactor models, which also include the time trend and dummy variables. This shift is partly justified by the specific behavior of the electricity price in the free market, which is caused by a strictly cyclic change of its value, e.g., proceeding from such attributes as the heating season, day of week, etc. The techniques of constructing combined prediction models has been developed to the level of elaborating effective computational procedures based on the Statistica and OsiSoft PI-System software packages. The application of the autoregressive and combined regression prediction models to the Russian market has demonstrated their fairly good effectiveness with an acceptable level of accuracy. A comparison of the achieved levels of accuracy provided by the competing models has not shown any advantages of the shift to the use of combined regression multifactor models in terms of achieving better prediction accuracy; however, their application for analyzing the influence of different factors on the predicted variable may become a fundamental advantage in selecting the type of prediction model. Despite their being limited to an analysis of the Belgorod region market, the obtained results demonstrate the achieved prediction accuracy that is as least as good, and in the main is even better than the majority of the data presented in the review of the results for European electricity markets. The article substantiates the advisability of studying the combined regression models as a tool for analyzing the influence of individual factors as components influencing the electricity price formation for the predicted period, given that the accuracy level of the combined regression models corresponds to the currently achieved electricity price prediction accuracy levels.

scholarly journals Neural Network Based Model Comparison for Intraday Electricity Price Forecasting

Energies ◽  
2019 ◽  
Vol 12 (23) ◽  
pp. 4557 ◽  
Author(s):  
Ilkay Oksuz ◽  
Umut Ugurlu
Keyword(s):  
Neural Networks ◽  
Electricity Markets ◽  
Electricity Market ◽  
Network Architecture ◽  
Model Comparison ◽  
Market Price ◽  
Absolute Error ◽  
Electricity Price ◽  
Price Forecasting ◽  
Electricity Price Forecasting

The intraday electricity markets are continuous trade platforms for each hour of the day and have specific characteristics. These markets have shown an increasing number of transactions due to the requirement of close to delivery electricity trade. Recently, intraday electricity price market research has seen a rapid increase in a number of works for price prediction. However, most of these works focus on the features and descriptive statistics of the intraday electricity markets and overlook the comparison of different available models. In this paper, we compare a variety of methods including neural networks to predict intraday electricity market prices in Turkish intraday market. The recurrent neural networks methods outperform the classical methods. Furthermore, gated recurrent unit network architecture achieves the best results with a mean absolute error of 0.978 and a root mean square error of 1.302. Moreover, our results indicate that day-ahead market price of the corresponding hour is a key feature for intraday price forecasting and estimating spread values with day-ahead prices proves to be a more efficient method for prediction.

scholarly journals Civil airline fare prediction with a multi-attribute dual-stage attention mechanism

2021 ◽  
Author(s):  
Zhichao Zhao ◽  
Jinguo You ◽  
Guoyu Gan ◽  
Xiaowu Li ◽  
Jiaman Ding
Keyword(s):  
Prediction Models ◽  
Moving Average ◽  
Attention Mechanism ◽  
Civil Aviation ◽  
Data Sets ◽  
Prediction System ◽  
Price Prediction ◽  
Dual Stage ◽  
Core Facilities ◽  
The Impact

AbstractAirfare price prediction is one of the core facilities of the decision support system in civil aviation, which includes departure time, days of purchase in advance and flight airline. The traditional airfare price prediction system is limited by the nonlinear interrelationship of multiple factors and fails to deal with the impact of different time steps, resulting in low prediction accuracy. To address these challenges, this paper proposes a novel civil airline fare prediction system with a Multi-Attribute Dual-stage Attention (MADA) mechanism integrating different types of data extracted from the same dimension. In this method, the Seq2Seq model is used to add attention mechanisms to both the encoder and the decoder. The encoder attention mechanism extracts multi-attribute data from time series, which are optimized and filtered by the temporal attention mechanism in the decoder to capture the complex time dependence of the ticket price sequence. Extensive experiments with actual civil aviation data sets were performed, and the results suggested that MADA outperforms airfare prediction models based on the Auto-Regressive Integrated Moving Average (ARIMA), random forest, or deep learning models in MSE, RMSE, and MAE indicators. And from the results of a large amount of experimental data, it is proven that the prediction results of the MADA model proposed in this paper on different routes are at least 2.3% better than the other compared models.

Impact of Chaining Method and Level of Completion on Accuracy of Function Structure-Based Market Price Prediction Models

2017 ◽  
Author(s):  
Amaninder Singh Gill ◽  
Joshua D. Summers
Keyword(s):  
Prediction Models ◽  
Market Price ◽  
Function Structure ◽  
Topological Information ◽  
Market Prices ◽  
Forward Chaining ◽  
Price Prediction ◽  
Accuracy And Precision ◽  
Model Completion ◽  
Different Levels

The goal of this paper is to explore how different modeling approaches to construct function structure models and different levels of model completion affect the information contained within the respective models. Specifically, the models are used to predict market prices of products. These predictions are compared based on their accuracy and precision. This work is based on previous studies on understanding how function modeling is done and how topological information from design graphs can be used to predict information with historical training. It was found that forward chaining was the least favorable chaining type irrespective of the level of completion. Backward chaining models work relatively better across all completion percentages, while Nucleation models don’t perform as well for a higher completion percentage. Hence, a greater attention is needed to understand and employ the methods yielding the most accuracy.

