Forecasting Results Research Articles

Electric Vehicle Charging Load Forecasting Based on K-Means++-GRU-KSVR

The accurate short-term forecasting of an electric vehicle (EV) load is crucial for the reliable operation of a power grid and for effectively reducing energy consumption. Due to the fluctuations in EV charging loads, particularly the significant load variation between commercial and non-commercial areas, global models often suffer from prediction errors when forecasting loads. To address this issue, this paper proposes a regional forecasting method based on K-means++ clustering and deep learning algorithms. First, the K-means++ algorithm was used to partition the data into different regions, and an independent load-forecasting model was established for each region. Then, a combination of kernel support vector regression (KSVR) and gated recurrent unit (GRU) models was used to handle nonlinear features and time-dependent data, where particle swarm optimization (PSO) further optimized the model parameters to improve the forecasting accuracy. Finally, a weighted summation method was used to integrate the forecast results from each region, resulting in a more accurate overall load forecast. The experimental results show that the proposed model provided better prediction performance by capturing the spatiotemporal characteristics of the EV charging load, effectively addressing the challenges posed by regional differences, and outperforming the single-model forecasts.

INFLUENCE OF ANOMALOUS VALUES ON THE ACCURACY OF FORECASTING LOSSES IN DISTRIBUTION NETWORKS

The relevance of the study is determined by modern trends in managing the operation modes of distribution electrical networks using Smart Grid technologies, as well as the need to reduce the costs incurred by distribution system operators for purchasing electricity. Accurate load forecasting results at network nodes for different forecasting horizons are crucial for this purpose. Sudden changes in network topology can increase the errors in loss forecasts as a single time series, negatively impacting network management efficiency and increasing the costs of electricity procurement to cover losses. The study proposes using forecasting methods based on artificial neural networks for the calculation and prediction of electricity losses, along with a comparison of these methods. The calculations were performed using data from one of Ukraine's distribution system operators, and the test electrical network was adapted based on the CIGRE scheme for modeling electricity losses. Since the nodal load data contained gaps and anomalies, a two-step data analysis algorithm was employed using the DBSCAN clustering method for detection and correction. As a result of loss calculations based on cleaned data, the error was reduced threefold compared to calculations based on load factors. Applying data analysis methods and forecasting methods based on artificial neural networks significantly improves the accuracy of loss calculations and minimizes errors.

Enhanced Sequence-to-Sequence Attention-Based PM2.5 Concentration Forecasting Using Spatiotemporal Data

Severe air pollution problems continue to increase because of accelerated industrialization and urbanization. Specifically, fine particulate matter (PM2.5) causes respiratory and cardiovascular diseases, and according to the World Health Organization (WHO), millions of premature deaths and significant health burdens annually. Therefore, PM2.5 concentration forecasting is essential. This study proposed a method to forecast PM2.5 concentrations one hour after using Sequence-to-Sequence Attention (Seq2Seq-attention). The proposed method selects neighboring stations using minimum redundancy maximum relevance (mRMR) and integrates their data using a convolutional neural network (CNN). The proposed attention score and Seq2Seq are used on the integrated data to forecast PM2.5 concentration after one hour. The performance of the proposed method is validated through two case studies. The first comparison evaluated the performance of the conventional attention score against the proposed attention scores. The second comparison evaluated the forecasting results with and without considering neighboring stations. The first study showed that the proposed attention score improved the performance index (Root Mean Square Error (RMSE): 3.48%p, Mean Absolute Error (MAE): 8.60%p, R2: 0.49%p, relative Root Mean Square Error (rRMSE): 3.64%p, Percent Bias (PBIAS): 59.29%p). The second case study showed that considering neighboring stations’ data can be more effective in forecasting than considering that of a standalone station (RMSE: 5.49%p, MAE: 0.51%p, R2: 0.67%p, rRMSE: 5.44%p, PBIAS: 46.56%p). This confirmed that the proposed method can effectively forecast the PM2.5 concentration after one hour.

