1,450 Hits in 5.6 sec

Electric Load and Power Forecasting Using Ensemble Gaussian Process Regression [article]

Tong Ma and Renke Huang and David Barajas-Solano and Ramakrishna Tipireddy and Alexandre M. Tartakovsky
2019 arXiv   pre-print
The proposed approach for week-long forecasting is based on the Gaussian process regression (GPR) method, with prior covariance matrices of the quantities of interest (QoI) computed from ensembles formed  ...  We demonstrate that the the proposed ensemble GPR (EGPR) method is capable of accurately forecasting weekly total load demand and power generation profiles.  ...  Discussion and conclusions The ensemble Gaussian process regression (EGPR) method is proposed and used for weekly forecasting of load demand and generation scheduling (optimal generator output) for a power  ... 
arXiv:1910.03783v1 fatcat:rstn3uo42bhvrasnw4e6qsqcle

Deep Learning Approach to Power Demand Forecasting in Polish Power System

Tomasz Ciechulski, Stanisław Osowski
2020 Energies  
machine in regression model, for final 24-h forecast one-week advance.  ...  The paper presents a new approach to predicting the 24-h electricity power demand in the Polish Power System (PPS, or Krajowy System Elektroenergetyczny—KSE) using the deep learning approach.  ...  KSE Krajowy System Elektroenergetyczny (Polish Power System) MLP Multilayer perceptron RBF Radial basis function SVR Support vector machine in the regression model MAPE Mean absolute percentage error Energies  ... 
doi:10.3390/en13226154 fatcat:n4uzktl7dfdjpcblzjmq5a5kle

Probabilistic multivariate electricity price forecasting using implicit generative ensemble post-processing [article]

Tim Janke, Florian Steinke
2020 arXiv   pre-print
In this paper, we propose implicit generative ensemble post-processing, a novel framework for multivariate probabilistic electricity price forecasting.  ...  We use a likelihood-free implicit generative model based on an ensemble of point forecasting models to generate multivariate electricity price scenarios with a coherent dependency structure as a representation  ...  The data set contains the prices y d,h for the hours h ∈ {1, ..., 24} on the days d ∈ {1, ..., 1096} along with the forecasted load Load d,h , wind power generation W ind d,h , and solar power generation  ... 
arXiv:2005.13417v1 fatcat:ihvisyzflrfe5axgecevjqiqby

Applications of Probabilistic Forecasting in Smart Grids: A Review

Hosna Khajeh, Hannu Laaksonen
2022 Applied Sciences  
Then, it reviews how the recent literature used these forecasting methods and for which uncertain parameters they wanted to obtain distributions.  ...  Finally, we propose some future applications of probabilistic forecasting based on the flexibility challenges of power systems in the near future.  ...  Acknowledgments: The work of Hosna Khajeh was supported by the Ella and Georg Ehrnrooth Foundation. Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/app12041823 doaj:7983bd9658584546868ebcb5964433cc fatcat:ddrmqguhmbe6dpn5nbw3cl43bm

Stochastically forced ensemble dynamic mode decomposition for forecasting and analysis of near-periodic systems [article]

Daniel Dylewsky, David Barajas-Solano, Tong Ma, Alexandre M. Tartakovsky, J. Nathan Kutz
2021 arXiv   pre-print
Gaussian process regression (GPR) process to actuate this system.  ...  Results are presented for a test case using load data from an electrical grid.  ...  Results are also presented for the Ensemble Gaussian Process Regression (EGPR) method, which has been shown to improve accuracy in load forecasting applications compared to the standard GPR approach described  ... 
arXiv:2010.04248v2 fatcat:yqbaj73mcrbddj5ddgsyr65ztq

Using weather ensemble predictions in electricity demand forecasting

James W. Taylor, Roberto Buizza
2003 International Journal of Forecasting  
This study investigates the use of weather ensemble predictions in electricity demand forecasting for lead times from one to 10 days ahead.  ...  A weather ensemble prediction consists of 51 scenarios for a weather variable. We use these scenarios to produce 51 scenarios for the weather-related component of electricity demand.  ...  Acknowledgements We are very grateful to Shanti Majithia and Chris Rogers of the National Grid Group for supplying data and information regarding the company's approach to demand forecasting, and to Tony  ... 
doi:10.1016/s0169-2070(01)00123-6 fatcat:lmribprdfreatnfn7g5ptuhpse

Guest Editorial for the Special Section on Advances in Renewable Energy Forecasting: Predictability, Business Models and Applications in the Power Industry

Ricardo J. Bessa, Pierre Pinson, George Kariniotakis, Dipti Srinivasan, Charlie Smith, Nima Amjady, Hamidreza Zareipour
2022 IEEE Transactions on Sustainable Energy  
Currently, power system operators and electrical energy traders use weather and power forecasts embedded in their decision-making processes.  ...  energy forecasting and prescriptive analytics, and novel use cases for forecasting in power system operation and electricity markets.  ... 
doi:10.1109/tste.2022.3157009 fatcat:opza5jppwbcb5ggbshlf72jqt4

Combining Probabilistic Load Forecasts [article]

