Wyniki wyszukiwania - BazTech

1

Simulation analysis of artificial neural network and XGBoost algorithms in time series forecasting

Sroka Łukasz

Zeszyty Naukowe. Organizacja i Zarządzanie / Politechnika Śląska

|

2024

|

z. 195

561--575

EN

Purpose: The aim of the article was to prepare a simulation analysis of artificial neural network and XGBoost algorithm with determining which of the method was characterized by a lower level of forecast errors for time series predictions. Design/methodology/approach: The objective of the article was reached by applying, a simulation study on a sample of 1000 artificially generated time series. The analyzed XGBoost algorithm and the artificial neural network ANN model were intended to prepare forecasts for five periods ahead. These forecasts were compared with the actual implementations of the time series and proposed forecast error measures. Findings: It is possible to use simulated time series to check which of the presented algorithms were characterized by a lower forecast error. The study showed that applying of the artificial neural networks ANN to forecast future observations generated a lower level of MAPE, MAE and RMSE errors than in the case of the XGBoost algorithm. It was found that both methods generate a lower level of forecast error for time series characterized by a high level of mean value, standard deviation and variance, and levels of kurtosis and skewness close to 0. Practical implications: The research results can be used by both investors and enterprises to better adjust their business decisions to changing market prices by using a model with a lower forecast bias. Originality/value: The original contribution of this article is a comprehensive comparison of forecasts generated by the XGBoost and ANN algorithm, along with determining for which types of time series of the algorithms forecast future values with less error. Moreover, due to the use of simulated artificial time series, it was possible to test each algorithm for various market conditions.

2

Przegląd obecnie istniejących instalacji LNG na świecie, aspekty techniczne pojedynczej stacji oraz prognozowanie zużycia gazu. Część 2 - obliczenia

Cieślik Tomasz, Narloch Piotr, Żero Andrzej

Gaz, Woda i Technika Sanitarna

|

2024

|

Nr 2

2--7

PL

Jednym z warunków prawidłowego zarządzania pracą sieci wyspowej zasilanej z stacji regazyfikacji LNG jest planowanie dostaw opartych o prognozy zużycia. Na podstawie zgromadzonych danych atmosferycznych oraz zużycia gazu z wybranej stacji na przestrzeni dwóch lat określono wpływ czynników atmosferycznych na konsumpcję gazu ziemnego za pomocą sztucznych sieci neuronowych. Wyznaczono wpływ miesiąca oraz dnia (parametr sztuczny) na konsumpcję gazu. Wyznaczono model sieci neuronowych dający najlepsze dopasowania za pomocą współczynnika korelacji.

EN

One of the conditions for proper management of the islanded network supplied by LNG regasification stations is planning deliveries based on consumption forecasts. Based on collected meteorological data and gas consumption from a selected station over a two-year period, the impact of atmospheric factors on natural gas consumption was determined using artificial neural networks. The influence of the month and day (artificial parameter) on gas consumption was identified. A neural network model was developed to achieve the best fits using correlation coefficients.

3

Daily air temperature forecasting using LSTM-CNN and GRU-CNN models

Uluocak Ihsan, Bilgili Mehmet

Acta Geophysica

|

2024

|

Vol. 72, no. 3

2107--2126

EN

Today, air temperature (AT) is the most critical climatic indicator. This indicator accurately defines global warming and climate change, despite the fact that it has effects on different things, including the environment, hydrology, agriculture, and irrigation. Accurate and timely AT forecasting is crucial since it supplies more significant details that can create credibility for future planning. This study proposes innovative hybrid models that integrate a convolutional neural network (CNN) with a long short-term memory (LSTM) neural network and a gated recurrent unit (GRU) to perform one-day ahead AT predictions. For this purpose, the daily AT data obtained from 2012 to 2019 at the Adana and Ankara meteorological stations over Türkiye under Continental and Mediterranean climate conditions are used. The hybrid GRU-CNN and LSTM-CNN models are compared with various traditional statistical and machine-learning models such as feed-forward neural network, adaptive neuro-fuzzy inference system, autoregressive moving average, GRU, CNN, and LSTM. The success of the prediction models is evaluated utilizing various statistical criteria (MAE, RMSE, NSE, and R2) and visual comparisons. The results show that the proposed hybrid GRU-CNN and LSTM-CNN models in one day-ahead AT predictions yield the best results among all models with high accuracy.

