Short-term Forecasting Model Research Articles

Two-Stage Combined Model for Short-Term Electricity Forecasting in Ports

Two-Stage Combined Model for Short-Term Electricity Forecasting in Ports

A CNN-LSTM Model for Short-Term Passenger Flow Forecast Considering the Built Environment in Urban Rail Transit Stations

A CNN-LSTM Model for Short-Term Passenger Flow Forecast Considering the Built Environment in Urban Rail Transit Stations

Models for Short-Term Forecast of Maximum X-ray Class of Solar Flares Based on Magnetic Energy of Active Regions

Models for Short-Term Forecast of Maximum X-ray Class of Solar Flares Based on Magnetic Energy of Active Regions

A hybrid deep learning-based short-term forecast model for ionospheric foF2 in East Asia region

The short-term forecast of the critical frequency of the ionospheric F2 layer (foF2) is particularly challenging due to its nonlinear and non-stationary characteristics. To improve the short-term forecast accuracy of foF2, we propose a short-term hybrid deep learning model that integrates the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN) and long short-term memory (LSTM) algorithms. The proposed model leverages the ICEEMDAN decomposition algorithm to expand foF2 time series data into multi-dimensional space and utilizes the LSTM algorithm to preserve long-term data information, capturing detailed changes in foF2 parameters and obtaining internal information about foF2. The 2014 and 2017 foF2 data from four observation stations located in Mohe, Beijing, Jeju, and Kokubunji in the mid-latitudes of East Asia were utilized for modeling and 1-hour forecast analysis. The forecast values of the proposed model align closely with the measured data, exhibiting minimal fluctuation in forecast error and effectively tracking the changing trend of foF2. The average root mean square error (RMSE) across the four stations in 2014 is 0.40 MHz, with a relative RMSE (RRMSE) of 7.11 % and a coefficient of determination (R2) of 0.98. The average RMSE in 2017 is 0.43 MHz, RRMSE is 7.68 %, and R2 is 0.92. The proposed model reveals significant improvements in the forecast accuracy of the comparison model compared with the CCIR, URSI, NN, and LSTM models. Especially compared with the CCIR and URSI models in the International Reference Ionosphere (IRI), demonstrating superior real-time tracking capability for foF2 and effectively addressing the challenge of poor short-term forecast accuracy observed in the IRI model.

Short-term forecasting of consumption of the oil and gas enterprises using technological factors and Shapley additive explanations

RELEVANCE of the study lies in the development of system for the short-term forecasting of power consumption by the enterprise of the oil and gas industry with consideration of technological factors and interpretation of their influence on the result of the forecast.THE PURPOSE. To consider the problems of short-term forecasting. To test the applicability of the multi-agent approach to determine the features used to build a machine learning model of short-term forecasting of power consumption. To build machine learning models. To study the influence of technological factors on the accuracy of forecasting of power consumption. To apply the SHapley Additive exPlanations and analyze its interpretation of the forecasting results.METHODS. Pre-processing of the dataset, construction and testing of machine learning models were made in the programming language Python 3 using opensource libraries Scikit-Learn, XGBoost, LightGBM, Shap.RESULTS. The article describes the relevance of the topic of short-term forecasting of power consumption by the enterprise of the oil and gas industry within the ESG-approach. The method of selecting the features used using a multi-agent approach to build a machine learning model was developed. Machine learning models were built. Experimentations with the consideration of different features were made. Interpretation of results using SHapley Additive exPlanations was made.CONCLUSION. The use of technological factors of power consumption of compressor yards and natural gas air coolers allowed to increase the accuracy of forecast of power consumption from 8.82 % to 3.65 %. The application of the SHapley Additive exPlanations allows to interpret the results of machine learning models and confirms the need to consider technological factors in the task of short-term forecasting of power consumption of oil and gas industry.