Analysis of Optimal Stock Performance Using the Discounted Cash Flow Method and Stock Price Forecasting Using the Holt-Winters Method

The high liquidity of PT Perusahaan Gas Negara Tbk shares and significant fluctuations in share prices create uncertainty that requires in-depth analysis. Stock performance analysis is carried out with 2 stages in outline, namely the stages of fundamental analysis and technical analysis. Fundamental analysis is carried out to analyze optimal stock performance, one of which is by using the discounted cash flow (DCF) method. Technical analysis is used to determine the condition of stock performance in the future by forecasting stock prices using the Holt-Winters forecasting method. The objectives of this study are to analyze optimal stock performance, forecast stock prices, and evaluate forecasting results. The data used is PGN's 2023 annual report and daily data on PGN's stock price for the period January 1, 2019, to December 31, 2023, totalling 1,231 data. The results of the optimal stock performance analysis show that PGN's stock performance is declared optimal with an intrinsic value of 3,149.18, which is greater than the current stock price (undervalued). The results of stock price forecasting show that the forecasting results follow the actual data pattern, with an accuracy value using MAPE (mean absolute percentage error ) of 10.9%, it is stated that the forecasting performance has performed well.

Semi-parametric financial risk forecasting incorporating multiple realized measures

A semi-parametric joint Value-at-Risk (VaR) and Expected Shortfall (ES) forecasting framework employing multiple realized measures is developed. The proposed framework extends the realized exponential GARCH model to be semi-parametrically estimated, via a joint loss function, whilst extending existing quantile time series models to incorporate multiple realized measures. A quasi-likelihood is built, employing the asymmetric Laplace distribution that is directly linked to a joint loss function, which enables Bayesian inference for the proposed model. An adaptive Markov Chain Monte Carlo method is used for the model estimation. The empirical section evaluates the performance of the proposed framework with six stock markets from January 2000 to June 2022, covering the period of COVID-19. Three realized measures, including 5-minute realized variance, bi-power variation, and realized kernel, are incorporated and evaluated in the proposed framework. One-step-ahead 1% and 2.5% VaR and ES forecasting results of the proposed model are compared to a range of parametric and semi-parametric models, lending support to the effectiveness of the proposed framework.

Stock Price Prediction System LSTM Based on Deep Learning

Stock price prediction is a highly complex task due to the inherent volatility and non-linear patterns of financial markets. Recent advancements in deep learning, particularly Long Short-Term Memory (LSTM) networks, have yielded promising results in time series forecasting. This paper provides an in-depth analysis of LSTM models applied to the stock price prediction of major technology companies, including Apple (AAPL), Tesla (TSLA), Microsoft (MSFT), and Nvidia (NVDA). The study utilizes historical stock data to train and evaluate LSTM models, comparing their performance against various other regression models such as Linear Regression, Support Vector Regression (SVR), Decision Tree Regression, and Gradient Boosting Decision Trees (GBDT).The results demonstrate that the LSTM model outperforms traditional models, particularly in its ability to capture long-term dependencies and manage complex, volatile stock data. Among the companies analyzed, the LSTM model achieved the most accurate predictions for Apple, as indicated by the lowest Mean Squared Error (MSE). Tesla's predictions, while less accurate due to high volatility, still showed improvement compared to other models. In conclusion, the LSTM network proved to be the most effective method for stock price prediction in this study, particularly excelling in forecasting long-term trends and reducing prediction errors for volatile stocks.

AUTOMATED MULTI-MODEL PREDICTION AND EVALUATION FOR CONNECTING RAINFALL PREDICTION INFORMATION AND SINGLE-YEAR OPERATIONAL PLAN OF LAHOR-SUTAMI DAM

There is a gap between existing climate information and the needs of annual dam operational planning. This study aims to demonstrate that the percentile approach currently used for planning is not optimal, especially now that automation has become more accessible. The purpose of this study is to design an automated forecasting and evaluation system based on 36 10-days rainfall projections using a multi-model approach. This approach comprises a percentile, ARIMA, ECMWF+ARIMA, IOD DMI regression, ERSST regression, and ensemble methods models. Additionally, this study aims to demonstrate how a verified, multi-model-based rainfall forecast can provide more reliable assurance for the annual operational planning of Lahor-SutamiDam, simulated operationally in November 2022 for the 2022/2023 planning cycle. Data utilized include historical 10-days rainfall data from 1991 to 2023, ECMWF raw and corrected model outputs, Nino-Dipole index, and global sea surface temperature. The verification method employs four criteria based on MAE and fit index. An operational simulation approach is used for training-testing period segmentation, while a 10-year window is applied to account for possible climate-change-induced shifts in relationships. Single linear regression is used to avoid overfitting. The automation system was developed using R-Statistics. Results indicate that the current approach is only optimal for 58% of locations. Superior methods identified include ECMWFcorrected, ERSST regression, and Ensemble models. A case study for 2022/2023 demonstrates that the forecast results outperform the existing plan for at least 78% of the projected periods.

