Development Of Forecasting Model Research Articles

Hybrid Long Short-Term Memory Wavelet Transform Models for Short-Term Electricity Load Forecasting

To ensure the constant availability of electrical energy, power companies must consistently maintain a balance between supply and demand. However, electrical load is influenced by a variety of factors, necessitating the development of robust forecasting models. This study seeks to enhance electricity load forecasting by proposing a hybrid model that combines Sorted Coefficient Wavelet Decomposition with Long Short-Term Memory (LSTM) networks. This approach offers significant advantages in reducing algorithmic complexity and effectively processing patterns within the same class of data. Various models, including Stacked LSTM, Bidirectional Long Short-Term Memory (BiLSTM), Convolutional Neural Network—Long Short-Term Memory (CNN-LSTM), and Convolutional Long Short-Term Memory (ConvLSTM), were compared and optimized using grid search with cross-validation on consumption data from Lome, a city in Togo. The results indicate that the ConvLSTM model outperforms its counterparts based on Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE), and correlation coefficient (R2) metrics. The ConvLSTM model was further refined using wavelet decomposition with coefficient sorting, resulting in the WT+ConvLSTM model. This proposed approach significantly narrows the gap between actual and predicted loads, reducing discrepancies from 10–50 MW to 0.5–3 MW. In comparison, the WT+ConvLSTM model surpasses Autoregressive Integrated Moving Average (ARIMA) models and Multilayer Perceptron (MLP) type artificial neural networks, achieving a MAPE of 0.485%, an RMSE of 0.61 MW, and an R2 of 0.99. This approach demonstrates substantial robustness in electricity load forecasting, aiding stakeholders in the energy sector to make more informed decisions.

Current state and forecast model development of the agrarian structure of the Southern Federal District

Current state and forecast model development of the agrarian structure of the Southern Federal District

Development of Econometric Models for Financial Performance Forecasting in Companies

This study develops an econometric model to predict corporate financial performance. The goal is to improve the accuracy of predictions by analysing relevant economic and financial variables. The model combines statistical and econometric analysis to identify significant input variables such as asset turnover, firm size, capital structure, and liquidity. The study also highlights the importance of external factors, such as environmental policies and knowledge management, that affect corporate financial performance. Using ARIMA and VAR models, the study shows that selecting the correct parameters, such as the number of lags, is critical to improving prediction accuracy. The developed model is evaluated based on RMSE, MAD, and MAPE metrics, which show that the econometric model offers more accurate predictions than the classical statistical model. These results contribute significantly to understanding corporate financial performance dynamics and can be a reliable tool in strategic decision-making across various industry sectors.

Розвиток систем обліково-аналітичного забезпечення в умовах цифрової трансформації інформаційної індустрії

The article analyzes the current state and development of accounting and analytical systems in the context of the digital transformation of the information industry, a critical issue for enterprises in this sector. The study examines the main trends and challenges companies face due to the active implementation of digital technologies in accounting and analytical activities. It characterizes the critical aspects of how digital transformation impacts the processes of data collection, processing, and analysis within the modern information industry. The article proposes new approaches to organizing accounting and analytical systems that meet the digital economy’s demands. It explores the potential of modern information technologies to enhance the effectiveness of management decisions based on the analysis of large data sets, which contributes to increasing enterprises’ competitiveness in the digital environment. Additionally, the article highlights the necessity of integrating advanced technologies into financial control and management processes. The research identifies prospects for developing accounting and analytical systems, considering global digital trends. Recommendations are developed to improve the adaptability of information industry enterprises to the rapidly changing digital environment. Through a comprehensive analysis, the article underscores the importance of adapting to and leveraging digital transformation to enhance operational efficiency and maintain a competitive edge. The findings suggest that the ongoing digital revolution in accounting and analytics presents opportunities and challenges, requiring businesses to innovate and continuously adapt their systems and processes. This will ensure they remain resilient and competitive in an increasingly digitized global market. In the future, research in this field should focus on integrating the latest digital technologies, such as artificial intelligence and blockchain, which can significantly improve the accuracy and speed of data processing. Also, an important direction is the development of new analytical forecasting models based on big data, which will help to make management decisions more effectively. Keywords: Digital transformation, accounting systems, analytical systems, information industry, big data, competitiveness, financial control, management efficiency, modern information technologies, digital economy.

