Tomasz Ciechulski

Dr. Tomasz Ciechulski

orcid

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 May 2021 in Energies
Verified
Journal Article
Open access
PDF file
TCTomasz Ciechulski
Tomasz Ciechulski
SOStanislaw Osowski
Stanislaw Osowski
The paper presents the application of recurrent LSTM neural networks for short-time load forecasting in the Polish Power System (PPS) and a small region of a power system in Central Poland. The objective of the present work was to develop an efficient and accurate method of forecasting the 24-h pattern of power load with a 1-h and 24-h horizon. LSTM showed effectiveness in predicting the irregular trends in time series. The final forecast is estimated using an ensemble consisted of five independent predictions. Numerical experiments proved the superiority of the ensemble above single predictor resulting in a reduction of the MAPE the RMSE error by more than 6% in both forecasting tasks.

4 January 2024 in Energies
Verified
Journal Article
Open access
PDF file
TCTomasz Ciechulski
Tomasz Ciechulski
SOStanislaw Osowski
Stanislaw Osowski
Short-term wind power forecasting has difficult problems due to the very large variety of speeds of the wind, which is a key factor in producing energy. From the point of view of the whole country, an important problem is predicting the total impact of wind power’s contribution to the country’s energy demands for succeeding days. Accordingly, efficient planning of classical power sources may be made for the next day. This paper will investigate this direction of research. Based on historical data, a few neural network predictors will be combined into an ensemble that is responsible for the next day’s wind power generation. The problem is difficult since wind farms are distributed in large regions of the country, where different wind conditions exist. Moreover, the information on wind speed is not available. This paper proposes and compares different structures of an ensemble combined from three neural networks. The best accuracy has been obtained with the application of an MLP combiner. The results of numerical experiments have shown a significant reduction in prediction errors compared to the naïve approach. The improvement in results with this naïve solution is close to two in the one-day-ahead prediction task.

29 April 2022 in Energies
Verified
Journal Article
Open access
PDF file
SOStanislaw Osowski
Stanislaw Osowski
RSRobert Szmurlo
Robert Szmurlo
KSKrzysztof Siwek
Krzysztof Siwek
TCTomasz Ciechulski
Tomasz Ciechulski
Background: The purpose of the paper is to propose different arrangements of neural networks for short-time 24-h load forecasting in Power Systems. Methods: The study discusses and compares different techniques of data processing, applying the feedforward and recurrent neural structures. They include such networks as multilayer perceptron, radial basis function, support vector machine, self-organizing Kohonen networks, deep autoencoder, and recurrent deep LSTM structures. The important point in getting high-quality results is the composition of many solutions in the common ensemble and their fusion to create the final forecast of time series. The paper considers and compares different methods of fusing the individual results into the final forecast, including the averaging, application of independent component analysis, dynamic integration, and wavelet transformation. Results: The numerical experiments have shown a high advantage of using many individual predictors integrated into the ensemble which are responsible for the final forecast. Especially efficient is the application of non-standard wavelet application in the formation of an ensemble, as well as the use of LSTM as the basic prediction unit. 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 presented approach may be useful for the users involved in power system operation management.

23 November 2020 in Energies
Verified
Journal Article
Open access
PDF file
TCTomasz Ciechulski
Tomasz Ciechulski
SOStanislaw Osowski
Stanislaw Osowski
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. The prediction system uses a deep multilayer autoencoder to generate diagnostic features and an ensemble of two neural networks: multilayer perceptron and radial basis function network and support vector machine in regression model, for final 24-h forecast one-week advance. The period of the data that is the subject of the experiments is 2014–2019, which has been divided into two parts: Learning data (2014–2018), and test data (2019). The numerical experiments have shown the advantage of deep learning over classical approaches of neural networks for the problem of power demand prediction.

5 October 2019 in PRZEGLĄD ELEKTROTECHNICZNY
Verified
Journal Article
Closed access
TCTomasz Ciechulski
Tomasz Ciechulski
Wydawnictwo SIGMA-NOT wydaje czasopisma fachowe informuj?ce swoich czytelnik?w o najnowszych osi?gni?ciach naukowych i nowoczesnych rozwi?zaniach technicznych w Polsce i na ?wiecie, popularyzuje problemy techniczne oraz poszerza wiedz? i kultur? techniczn?.

1 January 2018 in PRZEGLĄD ELEKTROTECHNICZNY
Verified
Journal Article
Closed access
TCTomasz Ciechulski
Tomasz Ciechulski
The paper shows the neural method applied for 24-hour load forecasting for the next day in National Power System in Poland. Three neural networks: RBF, MLP and SVM arranged in an ensemble were used for predicting hourly load demands in the power system. Their individual predictions have been integrated into final forecast. The method was tested on the real data of Polish Power System, proving its effectiveness and significant improvement in accuracy.