Comparative Time Series Analysis of SARIMA, LSTM, and GRU Models for Global SF6 Emission Management System

To maintain the balance of the atmosphere, the amount of change in greenhouse gas emissions must be under control. In order to create a management system and take forward-looking steps in this regard, there is no concrete data other than prediction models today. The success of prediction methods is better understood by comparing multiple methods. This research estimates the changes in the emissions of Sulfur Hexafluoride gas (SF6) in the atmosphere using Seasonal Autoregressive Integrated Moving Average Model (SARIMA), Long-Short Term Memory Neural Network (LSTM) and Gated Recurrent Unit (GRU) forecast models and compares their accuracies. Focusing on monthly SF6 emission values between 1998; 2023, time series analysis was performed to predict future emission figures. The actual values and forecast results were compared and evaluated with performance criteria such as R2, RMSE, NSE, MAE and MAPE%. The findings of this research highlight a continious upward trend in SF6 emissions and project that emission levels could approximately double from current levels by 2050. During the analysis process, all three methods performed well in estimating global SF6 gas emissions. The LSTM model generally outperformed SARIMA and GRU models, having the lowest MAPE (0.003%), MAE (0.0003), RMSE (0.0003), and R2 (1) values. It also exhibited very high predictive success with an NSE value of 0.9991. Therefore, it was determined to be the most suitable estimation method with the least error. The aim of this study is to contribute scientifically to the reduction strategies of SF6 emissions.

Dissipation Scaled Internal Wave Drag in a Global Heterogeneously Coupled Internal/External Mode Total Water Level Model

AbstractThis study showcases a global, heterogeneously coupled total water level system wherein salinity and temperature outputs from a coarser‐resolution (12 km) ocean general circulation model are used to calculate density‐driven terms within a global, higher‐resolution (2.5 km) depth‐averaged total water level model. We demonstrate that the inclusion of baroclinic forcing in the barotropic model requires modification of the internal wave drag term to prevent excess degradation of tidal results compared to the barotropic model. By scaling the internal tide dissipation by an easy to calculate dissipation ratio, the resulting heterogeneously coupled model has complex root mean square errors (RMSE) of 2.27 cm in the deep ocean and 12.16 cm in shallow waters for the tidal constituent. While this represents a 10%–20% deterioration as compared to the barotropic model, the improvements in total water level prediction more than offset this degradation. Global median RMSE compared to observations of total water levels, 30‐day sea levels, and non‐tidal residuals improve by 1.86 (18.5%), 2.55 (42.5%), and 0.36 (5.3%) cm respectively. The drastic improvement in model performance highlights the importance of including density‐driven effects within global hydrodynamic models and will help to improve the results of both hindcasts and forecasts in modeling extreme and nuisance flooding. With only an 11% increase in model run time compared to the fully barotropic total water level model, this approach paves the way for high resolution coastal water level and flood models to be used alongside climate models, improving operational forecasting of total water levels.

Prediction of Summer Precipitation via Machine Learning with Key Climate Variables：A Case Study in Xinjiang, China

Study region: Xinjiang is located in the mid-latitude region of Eurasia in northwestern China. Precipitation is predominantly concentrated in northern Xinjiang, while southern Xinjiang remains comparatively arid. Summer precipitation accounts for 54.4% of the annual total. Study focus: This study aims to develop a machine learning model to predict summer precipitation (June–August) in XJ and explore the key variables contributing to summer precipitation in this region. The SHapley Additive exPlanations method was integrated with an extreme tree model to quantify the contributions of variables towards precipitation. Artificial neural networks, support vector machines, and extreme gradient boosting were considered to predict summer precipitation. To train the ML model, we used precipitation data from 1961 to 2012, whilst the forecast results from 2013 to 2017 were used for validation.New hydrological insights for the regions: The results demonstrated that the ANN model achieved robust performance during both the training and validation periods. For Northern and Southern XJ, the Mean Absolute Error and Root Mean Square Error of the ANN model were 15.34 (20.40) and 23.21 (30.01), respectively. The SHAP analysis showed that in the context of Northern Xinjiang, the Niño B Sea Surface Temperature Anomaly, Western Pacific Subtropical High Intensity, Pacific Subtropical High Intensity, and Multivariate ENSO Index play crucial roles in the prediction of summer precipitation. In Southern Xinjiang, the South China Sea Subtropical High Intensity, South China Sea Subtropical High Area, Western Pacific Warm Pool Strength, and Atlantic multidecadal oscillation have emerged as key variables affecting summer precipitation forecasting.