Short-term photovoltaic forecasting model with parallel multi-channel optimization based on improved dung beetle algorithm

Accurate prediction of photovoltaic(PV) generation plays a vital role in power dispatching and is one of the effective ways to ensure the safe operation of power grid. In response to this issue, this paper improves the Rhino beetle optimization algorithm (LSDBO) using Logistic chaos mapping and sine function strategies an optimizes the PCL-MHA model (running CNN-MHA and LSTM-MHA models in parallel, PCL; Multi-Head-Attention, MHA) to enhance predictive accuracy. Various experiments were conducted using historical data from the Alice Springs PV system in Australia. PV component technologies comprise monocrystalline silicon and polycrystalline silicon, with array fixed on the ground. Through experiments, the proposed model in this paper achieved the best results in 16 metrics under different weather conditions, with average values of 98.43 % for R2, 2.69 % for MSE, 7.8 % for MAE, and 15.09 % for RMSE. Compared to other models, an average improvement of 2.41 %, 6.6 %, 7.77 %, and 11.21 % in these metrics.

Polynomial fuzzy information granule based [formula omitted]-triple I fuzzy reasoning algorithm and its short-term forecasting of time series

Short-term forecasting of time series is an important research topic, which involves data characteristic capture and intelligent reasoning. For this topic, the Gaussian polynomial fuzzy information granule with interpretability is granulated on data, enabling the extraction of data trend characteristic, besides, the associate characteristic within the data is captured through building fuzzy association rule. Building upon the data characteristics captured in fuzzy information granule and fuzzy association rule, an intelligent reasoning algorithm called the fuzzy information granule based α-Triple I algorithm is proposed, where the membership degree of data to granule is considered in reasoning, and next the accurate level of deviation from data to granule can be inferenced. Based on the excavated data characteristics and a rational inference, a short-term forecasting model is established. Its superiority in terms of accuracy and reliability when compared to 7 other models in real time series has been tested. Notably, the prediction of the novel model is accurate because the function of FAR is identified from FAR’s truth degree, which means the validity degree of prediction. The application of the proposed model for short-term forecasting holds a potential impact across various fields.

Artificial neural network-based models for short term forecasting of solar PV power output and battery state of charge of solar electric vehicle charging station

The main objective of this study is to develop ANN-based predictive models for short-term forecasting of solar PV power output and battery state of charge. The 3Ds energy model that integrates Decarbonization, Digitalization, and Decentralization of the energy system to facilitate the shift towards sustainable energy sources is used for this electric vehicle project. The experimental set up includes solar PV panels, a solar inverter, a battery inverter, and a battery bank. Additionally, smart meters were installed to collect real-time performance data from the solar PV-powered electric vehicle (EV) charging station. The weather and real-time system performance data were used to develop short term forecasting models based on Artificial Neural Networks (ANN) and the Levenberg-Marquardt method, to predict the performance of the system (power output and state of the charge) ahead. The R values for the prediction models of solar photovoltaic (PV) specific power and battery state of charge fall within the range of 0.9957–0.9969 and 0.9990 to 0.9996, respectively. Furthermore, the mean squared errors (MSEs) for the artificial neural network (ANN) models pertaining to solar photovoltaic (PV) power output and battery state of charge exhibit a variety of values. Specifically, the MSEs for solar PV power output range from 1.242 x 10^-4 to 1.579 x 10^-4, while the MSEs for battery status of charge range from 0.1889 to 0.3402. Artificial neural network (ANN) models possess considerable promise for practical implementations as they simplify intricate connections among inputs, parameters, and outputs in real-world scenarios. The level of accuracy and short-term predictive models of the solar PV powered EV charging station are very important for achieving a balance between the supply of solar photovoltaic (PV) system and the demand for electric vehicles (EVs). Predictive models will help build complex control mechanisms for controlling and optimizing solar PV-powered charging stations, supervising their operation and maintenance, and simplifying renewable energy pre-purchase. Future works will include the development of an energy management system to improve the efficiency of the solar stations charging the EVs, the establishment of blockchain networks for both the solar PV system and battery bank, and the integration of cybersecurity protocols for the charging station.