Reduced-order reconstruction of discrete grey forecasting model and its application

Discrete grey forecasting models based on an accumulative operator have been widely used in many practical fields. With the development of grey forecasting models, it is a problem to be solved to further analyze internal mechanisms and unify the structures. This paper aims to reconstruct the model from a perspective of sequence characteristics and simplify the modeling steps under the condition of ensuring the accuracy of the model. First, this paper analyzes dynamic sequence evolution hidden and mines relationship between the structure and original sequence features contained in discrete grey forecasting model. Then, the reconstruction is carried out to prove the equivalence and quantitative relation between reduced-order model and original model. Under order recursive estimation, new parameters are addressed. Finally, theoretical correctness is verified by large-scale numerical simulation. Moreover, the reduced-order model is applied for prediction on the peak of battery incremental capacity and capacity degradation. Results show the effectiveness and superior prediction performance of the reduced-order model, where MAPEs of grey forecasting models have controlled under 4%.

Development and Performance Analysis of Aquila Algorithm Optimized SPV Power Imputation and Forecasting Models

Development and Performance Analysis of Aquila Algorithm Optimized SPV Power Imputation and Forecasting Models

ПРОГНОЗЫ ГОДОВОГО СТОКА Р. ЖАЙЫК (УРАЛ) С УЧЕТОМ АВТОКОРРЕЛЯЦИОННЫХ МОДЕЛЕЙ ЕГО МНОГОЛЕТНИХ КОЛЕБАНИЙ ЗА ОТДЕЛЬНЫЕ МЕСЯЦЫ

The study is devoted to the development and application of autocorrelation and general regression models for long-term forecasting of the Ural (Zhaiyk) River flow based on the analysis of multi-year fluctuations. The Ural River is an important water resource of the Russian Federation and the Republic of Kazakhstan, demonstrating significant variability in annual runoff, which affects various sectors of economic activity. In the course of the study, annual and monthly series of the river flow for the period from 1943 to 2010 were estimated using the autocorrelation method of Y.M. Alekhin. Based on these data, forecasts were made for the period from 2011 to 2015. The results show that autocorrelation models provide more accurate forecasts compared to models based on average values of series. The general regression model integrating monthly and annual data showed the best results, confirming the effectiveness of the combined approach in predicting hydrological characteristics. The scientific significance of the work is to improve the accuracy and reliability of the Ural River flow forecasts, which contributes to more effective water resources management in this region.

Sensitivity of HAFS-B Tropical Cyclone Forecasts to Planetary Boundary Layer and Microphysics Parameterizations