4

Autoregressive conditional duration modeling and forecasting the earthquakes temporal data of the different regions of Pakistan

Khan Muhammad Yousaf, Mittnik Stefan, Tahir Mohammad, Shah Muhammad Ali, Iqbal Talat

Acta Geophysica

|

2024

|

Vol. 72, no. 3

1543--1559

EN

Pakistan is situated in an earthquake-prone area, and in the past, many destructive earthquakes have occurred including the most destructive 1935 Quetta, and 2005 Kashmir, earthquakes. Therefore, it is of vital importance to investigate the statistical properties of the earthquake temporal data of Pakistan. The present study brings novelty through the vast extension of the linear and nonlinear autoregressive conditional duration models in the field of seismology. A simple duration model capable of describing and forecasting the earthquake elapsed times data has been developed. Different specifications of the duration models were considered to completely extract the time-dependent structure in earthquake data. This study aims to identify the most suitable in-sample fitted and out-of-sample forecasting models for the earthquake elapsed times data of Pakistan. A variety of autoregressive conditional duration models were applied to the complete and updated earthquake catalog of Pakistan. The most suitable model was chosen through statistical model evaluation techniques. The method of maximum likelihood was used to estimate the model parameters. The adequacy of fitted models is assessed through residual analysis. The obtained results suggest that the Logarithmic Autoregressive Conditional Duration model of type 2 (LACD2) appeared as the most suitable in-sample fitted model for describing the earthquake temporal data of the different zones of Pakistan. Further, the simple autoregressive conditional duration (ACD) model outperforms the remaining considered models regarding 1-through-4 steps-ahead out-of-sample forecasting performance for both India-Eurasia collision (IEC) and Makran subduction (MS) zones. Autoregressive models with Burr and exponential distributions as assumed error distributions have appeared as the most suitable fitted models for IEC and MS zones, respectively. The residuals analysis results show that the most suitable fitted models are correctly identified. The results show that the earthquake short-term (h = 1) forecasting with duration models is more accurate in comparison with earthquake long-term (h = 1, 2, 3) forecasting. The forecasted elapsed times for IEC and MS zones are 0.60 and 2.94 years, respectively. The obtained results show that the autoregressive conditional models are a more useful tool for forecasting the earthquake elapsed times for short term in comparison with the long-term forecasting. Hence, autoregressive conditional models are capable of modeling and forecasting the earthquake temporal data of the different regions of Pakistan. Among the competing models, the best fit model can serve the purpose of data description, missing value estimation in earthquake catalogs and uncertainty quantification in the earthquake occurrence process. The most suitable forecasted model yields the future earthquake occurrence trend in the study region.

5

The use of neural networks to forecast the number of road accidents in Poland

Gorzelańczyk Piotr

Zeszyty Naukowe. Transport / Politechnika Śląska

|

2023

|

z. 118

45--54

EN

Every year, a large number of traffic accidents occur on Polish roads. However, the pandemic of recent years has reduced the number of these accidents, although the number is still very high. For this reason, all measures should be taken to reduce this number. This article aims to forecast the number of road accidents in Poland. Thus, using Statistica software, the annual data on the number of road accidents in Poland were analyzed. Based on actual past data, a forecast was made for the future, for the period 2022-2040. Forecasting the number of accidents in Poland was conducted using selected neural network models. The results show that a reduction in the number of traffic accidents is likely. The choice of the number of random samples (learning, testing and validation) affects the results obtained.

6

Application of the creeping trend model for forecasting of accident events in the steel industry in Poland

