Wyniki wyszukiwania - BazTech

1

Grid Search of Convolutional Neural Network model in the case of load forecasting

Tran Thanh Ngoc

Archives of Electrical Engineering

|

2021

|

Vol. 70, nr 1

25--36

EN

The Convolutional Neural Network (CNN) model is one of the most effective models for load forecasting with hyperparameters which can be used not only to determine the CNN structure and but also to train the CNN model. This paper proposes a frame work for Grid Search hyperparameters of the CNN model. In a training process, the optimalmodels will specify conditions that satisfy requirement for minimum of accuracy scoresof Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE) and Mean Absolute Error (MAE). In the testing process, these optimal models will be used to evaluate the results along with all other ones. The results indicated that the optimal models have accuracy scores near the minimum values. Load demand data of Queensland (Australia) and Ho Chi Minh City (Vietnam) were utilized to verify the accuracy and reliability of the Grid Search framework.

2

Shallow, Deep, Ensemble models for Network Device Workload Forecasting

Liu Cenru

Annals of Computer Science and Information Systems

|

2020

|

Vol. 21

101--104

EN

Reliable prediction of workload-related characteristics of monitored devices is important and helpful for management of infrastructure capacity. This paper presents 3 machine learning models (shallow, deep, ensemble) with different complexity for network device workload forecasting. The performance of these models have been compared using the data provided in FedCSIS'20 Challenge. The R2 scores achieved from the cascade Support Vector Regression (SVR) based shallow model, Long short-term memory (LSTM) based deep model, and hierarchical linear weighted ensemble model are 0.2506, 0.2831, and 0.3059, respectively, and was ranked 3rd place in the preliminary stage of the challenges.

3

Dynamic Rating of 110 kV Overhead Lines

Babś A., Samotyjak T.

Acta Energetica

|

2016

|

nr 3

4--9

EN

The paper justifies the need of using, within the 110 kV networks, a dynamic line rating model along the power lines. The work describes in detail the way in which the dynamic line rating is determined, basing the process solely on measurement of the weather conditions. Some aspects related to selection of the numerical values of the coefficients present in the heat model of the power-lines, which is being used to determine the dynamic line rating and the distance between the ground and the conductor, have been described. Subsequent stages of implementation of the system used to determine the dynamic line rating of the power lines have also been described. These include selection of the critical spans of the overhead lines, in case of which risk of exceeding the distance to the crossed-over objects is higher than in case the of the other spans of the very same power line. Additionally, optimal displacement of the weather-reporting stations, that are the source of the data used to determine the dynamic line rating of the lines, has been described. The work also deals with applications of the dynamic line rating for the power line related to the dangerous situation in case of which rime (ice) would be accumulated on the conductors. The forecasting procedures, regarding the load imposed on the power-lines, within a defined time period are also considered by the present paper. Forecasting the permissible load for the power lines is one of the main elements of planning an energy transmission system. Conclusions have been drawn regarding selection of the methodology which is to be used to determine the dynamic line rating, and the way of implementing and using these conclusions within the scope of maintaining the electric energy network.

PL

W artykule uzasadniono celowość i potrzebę wykorzystywania w prowadzeniu ruchu sieci 110 kV dynamicznej obciążalności linii. Szczegółowo opisano wyznaczanie dynamicznej obciążalności linii z wykorzystaniem wyłącznie pomiaru warunków pogodowych. Opisano niektóre aspekty doboru wartości liczbowych współczynników występujących w modelu cieplnym linii, wykorzystywanym do wyznaczania dynamicznej obciążalności linii oraz odległości przewodu od ziemi. Opisano kolejne etapy wdrożenia systemu wyznaczania dynamicznej obciążalności linii, związane m.in. z wyborem przęseł krytycznych, tj. przęseł, w których ryzyko przekroczenia minimalnej odległości od obiektów krzyżowanych jest większe niż w przypadku innych przęseł tej samej linii, oraz optymalnym rozmieszczeniem stacji pogodowych będących źródłem danych dla wyznaczania dynamicznej obciążalności linii. Opisano również inne zastosowania wyznaczania dynamicznej obciążalności linii związane z monitorowaniem jej zagrożenia wystąpieniem oblodzenia (szadzi) oraz prognozowania obciążenia linii w określonym horyzoncie czasowym. Prognozowanie dopuszczalnego obciążania linii jest jednym z elementów planowania pracy systemu elektroenergetycznego. Sformułowano wnioski co do wyboru metody wyznaczania dynamicznej obciążalności linii oraz sposobu wdrożenia i wykorzystania w prowadzeniu ruchu sieci elektroenergetycznej.