Abstract Understanding how model physics impact tropical cyclone (TC) structure, motion, and evolution is critical for the development of TC forecast models. This study examines the impacts of microphysics and planetary boundary layer (PBL) physics on forecasts using the Hurricane Analysis and Forecast System (HAFS), which is newly operational in 2023. The “HAFS-B” version is specifically evaluated, and three sensitivity tests (for over 400 cases in 15 Atlantic TCs) are compared with retrospective HAFS-B runs. Sensitivity tests are generated by 1) changing the microphysics in HAFS-B from Thompson to GFDL, 2) turning off the TC-specific PBL modifications that have been implemented in operational HAFS-B, and 3) combining the PBL and microphysics modifications. The forecasts are compared through standard verification metrics, and also examination of composite structure. Verification results show that Thompson microphysics slightly degrades the days 3–4 forecast track in HAFS-B, but improves forecasts of long-term intensity. The TC-specific PBL changes lead to a reduction in a negative intensity bias and improvement in RI skill, but cause some degradation in prediction of 34-kt (1 kt ≈ 0.51 m s−1) wind radii. Composites illustrate slightly deeper vortices in runs with the Thompson microphysics, and stronger PBL inflow with the TC-specific PBL modifications. These combined results demonstrate the critical role of model physics in regulating TC structure and intensity, and point to the need to continue to develop improvements to HAFS physics. The study also shows that the combination of both PBL and microphysics modifications (which are both included in one of the two versions of HAFS in the first operational implementation) leads to the best overall results. Significance Statement A new hurricane model, the Hurricane Analysis and Forecast System (HAFS), is being introduced for operational prediction during the 2023 hurricane season. One of the most important parts of any forecast model are the “physics parameterizations,” or approximations of physical processes that govern things like turbulence, cloud formation, etc. In this study, we tested these approximations in one configuration of HAFS, HAFS-B. Specifically, we looked at two different versions of the microphysics (modeling the growth of water and ice in clouds) and boundary layer physics (the approximations for turbulence in the lowest level of the atmosphere). We found that both of these sets of model physics had important effects on the forecasts from HAFS. The microphysics had notable impacts on the track forecasts, and also changed the vertical depth of the model hurricanes. The boundary layer physics, including some of our changes based on observed hurricanes and turbulence-resolving models, helped the model better predict rapid intensification (periods where the wind speed increases quickly). Work is ongoing to improve the model physics for better forecasts of rapid intensification and overall storm structure, including storm size. The study also shows the combination of both PBL and microphysics modifications overall leads to the best results and thus was used as one of the two first operational implementations of HAFS.

Flood Prediction System Using IOT & Artificial Neural Network

Floods pose significant challenges as one of nature's most devastating disasters, making the development of accurate forecast model’s complex. This issue has led to severe consequences such as crop loss, population displacement, damage to infrastructure, and disruption of essential services. Advanced research on flood prediction models has played a crucial role in providing policy recommendations, mitigating risks, reducing human casualties, and minimizing property damage caused by floods. In this context, we propose an Internet of Things (IoT)-based flood prediction and forecasting model that prioritizes energy efficiency. Given the limited battery and memory capacity of IoT sensor nodes, we employ an energy-saving strategy within the fog layer, leveraging data diversity to minimize energy consumption. Additionally, cloud technology offers an effective storage solution. To accurately calibrate flood phases, we investigate climatic factors such as humidity, temperature, rainfall, as well as water body parameters including water flow and elevation. Neural networks are commonly used in constructing forecast systems, as they can replicate the complex calculations involved in flood physical processes, resulting in improved performance and cost-effectiveness. In our approach, the Artificial Neural Network (ANN) technique is employed for flood forecasting, and the effectiveness of different algorithms, such as Logistic Regression and Decision Tree, is assessed by comparing them to ANN. Accuracy values are computed using a classification report assessment, and graph parameters are carefully evaluated. Ultimately, our proposed system utilizes the ANN technique to train a predictive model by examining the dataset. This model generates real-time flood risk forecasts through a user-friendly graphical interface.

Data-driven approach for day-ahead System Non-Synchronous Penetration forecasting: A comprehensive framework, model development and analysis