Małysa Tomasz

Zeszyty Naukowe. Organizacja i Zarządzanie / Politechnika Śląska

|

2023

|

z. 170

313--324

EN

Purpose: The aim of the study to assess the possibility of using the creeping trend model in the forecasting of accidents at work in the steel sector in Poland, was presented. Design/methodology/approach: A four-stage research methodology was used to analyze the accident rate trend in the steel sector, based on: collecting empirical data, forecasting (creeping trend model), qualitative assessment of forecasts and determining the direction of activities in the field of health and safety. Findings: Based on the conducted research, it was found that it is possible to use the creeping trend model in forecasting the number of persons injured in accidents at work. The forecasts and their acceptance based on the criteria adopted in the methodology of own work made it possible to determine the directions of activities in the field of occupational health and safety in the steel sector in Poland. Research limitation/implications: The conducted analyses were limited to statistical data published by Statistic Poland. Forecasts of the number of persons injured in accidents in the steel sector were possible to determine thanks to the forecasting process using the creeping trend model. The forecasts are subject to errors, which is why it is important to interpret them more broadly, taking into account the specificity of the industry being the subject of the analyses. Practical implications: The forecasts can be important information on health and safety issues for the steel sector in Poland. The use of the creeping trend model, with the fulfillment of methodological assumptions (qualitative ocean of forecasts), can be useful in determining the direction of OSH activities in enterprises. Social implications: The article addresses the issue of the occurrence of accidents at work, the implementation of effective preventive measures in order to reduce them. Originality/value: The article presents the possibility of using the creeping trend model in the forecasting of the total number of persons injured in accidents in the steel sector in Poland. The forecasts and trend analysis can provide information for employers and employees of health and safety services regarding the effectiveness of the implemented preventive measures.

7

Wykorzystanie metod obliczeniowych i sztucznej inteligencji w bezpieczeństwie energetycznym

Morkisz Paweł, Wiącek Martyna, Wochlik Ireneusz

Wiedza Obronna

|

2023

|

nr 2

PL

Możliwości zastosowania sztucznej inteligencji w sektorze energetycznym są dziś szerokie. Ogromna ilość danych przechodzących przez ten sektor stwarza potrzebę wdrażania automatycznej, inteligentnej analizy oraz potencjał rozwoju tych technologii. Chcąc zapewnić bezpieczeństwo energetyczne rozumiane jako zapewnienie ciągłości dostaw energii i paliw, należy mieć pełną kontrolę nad ich dystrybucją i możliwymi zagrożeniami. Korzyści płynące z kontroli nad danymi, prognozowania kluczowych w tym sektorze wartości czy optymalizacji działań i operacji na sieci są nieocenione. Celem niniejszego artykułu jest przegląd konkretnych obszarów energetyki, w których metody obliczeniowe i sztuczna inteligencja mają największy potencjał. Ponadto, wskazanie konkretnych metod, które sprawdzone w innych sektorach lub zbadane w nauce mają zastosowanie również tutaj.

EN

The possibilities for using artificial intelligence in the energy sector are vast today. The massive amount of data passing through this sector creates the need to implement automatic, intelligent analysis and the potential for developing these technologies. In order to ensure energy security, understood as ensuring the continuity of energy and fuel supplies, it is necessary to have complete control over their distribution and possible threats. The benefits of controlling data, forecasting critical values in this sector, or optimizing activities and operations on the network are invaluable. The purpose of this article is to review specific areas of the energy sector where computational methods and artificial intelligence have the most significant potential. In addition, specific methods that have been proven in other sectors or studied in science are indicated to apply here.

8

Problems of forecasting the length of the assembly cycle of complex products realized in the MTO (make-to-order) model

Brzozowska Jolanta, Gola Arkadiusz, Kulisz Monika

Technologia i Automatyzacja Montażu

|

2023

|

nr 3

13--20

EN

This article presents the problem of forecasting the length of machine assembly cycles in make-to-order production (Make-to-Order). The model of Make-to-Order production and the technological process of manufacturing the finished product are presented. The possibility of developing a novel method, using artificial intelligence solutions, to estimate machine assembly times based on historical company data on manufacturing times for structurally similar components, is described. It is assumed that the result of the developed method will be an intelligent system supporting efficient and accurate estimation of machine assembly time, ready for implementation in production conditions. Such data as part availability, human resource availability and novelty factor will be used as input data for learning the neural network, while the output variable during learning the neural network will be the actual machine assembly time.

PL

W niniejszym artykule przedstawiono problem prognozowania długości cyklu montażu maszyn w produkcji na zamówienie (Make-to-Order). Przedstawiony został model produkcji na zamówienie oraz proces technologiczny wytwarzania wyrobu gotowego. Opisana została możliwość opracowania nowatorskiej metody, wykorzystującej rozwiązania z zakresu sztucznej inteligencji, umożliwiającej szacowanie czasu montażu maszyn w oparciu o dane historyczne przedsiębiorstw, dotyczące czasów wytwarzania podobnych konstrukcyjnie elementów. Zakłada się, iż rezultatem opracowanej metody będzie inteligentny system wspomagający skuteczne i dokładne szacowanie czasu montażu maszyn, gotowy do implementacji w warunkach produkcyjnych. Jako dane wejściowe do uczenia sieci neuronowej wykorzystane zostaną takie dane jak: dostępność części, dostępność zasobów ludzkich oraz czynnik nowości, zaś zmienną wyjściową podczas uczenia sieci neuronowej będzie rzeczywisty czas montażu maszyny.

