scholarly journals Improving short-term forecasting during ramp events by means of Regime-Switching Artificial Neural Networks

2011 ◽  
Vol 6 (1) ◽  
pp. 55-58 ◽  
Author(s):  
C. Gallego ◽  
A. Costa ◽  
A. Cuerva
Keyword(s):  
Time Series ◽  
Wind Power ◽  
Regime Switching ◽  
Neural Nets ◽  
Ann Model ◽  
Short Term ◽  
Explanatory Variables ◽  
Ramp Events ◽  
Artificial Neural ◽  
Short Term Forecasting

Abstract. Ramp events are large rapid variations within wind power time series. Ramp forecasting can benefit from specific strategies so as to particularly take into account these shifts in the wind power output dynamic. In the short-term context (characterized by prediction horizons from minutes to a few days), a Regime-Switching (RS) model based on Artificial Neural Nets (ANN) is proposed. The objective is to identify three regimes in the wind power time series: Ramp-up, Ramp-down and No-ramp regime. An on-line regime assessment methodology is also proposed, based on a local gradient criterion. The RS-ANN model is compared to a single-ANN model (without regime discrimination), concluding that the regime-switching strategy leads to significant improvements for one-hour ahead forecasts, mainly due to the improvements obtained during ramp-up events. Including other explanatory variables (NWP outputs, local measurements) during the regime assessment could eventually improve forecasts for further horizons.

scholarly journals A Markov Regime Switching Model for Ultra-Short-Term Wind Power Prediction Based on Toeplitz Inverse Covariance Clustering

2021 ◽  
Vol 9 ◽  
Author(s):  
Hang Fan ◽  
Xuemin Zhang ◽  
Shengwei Mei ◽  
Junzi Zhang
Keyword(s):  
Time Series ◽  
Prediction Model ◽  
Wind Power ◽  
Regime Switching ◽  
Wind Farms ◽  
Power Prediction ◽  
Short Term ◽  
Markov Regime Switching ◽  
Switching Model ◽  
Switching Method

The rapid development of wind energy has brought a lot of uncertainty to the power system. The accurate ultra-short-term wind power prediction is the key issue to ensure the stable and economical operation of the power system. It is also the foundation of the intraday and real-time electricity market. However, most researches use one prediction model for all the scenarios which cannot take the time-variant and non-stationary property of wind power time series into consideration. In this paper, a Markov regime switching method is proposed to predict the ultra-short-term wind power of multiple wind farms. In the regime switching model, the time series is divided into several regimes that represent different hidden patterns and one specific prediction model can be designed for each regime. The Toeplitz inverse covariance clustering (TICC) is utilized to divide the wind power time series into several hidden regimes and each regime describes one special spatiotemporal relationship among wind farms. To represent the operation state of the wind farms, a graph autoencoder neural network is designed to transform the high-dimensional measurement variable into a low-dimensional space which is more appropriate for the TICC method. The spatiotemporal pattern evolution of wind power time series can be described in the regime switching process. Markov chain Monte Carlo (MCMC) is used to generate the time series of several possible regime numbers. The Kullback-Leibler (KL) divergence criterion is used to determine the optimal number. Then, the spatiotemporal graph convolutional network is adopted to predict the wind power for each regime. Finally, our Markov regime switching method based on TICC is compared with the classical one-state prediction model and other Markov regime switching models. Tests on wind farms located in Northeast China verified the effectiveness of the proposed method.

scholarly journals Univariate Time Series Analysis of Short-Term Forecasting Horizons Using Artificial Neural Networks: The Case of Public Ambulance Emergency Preparedness

2020 ◽  
Vol 2020 ◽  
pp. 1-11
Author(s):  
Tichaona W. Mapuwei ◽  
Oliver Bodhlyera ◽  
Henry Mwambi
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Performance Measures ◽  
Test Statistic ◽  
Short Term ◽  
Neural Network Models ◽  
Linear Pattern ◽  
Univariate Time Series ◽  
Artificial Neural ◽  
Short Term Forecasting

This study examined the applicability of artificial neural network models in modelling univariate time series ambulance demand for short-term forecasting horizons in Zimbabwe. Bulawayo City Councils’ ambulance services department was used as a case study. Two models, feed-forward neural network (FFNN) and seasonal autoregressive integrated moving average, (SARIMA) were developed using monthly historical data from 2010 to 2017 and compared against observed data for 2018. The mean absolute error (MAE), root mean square error (RMSE), and paired sample t-test were used as performance measures. Calculated performance measures for FFNN were MAE (94.0), RMSE (137.19), and the test statistic value p=0.493(>0.05) whilst corresponding values for SARIMA were 105.71, 125.28, and p=0.005(<0.05), respectively. Findings of this study suggest that the FFNN model is inclined to value estimation whilst the SARIMA model is directional with a linear pattern over time. Based on the performance measures, the parsimonious FFNN model was selected to predict short-term annual ambulance demand. Demand forecasts with FFNN for 2019 reflected the expected general trends in Bulawayo. The forecasts indicate high demand during the months of January, March, September, and December. Key ambulance logistic activities such as vehicle servicing, replenishment of essential equipment and drugs, staff training, leave days scheduling, and mock drills need to be planned for April, June, and July when low demand is anticipated. This deliberate planning strategy would avoid a dire situation whereby ambulances are available but without adequate staff, essential drugs, and equipment to respond to public emergency calls.