This article presents a comprehensive, innovative, and data-driven approach for predicting System Non-Synchronous Penetration (SNSP) levels. It consists of iterative steps that involve data analytics and forecasting model development to overcome the challenges associated with forecasting, such as data mining or overfitting. The approach starts by defining the problem domain and identifying relevant features using the Pearson correlation method. The framework ensures that all forecasting models carry out data pre-processing uniformly. The hyperparameters, understood as adjustable external factors not learned during the training process that affect the performance and predictive ability of the forecasting model are optimized using the random search algorithm to enhance the models’ performance. The study compares the performance of classical models, such as Random Forest and Light Gradient Boosting, with advanced machine learning-based models, such as Feed-forward, Gate Recurrent Unit, Short-Term Long Memory, and Convolutional Neural Network. Data from the Irish power system is chosen as a case study. The results indicate that the Feed-forward model produces the lowest errors. It has a Mean Absolute Error of about 4.09, a Root Mean Squared Error of 5.37 and a Mean Absolute Percentage Error of 18.17% respectively. This systematic and practical approach can be applied to other regions with similar challenges. This study also highlights the potential of advanced machine learning-based models in improving SNSP forecasting accuracy. The approach is beneficial for network and market operators, and ancillary service providers in smart grid network operations, with a 15-minute resolution. It provides a promising direction for future research in this area.

Development of forecast models on electrical discharge machined graphene nanoplatelets reinforced aluminum composite fabricated via stir casting route

Development of forecast models on electrical discharge machined graphene nanoplatelets reinforced aluminum composite fabricated via stir casting route

Using of the Weibull distribution in developing global solar radiation forecasting models

AbstractIn this study, a solar radiation prediction model was developed using the Weibull distribution function (WDF). The main purpose of this study is to develop a new model for solar radiation (SR) estimation using the WDF and to bring this model to the literature. Although the WDF is widely used in wind energy forecasting due to its compatibility with wind speed data, it has not been used before in solar radiation forecasting model development. In this study, it is aimed to make SR estimation with the WDF for the first time. SR data for all regions where this new model was developed and its performance was examined were obtained from the General Directorate of Meteorology. In order to decide the success of these developed models, five different statistical metrics (RPE, MPE, MAPE, SSRE, and t‐stat) were discussed in the study. When the results are evaluated in general, it is seen that the new developed model has an acceptable performance. According to all test results in the region where the model was developed, it is seen that the new developed model showed the best performance with 0.0353, 0.4068, 7.1851, 0.1144, and 0.0162 values, respectively. The performance of this new developed model was observed in three different regions. When the statistical test results in these regions were examined, it was seen that the new model developed had a similar performance to the popular solar forecasting models widely used in the literature.

Solar Radiation Forecasting Models and their Thermodynamic Analysis in Asaba: Least Square Regression and Machine Learning Approach

Least square regression and machine learning tools were used for the development of global solar radiation forecasting models for Asaba region. Data from the year 2013-2022 from Nigerian Meteorological Agency, Asaba was used for this study. The least square regression method was used to develop four global solar radiation -based models, tagged H1, H2, H3 and H4 with characteristic day length, solar declination angle, rainfall amount, etc. as its model terms while the machine learning models produced multilayer perceptron, coarse Gaussian model (SVM-based model) and XGBoost model. The prediction factors like mean bias error, mean percentage error, root mean square error, Nash-Sutcliffe equation, coefficient of correlation (R), t-test, and coefficient of determination (R2) were considered using the model terms. The results indicates that H4 model outperformed H1, H2, H3, machine learning models (SVM-based model, multilayer perceptron and XGBoost) and other existing models (MA-MME and MLR) with a mean percentage error value of 0.740, RMSE value of 46.588, Nash-Sutcliffe equation value of 0.739, higher R2 value of 0.7391, t-test value of 2.595E-24 and mean bias error value of -6.88E-12. Thus, H4 model results fell within accepted range. Additionally, the exergy of the global solar radiation of Asaba varied from 20-185 W/m2 which are good. This shows that a more efficient and ideal global solar radiation prediction model (H4) has been developed for Asaba and other regions that share similar climatic conditions.