Forecast of Bus Passenger Traffic Based on Exponential Smoothing and Trend Moving Average Method

2013 ◽  
Vol 433-435 ◽  
pp. 1374-1378
Author(s):  
Sheng Yang Ge ◽  
Chang Jiang Zheng ◽  
Mao Mao Hou
Keyword(s):  
Average Method ◽  
Prediction Accuracy ◽  
Prediction Models ◽  
Moving Average ◽  
Exponential Smoothing ◽  
Basic Theory ◽  
Traffic Prediction ◽  
Passenger Traffic

Two prediction models, exponential smoothing and trend moving average method, are selected for bus passenger traffic prediction. An analysis is made from aspects of basic idea, basic theory and so on. With the bus passenger traffic of Anqing, underlying index is used to compare the prediction accuracy of two models. The results demonstrate that trend moving average method has better effect on bus passenger traffic prediction. Therefore, the trend moving average method is rational and effective on the bus passenger traffic prediction.

scholarly journals Future economic perspective and potential revenue of non-subsidized wind turbines in Germany

2021 ◽  
Vol 6 (1) ◽  
pp. 177-190
Author(s):  
Lucas Blickwedel ◽  
Freia Harzendorf ◽  
Ralf Schelenz ◽  
Georg Jacobs
Keyword(s):  
Wind Turbines ◽  
Electricity Markets ◽  
Business Models ◽  
Market Price ◽  
Order Effect ◽  
Electricity Price ◽  
Future Market ◽  
New Business ◽  
Uncertain Future ◽  
Revenue Estimation

Abstract. Fixed feed-in tariffs based on the Renewable Energy Act grant secure revenues from selling electricity for wind turbine operators in Germany. Anyhow, the level of federal financial support is being reduced consecutively. Plant operators must trade self-sufficiently in the future and hence generate revenue by selling electricity directly on electricity markets. Therefore, uncertain future market price developments will influence investment considerations and may lead to stagnation in the expansion of renewable energies. This study estimates future revenue potentials of non-subsidized wind turbines in Germany to reduce this risk. The paper introduces and analyses a forecasting model that generates electricity price time series suited for revenue estimation of wind turbines based on the electricity exchange market. Revenues from the capacity market are neglected. The model is based on openly accessible data and applies a merit-order approach in combination with a simple agent-based approach to forecast long-term day-ahead prices at an hourly resolution. The hourly generation profile of wind turbines can be mapped over several years in conjunction with fluctuations in the electricity price. Levelized revenue of energy is used to assess both dynamic variables (electricity supply and price). The merit-order effect from the expansion of renewables as well as the phasing out of nuclear energy and coal are assessed in a scenario analysis. Based on the assumptions made, the opposing effects could result in a constant average price level for Germany over the next 20 years. The influence of emission prices is considered in a sensitivity analysis and correlates with the share of fossil generation capacities in the generation mix. In a brief case study, it was observed that current average wind turbines are not able to yield financial profit over their lifetime without additional subsidies for the given case. This underlines a need for technical development and new business models like power purchase agreements. The model results can be used for setting and negotiating appropriate terms, such as energy price schedule or penalties for those agreements.

Forecasting Chinese Stock Market Prices using Baidu Search Index with a Learning-Based Data Collection Method

2019 ◽  
Vol 18 (05) ◽  
pp. 1605-1629 ◽  
Author(s):  
Jichang Dong ◽  
Wei Dai ◽  
Ying Liu ◽  
Lean Yu ◽  
Jie Wang
Keyword(s):  
Data Collection ◽  
Stock Market ◽  
Prediction Accuracy ◽  
Prediction Models ◽  
Robust Statistics ◽  
Market Price ◽  
Chinese Stock Market ◽  
Collection Method ◽  
Data Collection Method ◽  
Search Index

In this study, to address search index selection and volatility problems, we propose a learning-based search index collection method that collects the search data fraction for modeling by learning the best criteria from robust statistics. Based on the fraction of collected search index from internet search engine ( Baidu.com ) data sources, a novel model is formulated for Chinese stock market price forecasting. We empirically test our method on the two main Chinese stock market price indexes and discover that the prediction accuracy is equivalent or superior to the benchmarks from previous studies that used alternative search index collection methods or lagged data prediction models. All prediction results outstand the importance of an effective data collection method for the robustness of forecast models and demonstrate the utility of a learning-based collection method for addressing search index collection problem, leading to a significant improvement in Chinese stock market price prediction accuracy.

scholarly journals Forecasting Daily Electricity Price by Hybrid Model of Fractional Wavelet Transform, Feature Selection, Support Vector Machine and Optimization Algorithm

Electronics ◽  
2021 ◽  
Vol 10 (18) ◽  
pp. 2214
Author(s):  
Rahmad Syah ◽  
Afshin Davarpanah ◽  
Marischa Elveny ◽  
Ashish Kumar Karmaker ◽  
Mahyuddin Nasution ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Feature Selection ◽  
Wavelet Transform ◽  
Electricity Markets ◽  
Moving Average ◽  
Electricity Price ◽  
Support Vector ◽  
Forecast Errors ◽  
Electricity Prices ◽  
Fractional Wavelet Transform

This paper proposes a novel hybrid forecasting model with three main parts to accurately forecast daily electricity prices. In the first part, where data are divided into high- and low-frequency data using the fractional wavelet transform, the best data with the highest relevancy are selected, using a feature selection algorithm. The second part is based on a nonlinear support vector network and auto-regressive integrated moving average (ARIMA) method for better training the previous values of electricity prices. The third part optimally adjusts the proposed support vector machine parameters with an error-base objective function, using the improved grey wolf and particle swarm optimization. The proposed method is applied to forecast electricity markets, and the results obtained are analyzed with the help of the criteria based on the forecast errors. The results demonstrate the high accuracy in the MAPE index of forecasting the electricity price, which is about 91% as compared to other forecasting methods.

Sign in / Sign up

Export Citation Format

Share Document