Probabilistic forecasting of dynamic thermal line rating with temporal correlations

2022 ◽  
Vol 134 ◽  
pp. 107443
Author(s):  
Tomas Barton ◽  
Petr Musilek
Keyword(s):  
Probabilistic Forecasting ◽  
Temporal Correlations ◽  
Thermal Line

Day-ahead Load Probabilistic Forecasting Based on Space-time Correction

2020 ◽  
Vol 13 ◽  
Author(s):  
Fei Jin ◽  
Xiaoliang Liu ◽  
Fangfang Xing ◽  
Guoqiang Wen ◽  
Shuangkun Wang ◽  
...  
Keyword(s):  
Short Term Memory ◽  
Northern China ◽  
Space Time ◽  
Load Prediction ◽  
Probabilistic Forecasting ◽  
Residual Distribution ◽  
Time And Space ◽  
Probability Prediction ◽  
Time Correction ◽  
Interval Coverage

Background : The day-ahead load forecasting is an essential guideline for power generating, and it is of considerable significance in power dispatch. Objective: Most of the existing load probability prediction methods use historical data to predict a single area, and rarely use the correlation of load time and space to improve the accuracy of load prediction. Methods: This paper presents a method for day-ahead load probability prediction based on space-time correction. Firstly, the kernel density estimation (KDE) is employed to model the prediction error of the long short-term memory (LSTM) model, and the residual distribution is obtained. Then the correlation value is used to modify the time and space dimensions of the test set's partial period prediction values. Results: The experiment selected three years of load data in 10 areas of a city in northern China. The MAPE of the two modified models on their respective test sets can be reduced by an average of 10.2% and 6.1% compared to previous results. The interval coverage of the probability prediction can be increased by an average of 4.2% and 1.8% than before. Conclusion: The test results show that the proposed correction schemes are feasible.

scholarly journals Probabilistic Forecasting of Photovoltaic Generation: An Efficient Statistical Approach

2017 ◽  
Vol 32 (3) ◽  
pp. 2471-2472 ◽  
Author(s):  
Can Wan ◽  
Jin Lin ◽  
Yonghua Song ◽  
Zhao Xu ◽  
Guangya Yang
Keyword(s):  
Statistical Approach ◽  
Probabilistic Forecasting ◽  
Photovoltaic Generation

scholarly journals Probabilistic Flight Delay Predictions Using Machine Learning and Applications to the Flight-to-Gate Assignment Problem

Aerospace ◽  
2021 ◽  
Vol 8 (6) ◽  
pp. 152
Author(s):  
Micha Zoutendijk ◽  
Mihaela Mitici
Keyword(s):  
Assignment Problem ◽  
Absolute Error ◽  
Aviation Industry ◽  
Probabilistic Forecasting ◽  
Flight Delays ◽  
Mixture Density ◽  
Assignment Model ◽  
Gate Assignment ◽  
Flight Delay ◽  
Delay Prediction

The problem of flight delay prediction is approached most often by predicting a delay class or value. However, the aviation industry can benefit greatly from probabilistic delay predictions on an individual flight basis, as these give insight into the uncertainty of the delay predictions. Therefore, in this study, two probabilistic forecasting algorithms, Mixture Density Networks and Random Forest regression, are applied to predict flight delays at a European airport. The algorithms estimate well the distribution of arrival and departure flight delays with a Mean Absolute Error of less than 15 min. To illustrate the utility of the estimated delay distributions, we integrate these probabilistic predictions into a probabilistic flight-to-gate assignment problem. The objective of this problem is to increase the robustness of flight-to-gate assignments. Considering probabilistic delay predictions, our proposed flight-to-gate assignment model reduces the number of conflicted aircraft by up to 74% when compared to a deterministic flight-to-gate assignment model. In general, the results illustrate the utility of considering probabilistic forecasting for robust airport operations’ optimization.

Reducing multipath effect of low-cost GNSS receivers for monitoring by considering temporal correlations

2020 ◽  
Vol 14 (2) ◽  
pp. 167-175
Author(s):  
Li Zhang ◽  
Volker Schwieger
Keyword(s):  
Low Cost ◽  
Ground Plane ◽  
Single Frequency ◽  
Spatial Correlations ◽  
Raw Data ◽  
Multipath Effect ◽  
Temporal Correlations ◽  
Multipath Effects ◽  
Gnss Receivers ◽  
Multipath Signals

AbstractThe investigations on low-cost single frequency GNSS receivers at the Institute of Engineering Geodesy (IIGS) show that u-blox GNSS receivers combined with low-cost antennas and self-constructed L1-optimized choke rings can reach an accuracy which almost meets the requirements of geodetic applications (see Zhang and Schwieger [25]). However, the quality (accuracy and reliability) of low-cost GNSS receiver data should still be improved, particularly in environments with obstructions. The multipath effects are a major error source for the short baselines. The ground plate or the choke ring ground plane can reduce the multipath signals from the horizontal reflector (e. g. ground). However, the shieldings cannot reduce the multipath signals from the vertical reflectors (e. g. walls).Because multipath effects are spatially and temporally correlated, an algorithm is developed for reducing the multipath effect by considering the spatial correlations of the adjoined stations (see Zhang and Schwieger [24]). In this paper, an algorithm based on the temporal correlations will be introduced. The developed algorithm is based on the periodic behavior of the estimated coordinates and not on carrier phase raw data, which is easy to use. Because, for the users, coordinates are more accessible than the raw data. The multipath effect can cause periodic oscillations but the periods change over time. Besides this, the multipath effect’s influence on the coordinates is a mixture of different multipath signals from different satellites and different reflectors. These two properties will be used to reduce the multipath effect. The algorithm runs in two steps and iteratively. Test measurements were carried out in a multipath intensive environment; the accuracies of the measurements are improved by about 50 % and the results can be delivered in near-real-time (in ca. 30 minutes), therefore the algorithm is suitable for structural health monitoring applications.

Sign in / Sign up

Export Citation Format

Share Document