Green hydrogen blending in natural gas: A global review and a local analysis on Türkiye based on greenhouse gas emission reduction targets

In this study, Türkiye's natural gas consumption till 2030 is forecasted based on the greenhouse gas emissions reduction targets announced by the Turkish President. Two novel semi-empirical per capita based models are generated for forecasting. It is estimated that Türkiye's natural gas consumption in 2030 could reach 65.5 billion m3, and at this level nearly 650 million m3 of green hydrogen could be needed for 1.0% (v/v) blending. Root mean squared error (RMSE) and mean absolute percentage error (MAPE) values of forecast generated by Model 2 are estimated as 3.6 and 5.5%, respectively. These RMSE and MAPE values indicate high accuracy. The forecasting results of Model 2 are also compared with highly cited forecasts from the literature. The accuracy of fit with these forecasts changed between 90.7%–99.9%, which might be considered as an indication of model success. Finally, it is believed that this study could further be adapted by other researchers for estimating local or national natural gas consumption and potential green hydrogen requirements for blending conditional that historic geographical per capita data is available and associated addition/availability factors are calculated based on current circumstances.

A Non-stationary Transformer model for power forecasting with dynamic data distillation and wake effect correction suitable for large wind farms

Reliable, high-precision short-term power forecasting is crucial for ensuring power safety and improving wind energy utilization. However, the randomness and non-stationary features of wind present significant challenges in enhancing the precision and efficiency of power forecasts in large-scale wind farm (WF). Previous research often fails to adaptively enhance the original data’s features and neglects the impact of wake effects between wind turbines (WTs), leading to reduced forecasting accuracy. In this paper, a novel method is proposed for power forecasting based on non-stationary Transformer model, which also incorporates dynamic data distillation and wake effect correction to improve forecasting performance. In this proposed method, a non-stationary Transformer model is proposed for extracting features from supervisory control and data acquisition (SCADA) data, which significantly improved the feature extraction capability for non-stationary SCADA data. A dynamic data distillation technique is proposed to remove redundant data and enhance dataset quality, and the wake effect is developed to correct forecasting results and reducing error sources. Dynamic data distillation addresses the loss of data features caused by dataset preprocessing, while wake correction reduces the forecasting errors caused by the wake effect between WTs. The SCADA datasets are used from northwest and northeast China WFs, and the forecasting results demonstrate the effectiveness and superiority of the proposed method. Ablation experiments further confirm that dynamic data distillation and wake effect effectively enhance wind power forecasting accuracy.

Computing Method Applied for Simulation and Forecast of Hydrophysical Fields in the Southeastern Black Sea

In this paper, a numerical regional model of the Black Sea hydrodynamics with a spatial resolution of 1 km is applied to simulate and forecast the mesoscale circulation and thermohaline structure in the southeastern part of the Black Sea. The regional model is based on a nonlinear nonstationary system of differential equations in z coordinates, describing the evolution of three-dimensional fields of currents, temperature, salinity, and density. The solution of the equation system is based on the use of finite-difference methods, in particular, on the method of multicomponent splitting of the differential operator of the original problem into simpler operators. To illustrate the implementation of the numerical model, the paper presents the calculated fields of flow, temperature, and salinity for the summer season of 2020 under real atmospheric forcing derived from the atmospheric model SCIRON. The influence of basin-scale processes on regional processes was taken into account by boundary conditions on the liquid boundary separating the regional area from the open part of the sea basin. A comparison of the forecast results with available satellite data shows that the model reproduces well the basic peculiarities of hydrophysical fields.

Precipitation Prediction in Suqian City, Jiangsu Province of China Using LSTM Based on Grey Wolf Optimizer Algorithm

To enhance urban planning and disaster management in the context of global climate change, we focused on precipitation forecasting in Suqian City, Jiangsu Province, and established a Long Short-Term Memory (LSTM) model optimized by the Grey Wolf Optimizer (GWO) algorithm. Firstly, we collected five years of precipitation data to ensure a solid foundation for model training. Secondly, we integrated the GWO algorithm to optimize the LSTM model parameters, thereby improving prediction accuracy. Through data preprocessing, model establishment, and validation, we successfully constructed a precipitation forecasting model tailored for both rainy and non-rainy seasons in Suqian. Lastly, utilizing this model, we predicted the precipitation volume for the upcoming 12 months in Suqian and proposed targeted countermeasures and suggestions based on the forecast results to guide urban planning and disaster management efforts, ensuring that Suqian can effectively address the challenges posed by future precipitation changes. Additionally, by combining actual conditions with predictive data, we refined and optimized Suqian's precipitation management strategies.