Empowering urban climate resilience and adaptation: Crowdsourcing weather citizen stations-enhanced temperature prediction

The growing impact of climate change, including extreme weather events, represents a significant challenge for humanity. With most of the world's population living in urban areas, the urban heat island effect and anthropogenic heat contribute to elevated city temperatures. This increase in urban warming threatens human health and demands a deeper understanding of thermal distribution in urban environments. Collecting accessible and widespread temperature data in urban areas is essential to address this challenge. This study aims to develop a methodology for anticipating temperature distribution in urban environments, leveraging Citizen Weather Stations (CWS) as valuable crowdsourcing data sources. The ultimate goal is to create a predictive model that estimates urban temperatures based on government meteorological station forecasts, improving urban planning, regulating temperature-based routes, preventing health issues in vulnerable populations, and enhancing urban livability. The methodology is divided into three fundamental stages: data acquisition through CWS with citizen collaboration, the development and evaluation of optimal forecast models based on government weather stations (SWS) data, and its exploitation in terms of utility and applicability. This methodology encompasses data collection and filtering to ensure its usefulness and implement reliable models. The resulting tool facilitates informed decision-making and precise seasonal event planning in urban environments, effectively addressing the challenges of climate extrapolation and contributing to more effective adaptation and mitigation strategies in climate change and heatwaves. The results obtained probe the feasibility of using CWS to predict temperatures in urban environments, which has been demonstrated accurately. This is a significant achievement, as CWS has proven to be a reliable source of climate data for this context. Also, the filtering process described and applied to the case study has proven effective, discarding approximately 34.87 % of the data. This is achieved by detecting and eliminating anomalies, considering station availability, and adhering to specific quality criteria. Finally, the developed prediction model has demonstrated its ability to optimally estimate urban temperatures, utilizing climate prediction data provided by government weather stations (SWS). The model performance indicators support this claim. For the linear regression model, a Mean Squared Error (MSE) of 2.177 and an R-squared (R2) of 0.960 are obtained, while for the neural network, an MSE of 1.284 and an R2 of 0.976 are achieved.

СОВЕРШЕНСТВОВАНИЕ ПРОГНОЗИРОВАНИЯ СОЦИАЛЬНО-ЭКОНОМИЧЕСКОГО РАЗВИТИЯ РЕГИОНА

The article presents an algorithm for forecasting the socio-economic development of the region based on artificial intelligence models, a methodological approach and tools for forecasting the gross regional product, adaptive forecasts of the gross regional product of the Altai Territory, recommendations for the use of adaptive forecasts in strategic planning of the region. The purpose of the study is to develop an algorithm, a methodological approach and tools for forecasting the socio-economic development of the region based on artificial intelligence models. The study is based on official data from the Federal State Statistics Service. The main stages of forecasting the socio-economic development of the region based on artificial intelligence models are: identification of factors that have a dominant influence on the dynamics of forecast indicators, development of a methodological approach to forecasting based on the construction and use of artificial intelligence models, development of models for forecasting. The results of the conducted research provide grounds for the development and correction of strategic planning documents of the Altai Territory.

Daily flow discharge prediction using integrated methodology based on LSTM models: Case study in Brahmani-Baitarani basin

For flood control, hydropower operation, and agricultural planning, among other applications, flow discharge prediction is a critical first step toward the strong and dependable planning and management of water resources. Floods are destructive natural calamities that destroy human lives and infrastructure across the world. Development of effective flood forecasting and prediction models is critical for minimising deaths and mitigating damages. This study employs hybrid deep learning Long Short Term Memory (LSTM) algorithms like LSTM, Convolution LSTM (Conv-LSTM) and Convolutional Neural Network LSTM (CNN-LSTM) to predict likelihood flood events using daily precipitation, daily temperature and daily relative humidity from two flood-forecasting stations i.e., Champua (Baitarani River, Odisha) and Jarikela (Brahmani River, Odisha) over a 20-year period. The results show that CNN-LSTM performed best followed by Conv-LSTM and LSTM in terms of R2 = 0.98055, 0.96564, and 0.93244, RMSE = 19.137, 35.635, and 49.347, MAE = 18.372, 33.766, and 47.058, NSE = 0.971, 0.9517 and 0.9257 respectively. The findings support the claim that machine learning models and algorithms, in particular CNN-LSTM model, can be applied to flood forecasting with high accuracy, thereby enhancing water and hazard management.