9

Impact of information on the number of traffic accidents on the outcome of the forecast

Gorzelańczyk Piotr

Technical Sciences / University of Warmia and Mazury in Olsztyn

|

2023

|

nr 26(1)

219--230

EN

Every year, more and more vehicles appear on the world's roads. This leads to increased traffic on the roads. Road accidents have become a rapidly growing threat. They cause loss of human life and economic assets. This is due to the rapid growth of the world's human population and the very rapid development of motorization. The main problem in forecasting and analyzing data on the number of traffic accidents is the small size of the dataset that can be used for analysis in this regard. And on the other hand, road accidents cause, globally, millions of deaths and injuries annually is their density in time and space. It is worth noting that the pandemic has reduced the number of traffic accidents. However, the value is still very high. The purpose of the article is to assess the impact of information on the number of traffic accidents on the outcome of the forecast. To this end, using historical statistical data, the forecast of the number of traffic accidents for the following years was determined, and how this variability of the input data affects the value of the average percentage error of the forecast was determined. Based on the study, it can be concluded that a smaller number of input data, historical data on the number of accidents, instead of 32 years, 7 years, makes the determination of the forecast of the number of accidents for subsequent years, is at a satisfactory level, the average absolute percentage error of MAPE less than 7%. The article concludes with the determination of the forecast for future years. It is worth noting that the prevailing pandemic distorts the results obtained.

10

Forecasting the number of road accidents in Poland using weather-dependent trend models

Gorzelańczyk Piotr

Technical Sciences / University of Warmia and Mazury in Olsztyn

|

2023

|

nr 26(1)

57--76

EN

Every year a very large number of people die on the roads. From year to year, the value decreases, there are still a very high number of them. The pandemic has reduced the number of road accidents, but the value is still very high. For this reason, it is necessary to know under which weather conditions the highest number of road accidents occur, and to know the forecast of accidents according to the prevailing weather conditions for the coming years, in order to be able to do everything possible to minimize the number of road accidents. The purpose of the article is to make a forecast of the number of road accidents in Poland depending on the prevailing weather conditions. The research was divided into two parts. The first was the analysis of annual data from the Police statistics on the number of road accidents in Poland in 2001-2021, and on this basis the forecast of the number of road accidents for 2022-2031 was determined. The second part of the research, dealt with monthly data from 2007-2021. Again, the analyzed forecast for the period January 2022-December 2023 was determined. The results of the study indicate that we can still expect a decline in the number of accidents in the coming years, which is particularly evident when analyzing annual data. It is worth noting that the prevailing pandemic distorts the results obtained. The research was conducted in MS Excel, using selected trend models.

11

The use of quantitative methods as measures for forecast electricity demand on the local market in a short time horizon

Niekurzak Mariusz

Przegląd Elektrotechniczny

|

2023

|

R. 99, nr 3

86--93

EN

The article builds a model of an hourly system for short-term forecasting of electricity demand on the local market of the Krakow area in 2019-2022. Including quantitative methods. The time series representing the hourly system-wide electricity demand was decomposed. A comprehensive statistical analysis of the data was performed in order to select the best optimization method used to select the optimal coefficients of the developed method of estimating the quality of forecasts. In addition, the results of numerical experiments aimed at determining the impact of the y parameter value on the quality of forecasts for various forecast horizons were presented, and the relationships between the number of historical data and the quality of forecasts were established. Due to the periodic nature of the examined time series, a detailed analysis of seasonality and periodicity of a given signal was carried out using spectral analysis and autocorrelation. This analysis allowed the author create an effective tool for accurate local electricity demand forecasting in the time horizon "an hour before delivery". On the basis of data from the distribution company, the built system was verified. An analysis of profits and losses after applying the selected forecasting model was made. The proposed concept of the model is an effective analytical tool of the analyzed problem, which will make it easier for operators of energy companies to effectively support their decisions in forecasting electricity demand.