A Predictive Analysis of the Organized Retail Market in India Using Holt-Winter Exponential Smoothing Technique

The study aims to predict the size of the Indian organized retail market for future years. Most previous studies provided descriptive insights into the development of the organized retail industry without specifying any forecasting methods and approaches used in their predictions. This study attempts to employ the Holt-Winter exponential smoothing method for analyzing the Indian organized retail sector, a novel approach in this domain. The investigation began with a sales forecast for the preceding twenty-one years of data using different combinations of α and β coefficients. The best model was selected based on the α and β values that yielded the minimum statistical errors, as measured by MAD, MAPE, and MSE. The forecast results indicate a projected CAGR of 13.23% for the Indian organized retail market size over the next six years. The findings will provide retail marketers the latest market trends to inform sound business planning.

Short Term Prediction of Urban Traffic Flow based on Machine Learning Algorithms

With the increasing per capita car ownership worldwide, existing transportation facilities are unable to fully meet people's travel needs. The massive traffic flow can lead to traffic congestion, so predicting traffic flow can play a crucial role in urban traffic management. This study predicts the westbound traffic flow data of the Minnesota Department of Transportation (MN DoT) ATR 301 station on Interstate 94 in the United States for 28 consecutive days using a Long Short-Term Memory Network (LSTM) data prediction model. The Random Forest is utilized to analyze the association between attributes and the historical data has been separated into 1-hour intervals. The highway displays a bimodal pattern on weekdays and a unimodal pattern on holidays, according to the final forecast results. Furthermore, after making the necessary adjustments to the parameters, the simulated trend closely resembles the real value, proving that LSTM can be used to model short-term traffic flow. Accurately predicting urban traffic flow can make the management of urban traffic management systems more comprehensive and provide citizens with higher quality travel planning references.

Forecasting Gate-Front Water Levels Using a Coupled GRU–TCN–Transformer Model and Permutation Entropy Algorithm

Water level forecasting has significant impacts on transportation, agriculture, and flood control measures. Accurate water level values can enhance the safety and efficiency of water conservancy hub operation scheduling, reduce flood risks, and are essential for ensuring sustainable regional development. Addressing the nonlinearity and non-stationarity characteristics of gate-front water level sequences, this paper introduces a gate-front water level forecasting method based on a GRU–TCN–Transformer coupled model and permutation entropy (PE) algorithm. Firstly, an analysis method combining Singular Spectrum Analysis (SSA) and Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) is used to separate the original water level data into different frequency modal components. The PE algorithm subsequently divides each modal component into sequences of high and low frequencies. The GRU model is applied to predict the high-frequency sequence part, while the TCN–Transformer combination model is used for the low-frequency sequence part. The forecasting from both models are combined to obtain the final water level forecasting value. Multiple evaluation metrics are used to assess the forecasting performance. The findings indicate that the combined GRU–TCN–Transformer model achieves a Mean Absolute Error (MAE) of 0.0154, a Root Mean Square Error (RMSE) of 0.0205, and a Coefficient of Determination (R2) of 0.8076. These metrics indicate that the model outperforms machine learning Support Vector Machine (SVM) models, GRU models, Transformer models, and TCN–Transformer combination models in forecasting performance. The forecasting results have high credibility. This model provides a new reference for improving the accuracy of gate-front water level forecasting and offers significant insights for water resource management and flood prevention, demonstrating promising application prospects.