Multi-step electric vehicles charging loads forecasting: An autoformer variant with feature extraction, frequency enhancement, and error correction blocks

The extensive integration of electric vehicles (EVs) into power grids has raised safety concerns. Meanwhile current EVs charging loads forecasting models mainly focus on single-step predictions, neglect load sparsity and underutilize residuals, limiting their accuracy. To tackle these issues, a multi-step short-term forecasting model, specifically designed to predict charging loads at public EVs charging stations using historical data, is proposed. The model begins with a preprocessing phase to handle missing data and outliers. Subsequently, an Autoformer variant is intruduced, which initially integrates feature extraction block leveraging the Temporal Convolutional Network (TCN) to adeptly capture temporal dynamics. This is further enhanced with a Discrete Cosine Transform (DCT)-based frequency enhancement block to learn sparsity and periodicity features of EVs charging loads by frequency mapping. In addition, an advanced error correction block, comprising Bayesian optimization algorithm, Convolutional Neural Networks, Multi-Head Self-Attention, and Gated Recurrent Units (BCMG), is incorporated to refine initial prediction results. Above all, the TCN-DCT enhanced Autoformer-BCMG (TDformerBCMG) model is proposed. Finally, a comprehensive experimental analysis is conducted on ACN-data for EVs charging load forecasting in 1–3 h steps. It is demonstrated that TDformerBCMG not only is effective and superior in each component, but also achieves a reduction in Mean Absolute Error by 20.94 % to 74.05 % compared to existing models. Moreover, stability is evidenced across 50 repeated trials, with the standard deviation for the Coefficient of Determination varying between 8.5844e-3 and 3.1580e-2. Further discussion on application analysis is provided. Consequently, TDformerBCMG offers a viable methodology and establishes a new benchmark for power system implementation.

A dynamic ensemble model for short-term forecasting in pandemic situations.

During the COVID-19 pandemic, many hospitals reached their capacity limits and could no longer guarantee treatment of all patients. At the same time, governments endeavored to take sensible measures to stop the spread of the virus while at the same time trying to keep the economy afloat. Many models extrapolating confirmed cases and hospitalization rate over short periods of time have been proposed, including several ones coming from the field of machine learning. However, the highly dynamic nature of the pandemic with rapidly introduced interventions and new circulating variants imposed non-trivial challenges for the generalizability of such models. In the context of this paper, we propose the use of ensemble models, which are allowed to change in their composition or weighting of base models over time and could thus better adapt to highly dynamic pandemic or epidemic situations. In that regard, we also explored the use of secondary metadata-Google searches-to inform the ensemble model. We tested our approach using surveillance data from COVID-19, Influenza, and hospital syndromic surveillance of severe acute respiratory infections (SARI). In general, we found ensembles to be more robust than the individual models. Altogether we see our work as a contribution to enhance the preparedness for future pandemic situations.

Improved informer PV power short-term prediction model based on weather typing and AHA-VMD-MPE

Precise prediction of PV power in the short term is crucial for maintaining power system stability and balance. However, the performance of conventional time series prediction models on short-term long series prediction is scarcely sufficient because of the stochastic and turbulent character of PV power data. This work suggests a PV short-term power forecast model based on weather type, AHA-VMD-MPE decomposition reconstruction, and improved Informer combination to tackle this issue. Firstly, a SUM-ApEn-K-mean++ multidimensional clustering method to group the dataset by weather conditions. Then an AHA-VMD-MPE decomposition model is proposed to decompose the historical power data Finally the Informer model is improved and the improved model is utilized to predict the PV power under various weather conditions. The model exhibits great accuracy and stability in short-term PV power prediction, as demonstrated by the experimental results, which were validated using measured data from many PV power plants.

ES-dRNN: A Hybrid Exponential Smoothing and Dilated Recurrent Neural Network Model for Short-Term Load Forecasting.