PL

W artykule zbudowano model godzinowego systemu do krótkoterminowego prognozowania zapotrzebowania na energię elektryczną na lokalnym rynku obszaru Krakowa w latach 2019-2022. Z wykorzystaniem metod ilościowych dokonano dekompozycji szeregu czasowego reprezentującego godzinowe ogólnosystemowe zapotrzebowanie na energię elektryczną. Wykonano wszechstronną analizę statystyczną danych w celu wyboru najlepszej metody optymalizacyjnej służącej do doboru optymalnych współczynników opracowanej metody szacowania jakości prognoz. Dodatkowo zaprezentowano wyniki eksperymentów numerycznych mających na celu ustalenie wpływu wartości parametru y na jakość prognoz dla różnych horyzontów prognoz oraz ustalono związki między liczbą danych historycznych a jakością prognoz. Ze względu na okresowy charakter badanego szeregu czasowego została przeprowadzona szczegółowa analiza sezonowości oraz okresowości danego sygnału przy pomocy analizy spektralnej oraz autokorelacji. Analiza ta pozwoliła autorowi stworzyć skuteczne narzędzie do dokładnego lokalnego prognozowania zapotrzebowania na energię elektryczną w horyzoncie czasowym „godzina przed dostawą”. Na podstawie danych ze spółki dystrybucyjnej dokonano weryfikacji zbudowanego systemu. Dokonana została analiza zysków i strat po zastosowaniu wybranego modelu prognostycznego. Zaproponowany koncepcja modelu jest skutecznym narzędziem analitycznym analizowanego problemu, które ułatwi operatorom spółek energetycznych, skuteczne wspomaganie podejmowanych decyzji w prognozowaniu zapotrzebowania na energię elektryczną.

12

Deep learning technique for forecasting solar radiation and wind speed for dynamic microgrid analysis

Islam Md Mainul, Shareef Hussain, Al Hassan Eslam Salah Fayez

Przegląd Elektrotechniczny

|

2023

|

R. 99, nr 4

162--170

EN

The key variables in the development and operation of wind and solar power systems are wind speed and solar radiation. The prediction of solar and wind energy parameters is important to alleviate the effects of power generation fluctuations. Consequently, it is essential to predict renewable energy sources like solar radiation and wind speed precisely. An artificial intelligence-based random forest method is recommended in this paper to estimate wind speed and solar radiation. The number of decision trees in the random forest model is suggested to be optimised using a novel coot algorithm (CA), and the effectiveness of the CA is evaluated to that of the currently used particle swarm optimisation (PSO) method. The best forecasting data are used in this work to develop a dynamic Microgrid (MG) in MATLAB/SIMULINK. A novel binary CA is proposed to control the MG to minimize the cost. The effect of the energy storage system is also investigated during the simulation of the MG.

PL

Kluczowymi zmiennymi w rozwoju i działaniu systemów energii wiatrowej i słonecznej są prędkość wiatru i promieniowanie słoneczne. Prognozowanie parametrów energii słonecznej i wiatrowej jest ważne dla złagodzenia skutków wahań produkcji energii. W związku z tym niezbędne jest precyzyjne przewidywanie źródeł energii odnawialnej, takich jak promieniowanie słoneczne i prędkość wiatru. W tym artykule zaleca się metodę lasów losowych opartą na sztucznej inteligencji w celu oszacowania prędkości wiatru i promieniowania słonecznego. Sugeruje się optymalizację liczby drzew decyzyjnych w modelu losowego lasu przy użyciu nowego algorytmu łyski (CA), a skuteczność CA jest oceniana na podstawie obecnie stosowanej metody optymalizacji roju cząstek (PSO). W tej pracy wykorzystano najlepsze dane prognostyczne do opracowania dynamicznej mikrosieci (MG) w MATLAB/SIMULINK. Proponuje się nowy binarny CA do sterowania MG w celu zminimalizowania kosztów. Wpływ systemu magazynowania energii jest również badany podczas symulacji MG.