Research on Forecasting Sales of Pure Electric Vehicles in China Based on the Seasonal Autoregressive Integrated Moving Average–Gray Relational Analysis–Support Vector Regression Model

Aiming to address the complexity and challenges of predicting pure electric vehicle (EV) sales, this paper integrates a time series model, support vector machine and combined model to forecast EV sales in China. Firstly, a seasonal autoregressive integrated moving average (SARIMA) model was constructed using historical EV sales data, and the model was trained on sales statistics to obtain forecasting results. Secondly, variables that were highly correlated with sales were analyzed using gray relational analysis (GRA) and utilized as input parameters for the support vector regression (SVR) model, which was constructed to optimize sales predictions for EVs. Finally, a combined model incorporating different algorithms was verified against market sales data to explore the optimal sales prediction approach. The results indicate that the SARIMA-GRA-SVR model with the squared prediction error and inverse method achieved the best predictive performance, with MAPE, MAE and RMSE values of 12%, 1.45 and 2.08, respectively. This empirical study validates the effectiveness and superiority of the SARIMA-GRA-SVR model in forecasting EV sales.

Assessing Project Resilience Through Reference Class Forecasting and Radial Basis Function Neural Network

A project needs to be able to anticipate potential threats, respond effectively to adverse events, and adapt to environmental changes. This overall capability is known as project resilience. In order to make efficient project decisions when the project is subjected to disruption, such as adjusting the project budget, reformulating the work plan, and rationalizing the allocation of resources, it is necessary to quantitatively understand the level of project resilience. Therefore, this paper develops a novel approach for forecasting project performance, illustrating the changes in performance levels during the disruption and recovery phases of a project and thus quantitatively assessing project resilience. While there are several methods for assessing project resilience in existing research, the majority of assessment approaches originate from within projects and are highly subjective, which makes it difficult to objectively reflect the level of project resilience. Moreover, the availability of project samples is limited, which makes it difficult to forecast the level of project performance. In view of the fact that the Reference Class Forecasting (RCF) technique avoids subjectivity and the Radial Basis Function (RBF) neural network is known to be better at forecasting small sample datasets, this paper therefore combines the RCF technique and the RBF neural network to construct a model that forecasts the project performance of the current project after experiencing a disruption, further assessing the level of the project resilience. Specifically, this paper first presents a conceptual model of project resilience assessment; subsequently, an RBF neural network model that takes into account project budget, duration, risk level of disruption, and performance before disruption based on the RCF technique is developed to forecast project performance after experiencing disruption; and finally, the level of project resilience is assessed through calculating the ratio of recovery to loss of project performance. The model is trained and validated using 64 completed construction projects with disruptions as the datasets. The results show that the average relative errors between the forecast results of schedule performance index (SPI) and the real values are less than 5%, and the R2 of the training set and the testing set is 0.991 and 0.964, respectively, and the discrepancy between the forecasted and real values of project resilience is less than 10%. These illustrate that the model performs well and is feasible for quantifying the level of project resilience, clarifying its impact on project disruption and recovery situations, and facilitating the decision-makers of the project to make reasonable decisions.

Prediction of provincial Digital Economy Development Index based on grey combination forecasting model

PurposeIn many instances, the data exhibits periodic and trend characteristics. However, indices like the Digital Economy Development Index (DEDI), which pertains to science, technology, policy and economy, may occasionally display erratic behaviors due to external influences. Thus, to address the unique attributes of the digital economy, this study integrates the principle of information prioritization with nonlinear processing techniques to accurately forecast rapid and anomalous data.Design/methodology/approachThe proposed method utilizes the new information priority GM(1,1) model alongside an optimized BP neural network model achieved through the gradient descent technique (GD-BP). Initially, the provincial Digital Economic Development Index (DEDI) is derived using the entropy weight approach. Subsequently, the original GM(1,1) time response equation undergoes alteration of the initial value, and the time parameter is fine-tuned using Particle Swarm Optimization (PSO). Next, the GD-BP model addresses the residual error. Ultimately, the prediction outcome of the grey combination forecasting model (GCFM) is derived by merging the findings from both the NIPGM(1,1) model and the GD-BP approach.FindingsUsing the DEDI of Jiangsu Province as a case study, researchers demonstrate the effectiveness of the grey combination forecasting model. This model achieves a mean absolute percentage error of 0.33%, outperforming other forecasting methods.Research limitations/implicationsFirst of all, due to the limited data access, it is impossible to obtain a more comprehensive dataset related to the DEDI of Jiangsu Province. Secondly, according to the test results of the GCFM from 2011 to 2020 and the forecasting results from 2021 to 2023, it can be seen that the results of the GCFM are consistent with the actual development situation, but it cannot guarantee the correctness of the long-term forecasting, so the combination forecasting model is only suitable for short-term forecasting.Originality/valueThis article proposes a grey combination prediction model based on the principles of new information priority and nonlinear processing.