Short-term load forecasting (STLF) is challenging due to complex time series (TS) which express three seasonal patterns and a nonlinear trend. This article proposes a novel hybrid hierarchical deep-learning (DL) model that deals with multiple seasonality and produces both point forecasts and predictive intervals (PIs). It combines exponential smoothing (ES) and a recurrent neural network (RNN). ES extracts dynamically the main components of each individual TS and enables on-the-fly deseasonalization, which is particularly useful when operating on a relatively small dataset. A multilayer RNN is equipped with a new type of dilated recurrent cell designed to efficiently model both short and long-term dependencies in TS. To improve the internal TS representation and thus the model's performance, RNN learns simultaneously both the ES parameters and the main mapping function transforming inputs into forecasts. We compare our approach against several baseline methods, including classical statistical methods and machine learning (ML) approaches, on STLF problems for 35 European countries. The empirical study clearly shows that the proposed model has high expressive power to solve nonlinear stochastic forecasting problems with TS including multiple seasonality and significant random fluctuations. In fact, it outperforms both statistical and state-of-the-art ML models in terms of accuracy.

Business Cycle and Early Warning Indicators for the Economy of Hong Kong– Challenges of Forecasting Work amid the COVID-19 Pandemic

This paper discusses the use of the OECD’s framework to identify early warning indicators for building a Composite Leading Indicator (CLI) and the use of the Vector Autoregressive Model (VAR) for constructing a short-term forecasting model of economic growth of Hong Kong. With the onset of the COVID-19 pandemic, this paper further evaluates the performance of the CLI and forecasting model which were built based on pre-COVID-19 parameters and identify further adjustments to enhance the model performance.

Short-term solar irradiance forecasting under data transmission constraints

We report a data-parsimonious machine learning model for short-term forecasting of solar irradiance. The model follows the convolutional neural network – long-short term memory architecture. Its inputs include sky camera images that are reduced to scalar features to meet data transmission constraints. The model focuses on predicting the deviation of irradiance from the persistence of cloudiness (POC) model. Inspired by control theory, a noise signal input is used to capture the presence of unknown and/or unmeasured input variables and is shown to improve model predictions, often considerably. Five years of data from the NREL Solar Radiation Research Laboratory were used to create three rolling train-validate sets and determine the best representations for time, the optimal span of input measurements, and the most impactful model input data (features). For the chosen validation data, the model achieves a mean absolute error of 74.29 W/m2over a time horizon of up to two hours, compared to a baseline 134.35 W/m2 using the POC model.

Dynamic Temporal Dependency Model for Multiple Steps Ahead Short-Term Load Forecasting of Power System

Dynamic Temporal Dependency Model for Multiple Steps Ahead Short-Term Load Forecasting of Power System

Application of a single-equation SARIMA model for short-term conditional forecast (projection) of CPI price dynamics in Poland

The aim of the article is to construct an optimal SARIMA model for short-term conditional forecasting (projection) of the dynamics of prices expressed by the Consumer Price Index (CPI), as understood within the extended Box-Jenkins procedure. The construction of such a forecast aims to influence, through the expectations channel, the institutional trust of society in monetary authorities and assess the effectiveness of achieving the monetary policy goal within the framework of the democratic responsibility of the decision-making body of the National Bank of Poland – the Monetary Policy Council. The selection of the optimal SARIMA model was carried out using an iterative method within the Box-Jenkins procedure, with the goal of reducing the systematic bias of estimators – coherence with empirical data. The analysis was conducted on compiled secondary data of the monthly Consumer Price Index for goods and services from the Central Statistical Office for the years 2010-2023 (on a monthly basis). Results show that the short-term forecast demonstrated accuracy within a specified confidence interval. The application of the SARIMA model serves as a useful methodological tool for constructing elaborate DSGE models (for example, the NECMOD model) using procedures such as SEM (System for Averaging Models) from Norges Bank.

Hierarchical attention network for short-term runoff forecasting

Accurate prediction of runoff is critical concerning reservoir management and disaster preparedness. Data-driven methods are progressively applied to runoff prediction tasks and have led to impressive results. However, existing data-driven methods are hardly considered to the runoff generation process and the spatial characteristics of basins in the models due to the lack of a priori knowledge guidance. Here a structured approach is provided to develop the perceptual model for runoff generation and model the behavior in groups at different locations and scales; considering the hierarchical structure of basin systems, a short-term runoff forecasting model with spatial perception and scale interaction, i.e., the hierarchical attention network, is developed based on the encoder-decoder structure and attention mechanism. Compared to the single- and multi-step prediction performance of the six baseline models, the NSE improved by an average of 2.41, 9.68, and 12.14%, respectively. This implies that incorporating basin-related knowledge in modeling and considering runoff generation processes and spatial connectivity can improve prediction accuracy, and the necessity of considering conceptual mechanisms in data-driven models.