Yi Wang, Ning Zhang, Yushi Tan, Tao Hong, Daniel Kirschen, Chongqing Kang
2018 arXiv   pre-print
In recent years, many methodologies and techniques have been proposed for probabilistic load forecasting.  ...  This paper proposes a constrained quantile regression averaging (CQRA) method to create an improved ensemble from several individual probabilistic forecasts.  ...  His research interests include power system planning, power system operation, renewable energy, low carbon electricity technology and load forecasting.  ... 
arXiv:1803.06730v1 fatcat:smrhlfto6bgfhnafedotzxlq4e

Review of Low Voltage Load Forecasting: Methods, Applications, and Recommendations [article]

Stephen Haben, Siddharth Arora, Georgios Giasemidis, Marcus Voss, Danica Vukadinovic Greetham
2021 arXiv   pre-print
Reliable forecasting will be a necessary component of many of these systems to anticipate key features and uncertainties.  ...  Despite this urgent need, there has not yet been an extensive investigation into the current state-of-the-art of low voltage level forecasts, other than at the smart meter level.  ...  compared with linear regression, SVMs, and composite kernel methods based on Gaussian process regression.  ... 
arXiv:2106.00006v2 fatcat:rb2yrt4tsjap3jhrb7dz76dg2e

State of the art of machine learning models in energy systems, a systematic review

Mohsen Salimi, Amir Mosavi, Sina Faizollahzadeh Ardabili, Majid Amidpour, Timon Rabczuk, Shahabodin Shamshirband
2020 Zenodo  
Machine learning (ML) models have been widely used in diverse applications of energy systems such as design, modeling, complex mappings, system identification, performance prediction, and load forecasting  ...  This paper further concludes that there is an outstanding rise in the accuracy, robustness, precision and the generalization ability of the ML models in energy systems using the hybrid and ensemble ML  ...  System to forecast electricity load.  ... 
doi:10.5281/zenodo.4056884 fatcat:yf6gjoevffc2xnzoyjlc3pxbii

Short-term load forecasting in a hybrid microgrid: a case study in Tanzania

Benson Mbuya, Matteo Moncecchi, Marco Merlo, Thomas Kivevele
2019 Journal of Electrical Systems  
A short-term load forecast model framework consisting of hybrid feature selection and prediction model was developed using MATLAB©environment.  ...  Ngarenanyuki school microgrid's data was used for the experimental short-term load forecast in this case study.  ...  es salaam Institute of Technology, Ngarenanyuki secondary school, MCM energy lab -spin off Politecnico di Milano, OIKOS, ELVI Group, Phoenix contact, and Energy Team © .  ... 
doaj:6e156c0faad6470a8809788559a646e8 fatcat:o32v6zm5gvhebn6qryg77yqcxm

Incremental Ensemble Learning for Electricity Load Forecasting

2016 Acta Polytechnica Hungarica  
The model was designed to make predictions for electricity load time series taking into account their inherent characteristics, such as seasonal dependency and concept drift.  ...  The proposed ensemble model characteristicsrobustness, natural ability to parallelize and the ability to incrementally train the modelmake the presented ensemble suitable for processing streams of data  ...  Support Vector Machines are an excellent tool for classification, novelty detection, and regression (SVR). It is one of the most often used models for electricity load forecasting.  ... 
doi:10.12700/aph.13.2.2016.2.6 fatcat:uth2qbvolnbkdabxbz7sxwl4km

Towards Improved Understanding of the Applicability of Uncertainty Forecasts in the Electric Power Industry

Ricardo Bessa, Corinna Möhrlen, Vanessa Fundel, Malte Siefert, Jethro Browell, Sebastian Haglund El Gaidi, Bri-Mathias Hodge, Umit Cali, George Kariniotakis
2017 Energies  
For UC, this is typically performed in the day-ahead, and thus deterministic wind power forecasts used in this process typically range from 12-48 h ahead of the operating hour.  ...  Deterministic forecasts of load and renewable generation are critical in this process as it is currently designed due to the search of a single "optimal" solution.  ...  load; wind power and load forecast errors).  ... 
doi:10.3390/en10091402 fatcat:o6ebcce4wfgj5gnkujy3ggkk6a

A Short-Term User Load Forecasting with Missing Data

Zhi ZHANG, Liang GUO, Yan-jie DAI, Xiang-uang DONG, Ping-xin WANG
2018 DEStech Transactions on Engineering and Technology Research  
Different from wide area power grid, it is more difficult to implement short-term user load forecasting, especially existing missing data.  ...  Short-term load forecasting is an important component of grid economic dispatching and the forecasting error directly affects the economy of grid operation.  ...  In addition, nonparametric approaches had been used to do probabilistic forecasting problem, such as Gaussian process [7] .  ... 
doi:10.12783/dtetr/icmeit2018/23448 fatcat:rtg4rruaa5ce3c7e43g6vcqhzi

Neural Approaches to Short-Time Load Forecasting in Power Systems—A Comparative Study

Stanislaw Osowski, Robert Szmurlo, Krzysztof Siwek, Tomasz Ciechulski
2022 Energies  
The purpose of the paper is to propose different arrangements of neural networks for short-time 24-h load forecasting in Power Systems.  ...  The novelty of the paper is the critical comparative analysis of the time series prediction methods applied for load forecasting in the power system.  ...  The accurate hourly electric load forecasting allows the power operators to adjust the electric supply according to the real-time forecasted load and in this way provides the normal operation of electric  ... 
doi:10.3390/en15093265 fatcat:pz4zbvgrfrctxg7kec4l43vlq4
« Previous Showing results 1 — 15 out of 1,450 results