Very short-term forecasting of wind power generation using hybrid deep learning model

2021 ◽  
Vol 296 ◽  
pp. 126564
Author(s):  
Md Alamgir Hossain ◽  
Ripon K. Chakrabortty ◽  
Sondoss Elsawah ◽  
Michael J. Ryan
Keyword(s):  
Power Generation ◽  
Deep Learning ◽  
Wind Power ◽  
Learning Model ◽  
Wind Power Generation ◽  
Short Term ◽  
Short Term Forecasting ◽  
Deep Learning Model

scholarly journals Development of a wind turbine gearbox virtual load sensor using multibody simulation and artificial neural networks

2021 ◽  
Author(s):  
Baher Azzam ◽  
Ralf Schelenz ◽  
Björn Roscher ◽  
Abdul Baseer ◽  
Georg Jacobs
Keyword(s):  
Time Series ◽  
Wind Turbine ◽  
High Speed ◽  
Time Series Data ◽  
Development Trend ◽  
Series Data ◽  
Ann Model ◽  
Wind Turbine Gearbox ◽  
Virtual Sensor ◽  
Artificial Neural

AbstractA current development trend in wind energy is characterized by the installation of wind turbines (WT) with increasing rated power output. Higher towers and larger rotor diameters increase rated power leading to an intensification of the load situation on the drive train and the main gearbox. However, current main gearbox condition monitoring systems (CMS) do not record the 6‑degree of freedom (6-DOF) input loads to the transmission as it is too expensive. Therefore, this investigation aims to present an approach to develop and validate a low-cost virtual sensor for measuring the input loads of a WT main gearbox. A prototype of the virtual sensor system was developed in a virtual environment using a multi-body simulation (MBS) model of a WT drivetrain and artificial neural network (ANN) models. Simulated wind fields according to IEC 61400‑1 covering a variety of wind speeds were generated and applied to a MBS model of a Vestas V52 wind turbine. The turbine contains a high-speed drivetrain with 4‑points bearing suspension, a common drivetrain configuration. The simulation was used to generate time-series data of the target and input parameters for the virtual sensor algorithm, an ANN model. After the ANN was trained using the time-series data collected from the MBS, the developed virtual sensor algorithm was tested by comparing the estimated 6‑DOF transmission input loads from the ANN to the simulated 6‑DOF transmission input loads from the MBS. The results show high potential for virtual sensing 6‑DOF wind turbine transmission input loads using the presented method.

scholarly journals Short-term forecasting of soil temperature using artificial neural network

2014 ◽  
Vol 22 (3) ◽  
pp. 576-585 ◽  
Author(s):  
Hossein Tabari ◽  
P. Hosseinzadeh Talaee ◽  
Patrick Willems
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Soil Temperature ◽  
Short Term ◽  
Artificial Neural ◽  
Short Term Forecasting

Predicting wildfire vulnerability using logistic regression and artificial neural networks: a case study in Brazil's Federal District

2019 ◽  
Vol 28 (1) ◽  
pp. 35 ◽  
Author(s):  
Pablo Pozzobon de Bem ◽  
Osmar Abílio de Carvalho Júnior ◽  
Eraldo Aparecido Trondoli Matricardi ◽  
Renato Fontes Guimarães ◽  
Roberto Arnaldo Trancoso Gomes
Keyword(s):  
Logistic Regression ◽  
Characteristic Curve ◽  
Federal District ◽  
Burned Area ◽  
Ann Model ◽  
Wildfire Management ◽  
Explanatory Variables ◽  
Burned Areas ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Predicting the spatial distribution of wildfires is an important step towards proper wildfire management. In this work, we applied two data-mining models commonly used to predict fire occurrence – logistic regression (LR) and an artificial neural network (ANN) – to Brazil’s Federal District, located inside the Brazilian Cerrado. We used Landsat-based burned area products to generate the dependent variable, and nine different anthropogenic and environmental factors as explanatory variables. The models were optimised via feature selection for best area under receiver operating characteristic curve (AUC) and then validated with real burn area data. The models had similar performance, but the ANN model showed better AUC (0.77) and accuracy values when evaluating exclusively non-burned areas (73.39%), whereas it had worse accuracy overall (66.55%) when classifying burned areas, in which LR performed better (65.24%). Moreover, we compared the contribution of each variable to the models, adding some insight into the main causes of wildfires in the region. The main driving aspects of the burned area distribution were land-use type and elevation. The results showed good performance for both models tested. These studies are still scarce despite the importance of the Brazilian savanna.

An Artificial Neural Network in Short-Term Electrical Load Forecasting of a University Campus: A Case Study

2013 ◽  
Vol 135 (3) ◽  
Author(s):  
David Palchak ◽  
Siddharth Suryanarayanan ◽  
Daniel Zimmerle
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Energy Consumption ◽  
Time Of Day ◽  
University Campus ◽  
Electrical Load ◽  
Ann Model ◽  
Short Term ◽  
Management Options ◽  
Artificial Neural

This paper presents an artificial neural network (ANN) for forecasting the short-term electrical load of a university campus using real historical data from Colorado State University. A spatio-temporal ANN model with multiple weather variables as well as time identifiers, such as day of week and time of day, are used as inputs to the network presented. The choice of the number of hidden neurons in the network is made using statistical information and taking into account the point of diminishing returns. The performance of this ANN is quantified using three error metrics: the mean average percent error; the error in the ability to predict the occurrence of the daily peak hour; and the difference in electrical energy consumption between the predicted and the actual values in a 24-h period. These error measures provide a good indication of the constraints and applicability of these predictions. In the presence of some enabling technologies such as energy storage, rescheduling of noncritical loads, and availability of time of use (ToU) pricing, the possible demand-side management options that could stem from an accurate prediction of energy consumption of a campus include the identification of anomalous events as well the management of usage.

Sign in / Sign up

Export Citation Format

Share Document