SSA-ELM: A Hybrid Learning Model for Short-Term Traffic Flow Forecasting

Nowadays, accurate and efficient short-term traffic flow forecasting plays a critical role in intelligent transportation systems (ITS). However, due to the fact that traffic flow is susceptible to factors such as weather and road conditions, traffic flow data tend to exhibit dynamic uncertainty and nonlinearity, making the construction of a robust and reliable forecasting model still a challenging task. Aiming at this nonlinear and complex traffic flow forecasting problem, this paper constructs a short-term traffic flow forecasting hybrid optimization model, SSA-ELM, based on extreme learning machine by embedding the sparrow search algorithm in order to solve the above problem. Extreme learning machine has been widely used in short-term traffic flow forecasting due to its characteristics such as low computational complexity and fast learning speed. By using the sparrow search algorithm to optimize the input weight values and hidden layer deviations in the extreme learning machine, the sparrow search algorithm is utilized to search for the global optimal solution while taking into account the original characteristics of the extreme learning machine, so that the model improves stability while increasing prediction accuracy. Experimental results on the Amsterdam A10 road traffic flow dataset show that the traffic flow forecasting model proposed in this paper has higher forecasting accuracy and stability, revealing the potential of hybrid optimization models in the field of short-term traffic flow forecasting.

Deep learning-driven hybrid model for short-term load forecasting and smart grid information management

Accurate power load forecasting is crucial for the sustainable operation of smart grids. However, the complexity and uncertainty of load, along with the large-scale and high-dimensional energy information, present challenges in handling intricate dynamic features and long-term dependencies. This paper proposes a computational approach to address these challenges in short-term power load forecasting and energy information management, with the goal of accurately predicting future load demand. The study introduces a hybrid method that combines multiple deep learning models, the Gated Recurrent Unit (GRU) is employed to capture long-term dependencies in time series data, while the Temporal Convolutional Network (TCN) efficiently learns patterns and features in load data. Additionally, the attention mechanism is incorporated to automatically focus on the input components most relevant to the load prediction task, further enhancing model performance. According to the experimental evaluation conducted on four public datasets, including GEFCom2014, the proposed algorithm outperforms the baseline models on various metrics such as prediction accuracy, efficiency, and stability. Notably, on the GEFCom2014 dataset, FLOP is reduced by over 48.8%, inference time is shortened by more than 46.7%, and MAPE is improved by 39%. The proposed method significantly enhances the reliability, stability, and cost-effectiveness of smart grids, which facilitates risk assessment optimization and operational planning under the context of information management for smart grid systems.

Visibility forecast in Jiangsu province based on the GCN-GRU model

Low visibility weather easily leads to traffic accidents, posing threats to human life and property. To accurately forecast visibility, we conduct an empirical study focusing on Jiangsu Province. Firstly, we collect the monitoring data from meteorological stations and environmental stations for 2017-2018. Secondly, we analyze the changes in visibility from both spatial and temporal perspectives. Next, the maximum Relevance Minimum Redundancy (mRMR) algorithm is employed to select factors affecting visibility, finding that humidity and PM2.5\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$PM_{2.5}$$\\end{document} concentrations are the primary factors. Finally, we propose GCN-GRU (Graph Convolutional Network and Gated Recurrent Unit) model for short-term visibility forecasting, which employs GCN to capture the interactions between stations and uses GRU to learn the interactions between times. Experimental results indicate that GCN-GRU outperforms the standalone GRU model and three machine learning models regarding 6-hour visibility forecasting. Compared to the best competitor, GCN-GRU achieves an average increase of 3.32% in Correlation Coefficient (CORR), a decrease of 17.52% in Root Mean Square Error (RMSE), a reduction of 26.62% in Mean Absolute Percentage Error (MAPE), and a decline of 16.53% in Mean Absolute Error (MAE).