13

Shallot Price Forecasting Models: Comparison among Various Techniques

Kasemset Chompoonoot, Phuruan Kanokrot, Opassuwan Takron

Production Engineering Archives

|

2023

|

Vol. 29, Iss. 4

348-355

EN

Shallot is one of several horticultural products exported from Thailand to various countries. Despite an increase in shallot prices over the years, farmers face challenges in price forecasting due to fluctuations and other relevant factors. While different forecasting techniques exist in the literature, there is no universal approach due to varying problems and datasets. This study focuses on predicting shallot prices in Northern Thailand from January 2014 to December 2020. Traditional and machine learning models, including ARIMA, Holt-Winters, LSTM, and ARIMA-LSTM hybrids, are proposed. The LSTM model considers temperature and rainfall as influencing factors. Evaluation metrics include RMSE, MAE, and MAPE. Results indicate that the ARIMA-LSTM hybrid model performs best, with RMSE, MAE, and MAPE values of 10.275 Baht, 8.512 Baht, and 13.618%, respectively. Implementing this hybrid model can provide shallot farmers with advanced price information for informed decision-making regarding cultivation expansion and production management.

14

Visual solutions as a way to improve work safety when using machines – selected aspects of VM

Małysa Tomasz, Furman Joanna

Management Systems in Production Engineering

|

2023

|

nr 1 (31)

53--58

EN

The issue of ensuring work safety during the use of machines plays a key role due to the recorded accident events, the source of which are the machines in use. In the scope of reducing the risk associated with machines, particular attention should be paid to the threats, as well as solutions allowing to limit their negative impact on the operator. The study presents the possibility of using visual management (VM) as a form of information transfer that allows to meet the requirements set out in legal regulations, as well as reduce the risk of accidents. The machines in question were assessed for the possibility of using various forms of visual management to reduce the risk of accidents. The investigations were also supplemented with an analysis of accident statistics to present the importance of using visual management in improving the safety of machine operators' work. The conducted analyzes allowed to determine the direction of activities in the use of various forms of visual management aimed at improving the safety of machine operators.

15

Post-pandemic steel production scenarios for Poland based on forecasts of annual steel production volume

Gajdzik Bożena

Management Systems in Production Engineering

|

2023

|

nr 2 (31)

172--190

EN

The paper presents the results of forecasts made for the volume of steel production in Poland based on actual data for the period from 2006 to 2021 with forecasting until 2026. The actual data used for the forecasts included annual steel production volumes in Poland (crude steel) in millions of tons. Basic adaptive methods were used to forecast the volume of steel production for the next five years. When selecting the methods, the course of the trend of the studied phenomenon was taken into account. In order to estimate the level of admissibility of the adopted forecasting methods, as well as to select the best forecasts, the errors of apparent forecasts (ex post) were calculated. Errors were calculated in the work: RMSE Root Mean Square Error being the square root of the mean square error of the ex-post forecasts yt for the period 2006-2021; as the mean value of the relative error of expired forecasts y*t (2006-2021) – this error informs about the part of the absolute error per unit of the real value of the variable yt. Optimization of the forecast values was based on the search for the minimum value of one of the above-mentioned errors, treated as an optimization criterion. In addition, the value of the point forecast (for 2022) obtained on the basis of the models used was compared with the steel production volume obtained for 3 quarters of 2022 in Poland with the forecast for the last quarter. Forecasting results obtained on the basis of the forecasting methods used, taking into account the permissible forecast errors, were considered as the basis for determining steel production scenarios for Poland until 2026. To determine the scenarios, forecast aggregation was used, and so the central forecasts were determined separately for decreasing trends and for increasing trends, based on the average values of the forecasts obtained for the period 2022-2026. The central forecasts were considered the baseline scenarios for steel production in Poland in 2022-2026 and the projected production volumes above the baseline forecasts with upward trends were considered an optimistic scenario, while the forecasted production volumes below the central scenario for downward trends were considered a pessimistic scenario for the Polish steel industry.

16

Wiarygodne prognozy kluczem do usprawnienia realizacji zamówień

Guzanek Patrycja, Sobecki Grzegorz, Bawoł Piotr, Borucka Anna

Gospodarka Materiałowa i Logistyka

|

2023

|

nr 1

31--39

PL

Celem artykułu jest wskazanie różnic między ogólnodostępnym narzędziem prognozującym wykorzystywanym w planowaniu dostaw a dedykowanym, stworzonym specjalnie dla danej firmy. Autorzy na podstawie przeprowadzonych badań ukazują różnice w działalności sieci sklepów, prognozowaniu dostaw i ich wartości z użyciem dwóch różnych systemów wspomagających prognozowanie sprzedaży produktów. Przyjęto hipotezę badawczą, że wiarygodne prognozy są kluczowe w usprawnianiu realizacji zamówień i stanowią istotny czynnik wpływający na satysfakcję klienta oraz zdobywanie przewagi konkurencyjnej.