PV Forecasting Model Development and Impact Assessment via Imputation of Missing PV Power Data

PV Forecasting Model Development and Impact Assessment via Imputation of Missing PV Power Data

EV Charging Management: a Forecasting Model Development for Parking Time and Arrival State of Charge

In the context of optimizing electric vehicle (EV) charging and discharging management, this study addresses the critical task of predicting, for the next day, the arrival and departure times of each EV, as well as its state of charge (SoC) when accessing the parking lot. This management challenge requires the application of a robust forecasting approach to ensure accurate forecasts. In this paper, the proposed predictor is developed using the Long Short-Term Memory (LSTM) modeling technique. The model feature selection process, is carried out based on a correlation/autocorrelation matrix integrating data of different natures (weather, EV arrival and departure time, EV state of charge). Performance validation of the proposed forecasting model is carried out using the Mean Absolute Percentage Error (MAPE). The supremacy of the developed LSTM predictor is highlighted by comparing its performances with those of a Convolutional Neural Network (CNN) model. For the next day’s Arrival Time model, the LSTM demonstrates a MAPE of 1.95×10-3, the Departure Time model yields a MAPE of 5.49×10-3, and the SoC at Arrival model exhibits a MAPE of 5 × 10-2. These findings underscore the significance of the LSTM model, coupled with feature selection strategies, in enhancing the precision of EV charging and discharging management within residential contexts.

Watershed groundwater level multistep ahead forecasts by fusing convolutional-based autoencoder and LSTM models

The development of deep learning-based groundwater level forecast models can tackle the challenge of high dimensional groundwater dynamics, predict groundwater variation trends accurately, and manage groundwater resources effectively, thereby contributing to sustainable water resources management. This study proposed a novel ConvAE-LSTM model, which fused a Convolutional-based Autoencoder model (ConvAE) and a Long Short-Term Memory Neural Network model (LSTM), to provide accurate spatiotemporal groundwater level forecasts over the next three months. The HBV-light and LSTM models are chosen as benchmarks. An ensemble of point data and the corresponding derived images concerning the past (observations) and the future (forecasts from a conceptual model) of groundwater levels at 33 groundwater wells in Jhuoshuei River basin of Taiwan between 2000 and 2019 constituted the case study. The findings showcase the effectiveness of the ConvAE-LSTM model in extracting crucial features from both point and imagery datasets. This model successfully establishes spatiotemporal dependencies between regional images and groundwater level data over diverse time frames, leading to accurate multi-step-ahead forecasts of groundwater levels. Notably, the ConvAE-LSTM model exhibits a substantial improvement, with the R-squared values showing an increase of more than 18%, 22%, and 49% for the R1, R2, and R3 regions, respectively, compared to the HBV-light model. Additionally, it outperforms the LSTM model in this regard. This study represents a noteworthy milestone in environmental modeling, offering key insights for designing sustainable groundwater management strategies to ensure the long-term availability of this vital resource.

Study of Scenarios for Forecasting Freight Turnover on the Railway Considering Account Expert Information

A scenario approach is considered, taking into account expert information for the development of forecast models using the example of operational indicators of the East Siberian Railway. When creating scenarios, statistical data, as well as point expert estimates, were used. Expert assessments are proposed for two options. The final model for forecasting the basic indicator, which is freight turnover, is a linear convolution of partial models. The number of private models is three. It is proposed to calculate weight coefficients using the hierarchy analysis method. A special feature of this method is the creation by experts of a matrix of judgments that can be checked for consistency. Three scenarios for the development of the transportation process were proposed, which were processed until results were obtained. It is shown that the scenario approach gives good results even under conditions of uncertainty in the transportation process.