4

Short Term Electricity Demand Forecasting of an Isolated Area using Two Different Approach

Islam A., Hasib S. R., Islam M. S.

Journal of Power Technologies

|

2013

|

Vol. 93, nr 4

185--193

EN

Electricity demand forecasting of an off-grid area, where no previous load data is available, is an important prerequisite for power system expansion planning. Bangladesh is a small as well as densely populated country in South Asia with a large portion of the population living under poverty line. About 48.5% of the total population has access in grid electricity. Uninterruptable power supply is one of the most important parameter for future development which ends up with a decision of obvious expansion of present grid coverage. This paper represents an analysis to forecast the electricity demand of an isolated island in Bangladesh where past history of electrical load demand is not available. The analysis is based on the identification of factors on which electrical load growth of an area depends. The forecasting has been done through inverse matrix calculation and linear regression analysis method. It has been found that the demand data, calculated from two different approaches, are close enough which spans the reliability of the proposed method. This method can be applicable for short term load forecasting of any isolated area throughout the world.

5

Prediction Intervals for Short-Term Load Forecasting Neuro-Fuzzy Models

Bartkiewicz W.

Przegląd Elektrotechniczny

|

2012

|

R. 88, nr 10b

284-287

EN

In the paper the problem of estimation of the prediction intervals (error bars) for the family neuro-fuzzy Short-Term Load Forecasting (STLF) models is discussed. We investigate two neuro-fuzzy networks: Fuzzy Basis Function (FBF) Networks, and linear neuro-fuzzy model with Tagagi-Sugeno reasoning. The paper contains comparison of selected most important methods for error bars calculation (analytical delta method, and bootstrap), and discusses the obtained results in context STLF.

PL

W artykule zaprezentowane zostały metody wyznaczania przedziałów prognozy dla rodziny neuronowo rozmytych modeli krótkoterminowego prognozowania obciążenia sieci. Przebadane zostały dwa rodzaje sieci neuronowo-rozmytych: sieci Fuzzy Basis Function (FBF) i liniowe neuronowe modele rozmyte z wnioskowaniem typu Takagi-Sugeno. Artykuł obejmuje porównanie najistotniejszych metod szacowania przedziałów prognozy: analitycznej metody delta i bootstrapu), dyskutując wyniki w kontekście krótkoterminowych prognoz obciążenia sieci.

6

Prognozowanie obciążeń w sieciach nn w aspekcie poprawy efektywności energetycznej

Sulkowski M. A., Naruszewicz D.

Wiadomości Elektrotechniczne

|

2011

|

R. 79, nr 3

7-10

PL

Przedstawiono wyniki poprawy efektywności energetycznej odbiorników energii elektrycznej oraz jej wpływ na prognozowanie obciążeń sieci nn.

EN

The paper presents results of improvement of efficiency of energy consumers and its influence on forecasting ofload in LV network.

7

Ensemble neural network approach for accurate load forecasting in a power system

Siwek K., Osowski S., Szupiluk R.

International Journal of Applied Mathematics and Computer Science

|

2009

|

Vol. 19, no 2

303-315

EN

The paper presents an improved method for 1-24 hours load forecasting in the power system, integrating and combining different neural forecasting results by an ensemble system. We will integrate the results of partial predictions made by three solutions, out of which one relies on a multilayer perceptron and two others on self-organizing networks of the competitive type. As the expert system we will apply different integration methods: simple averaging, SVD based weighted averaging, principal component analysis and blind source separation. The results of numerical experiments, concerning forecasting the hourly load for the next 24 hours of the Polish power system, will be presented and discussed. We will compare the performance of different ensemble methods on the basis of the mean absolute percentage error, mean squared error and maximum percentage error. They show a significant improvement of the proposed ensemble method in comparison to the individual results of prediction. The comparison of our work with the results of other papers for the same data proves the superiority of our approach.