EN

The aim of the article is to indicate the difference between a publicly available forecasting indicator used in supplier planning and one created specifically for a given company. The authors based on the results of comparative research in the operation of chain stores, forecasting deliveries and their value with the use of various systems supporting the forecasting of product supply. A research hypothesis was adopted that reliable forecasts are crucial in improving order fulfillment and are an important factor influencing customer satisfaction and gaining a competitive advantage.

17

Intelligent Design Suggestion and Sales Forecasting for New Products in the Apparel Industry

Tsao Yu-Chung, Liu Yu-Hsuan, Vu Thuy-Linh, Fang I-Wen

Fibres & Textiles in Eastern Europe

|

2023

|

Vol. 31, no. 6

30--38

EN

This study demonstrates how algorithms can assist humans in decision-making in the apparel industry. A two-stage method including suggestions and intelligent forecasting was proposed. In the first stage, a web crawler was used to browse a B2C apparel website to identify popular products. In the second stage, machine learning methods were used to predict the sales demand for new products. Additionally, we used Google Trends to collect external information indices to adjust the demand forecasting. Our numerical study shows that the intelligent forecasting approach can effectively reduce the Mean Square Error (MSE), Root Mean Square Error (RMSE), and Mean Absolute Percentage Error (MAPE) by at least 45.79, 26.35, and 26.34 %, respectively.

18

Forecasting the development of electricity from renewable energy sources in Poland against the background of the European Union countries

Firlej Krzysztof Adam, Stanuch Marcin

Ekonomia i Środowisko

|

2023

|

nr 1

30--50

EN

One of the key elements in the development of countries is energy stability particularly related to ensuring, among other things, continuity of power supply. The European Commission is trying to protect the security of energy supply by introducing internal conditions regarding the share of RES in everyday life. The aim of this article is to forecast the share of RES in electricity production for all the EU member states. The study covers the years 1985-2021, the research is based on two models: the autoregressive (AR) model and the Holt-Winters model, whereas the prediction values were deter-mined for the period 2022-2030. The prediction values showed that Denmark, as the only one of the community countries, may turn out to be self-sufficient in terms of electricity production from RES already at the turn of 2026-2027. In the case of Poland, there is a high probability that the projected RES share for 2030 will not be met. Potentially, for most EU countries, the energy produced from RES will satisfy at least 50% of electricity demand by 2030. A projection of the chances of meeting the commitments presented in the National Energy and Climate Plans regarding the share of renewable energy sources in electricity production in the EU member states in 2030 indicates that they will not be met in most EU economies.

PL

Jednym z kluczowych elementów rozwoju krajów jest stabilność energetyczna szczególnie związana z zapewnieniem ciągłości zasilania, m.in. w energię elektryczną. Komisja Europejska próbuje uchronić bezpieczeństwo dostaw energii wprowadzając wewnętrzne uwarunkowania dotyczące udziału OZE w życiu codziennym. Celem artykułu była prognoza udziału OZE w produkcji energii elektrycznej dla wszystkich krajów członkowskich Unii Europejskiej. Badanie przeprowadzono analizując lata 1985-2021, gdzie badania oparto o dwa modele: autoregresyjny (AR) oraz model Holta-Wintersa, a wartości predykcji zostały wyznaczone dla okresu 2022-2030. Wartości prognoz wykazały, że Dania jako jedyny z krajów wspólnoty już na przełomie 2026-2027 może okazać się państwem samowystarczalnym pod względem produkcji energii elektrycznej z OZE. W przypadku Polski istnieje duże prawdopodobieństwo niespełnienia oczekiwań udziału OZE w planowanym udziale na rok 2030. Potencjalnie, dla większości krajów UE energia produkowana z OZE dla 2030 r. będzie zaspokajać przynajmniej 50% zapotrzebowania na energię elektryczną. Prognoza dotycząca szans realizacji przedstawionych w krajowych planach na rzecz energii i klimatu zobowiązań dotyczących udziału odnawialnych źródeł energii w produkcji energii elektrycznej w krajach członkowskich Unii Europejskiej w 2030 roku wskazuje, że nie zostaną one spełnione w większości gospodarek unijnych.

19

Application of exponential smoothing method to forecasting daily water consumption in rural areas

Cieżak Wojciech, Kutyłowska Małgorzata

Archives of Civil Engineering

|

2023

|

Vol. 69, nr 3

445--456

EN

The size and distribution of water demand within a given structural unit is the basis for the proper operation and planning of the expansion and modernization of the water supply system’s elements. In rural areas, particularly in municipalities adjacent to urban-industrial agglomerations, a change in the use of tap water has been increasingly observed. The water consumption for animal breeding or agricultural use, typical of these areas, has been decreasing and even disappearing. Water has been increasingly used for domestic purposes in single- and multi-family housing as well as for other purposes such as watering lawns and filling residential swimming pools. Taking this into account, this paper presents observations regarding daily water consumption in a municipality adjacent to Wrocław together with an analysis of the possibility of using the exponential smoothing method for the short-term forecasting of daily water consumption. The analyses presented in this paper were carried out using STATISTICA 13 software.

PL

Wzrost zapotrzebowania na wodę w gminach przyległych do dużych aglomeracji, a co za tym idzie wzrost produkcji wody, zmuszają przedsiębiorstwa wodociągowe do szukania nowych rozwiązań dotyczących między innymi optymalnego sterowania takimi procesami jak: ujmowanie i rozdział dyspozycyjnych zasobów wodnych, dystrybucja oraz oczyszczanie wody i ścieków. Aby zapewnić skuteczne sterowanie tymi procesami wymagany jest między innymi skalibrowany model hydrauliczny sieci dystrybucji i model prognostyczny poboru wody. Do bieżącego i krótkoterminowego prognozowania poboru wody wykorzystywane są modele stochastyczne, wprowadzane w postaci zalgorytmizowanej do struktury zarządzania procesem sterowania. Najczęściej stosowane są scałkowane modele autoregresji i średniej ruchomej ARIMA oraz metody wygładzania wykładniczego szeregów czasowych. Modele klasy ARIMA odwzorowują właściwości statyczne i dynamiczne szeregów stacjonarnych i pewnych klas szeregów niestacjonarnych, interpretowanych jako wynik przejścia białego szumu przez dyskretny filtr liniowy skończenie wymiarowy. Charakteryzują się one różnymi właściwościami przy jednolitym zapisie formalnym oraz identycznych metodach estymacji parametrów dla różnych typów i podklas modeli. Metody prognozowania oparte na algorytmach wygładzania wykładniczego są łatwe do praktycznego zastosowania i nie wymagają założenia o stacjonarności analizowanego szeregu czasowego. W niniejszej pracy przedstawiono obserwacje dotyczące dobowego zużycia wody w jednej z gmin przyległej do Wrocławia wraz z analizą możliwości zastosowania metody wygładzania wykładniczego do krótkoterminowego prognozowania dobowego poboru wody.

20

Impact of econometric modeling and perspectives of economic security of the cross-industry complex

Liezina Anastasiia, Lavruk Alexandr, Matviienko Halyna, Ivanets Iryna, Tseluiko Oleksii, Kuchai Oksana

Acta Innovations

|

2023

|

no. 47

73--83

EN

The paper presents a forecast of the economic security of the inter-industry complex through the construction of a simulation model. The authors considered the possibility of using an econometric model in predicting the level of economic security of the inter-industry complex. The goal was to form a definition of the "inter-industry complex", as well as to study the issues of conceptual and fundamental methods of econometric modeling and forecasting the development of regional industry markets in dynamics. A range of issues related to the main components of economic security in the inter-industry complex has been allocated for scientific work in order to analyze the impact of the components of economic security on the integral indicator. The paper uses a methodology for predicting the structural and spatial-temporal dynamics of interbranch complexes, which includes new and refined methods of modeling and forecasting. As a result, the authors proposed the definition of "inter-industry complex", "economic security in the inter-industry complex", as well as the general provisions of the methodology for econometric modeling and forecasting the level of economic security of the inter-industry complex. The paper presents a full-scale simulation model that allows you to set, evaluate and make a decision using large nonlinear data. This kind of system contains dynamic and retarded data, which makes it possible to apply econometric modeling in automatic calculation.