Short-term Forecasting Model Research Articles

Short-term wind speed interval prediction using improved quality-driven loss based gated multi-scale convolutional sequence model

Efficient estimation of the uncertainty associated with wind speed forecast is crucial for evaluating wind farms' power quality and operation. Typically, the performance of prediction interval (PI) generating models; is restricted in terms of computational efficiency inheritably from the sequential data processing; whereas restrictions in forecast quality are derived from the PI generation techniques. This paper presents an efficient Gated Multi-Scale Convolutional Sequence Model (GMSCSM) to forecast wind speed PIs. GMSCSM while conserving the ‘recurrence’ of LSTMs also offers ‘parallel input’ advantage of CNNs for better computational efficiency which is highly desirable for short-term forecasting models. In addition, capturing features at various scales in the sequence, GMSCSM learns both local details and global context which is vital for multi-horizon forecasts. The model generates quality PIs utilizing an improved quality-driven loss which we proposed by invoking calibration assessment in its existing definition. Forecasts generated for eight different datasets obtained from two different wind farms show an improvement of 30 % and 6 % in the average coverage width criterion index while reducing the model training time to nearly half and one third of the respective values obtained from traditional and LSTM based models which showcases the proposed model's excellent prediction capability and efficiency.

Evaluation of Various Deep Learning Models for Short-Term Solar Forecasting in the Arctic using a Distributed Sensor Network

Evaluation of Various Deep Learning Models for Short-Term Solar Forecasting in the Arctic using a Distributed Sensor Network

Research on optimization of improved short-term load composite forecasting model based on AM–CNN–Bi–LSTM

Accurate load prediction is a prerequisite for the design, operation, scheduling, and management of energy systems. In the context of the development of smart grids, the extensive integration of highly volatile distributed energy generation into the power system has brought new challenges to the accuracy, reliability, real-time performance, and intelligence of short-term load forecasting. Therefore, this article proposes a novel short-term power load composite prediction model based on AM–CNN–Bi–LSTM. First, CNN is used to extract relevant feature quantities of power load coupling characteristics. Then, AM is used to evaluate the importance of the feature data, highlighting the features that have a greater impact on the prediction results. Finally, the Bi-LSTM network captures bidirectional temporal information from multiple time steps for prediction. Taking one year of measured data as an example, the error comparison of the prediction results of the composite prediction model overlay shows that compared with other models, the composite prediction model has improved prediction accuracy, feature extraction, generalization ability, and other aspects. The research results improve the accuracy of short-term power load forecasting while providing effective model references for decision-making in power system optimization scheduling, safe operation, and reasonable pricing.

Seasonality of influenza-like illness and short-term forecasting model in Chongqing from 2010 to 2022

BackgroundInfluenza-like illness (ILI) imposes a significant burden on patients, employers and society. However, there is no analysis and prediction at the hospital level in Chongqing. We aimed to characterize the seasonality of ILI, examine age heterogeneity in visits, and predict ILI peaks and assess whether they affect hospital operations.MethodsThe multiplicative decomposition model was employed to decompose the trend and seasonality of ILI, and the Seasonal Auto-Regressive Integrated Moving Average with exogenous factors (SARIMAX) model was used for the trend and short-term prediction of ILI. We used Grid Search and Akaike information criterion (AIC) to calibrate and verify the optimal hyperparameters, and verified the residuals of the multiplicative decomposition and SARIMAX model, which are both white noise.ResultsDuring the 12-year study period, ILI showed a continuous upward trend, peaking in winter (Dec. - Jan.) and a small spike in May-June in the 2–4-year-old high-risk group for severe disease. The mean length of stay (LOS) in ILI peaked around summer (about Aug.), and the LOS in the 0–1 and ≥ 65 years old severely high-risk group was more irregular than the others. We found some anomalies in the predictive analysis of the test set, which were basically consistent with the dynamic zero-COVID policy at the time.ConclusionThe ILI patient visits showed a clear cyclical and seasonal pattern. ILI prevention and control activities can be conducted seasonally on an annual basis, and age heterogeneity should be considered in the health resource planning. Targeted immunization policies are essential to mitigate potential pandemic threats. The SARIMAX model has good short-term forecasting ability and accuracy. It can help explore the epidemiological characteristics of ILI and provide an early warning and decision-making basis for the allocation of medical resources related to ILI visits.

Wind-Speed Multi-Step Forecasting Based on Variational Mode Decomposition, Temporal Convolutional Network, and Transformer Model

Reliable and accurate wind-speed forecasts significantly impact the efficiency of wind power utilization and the safety of power systems. In addressing the performance enhancement of transformer models in short-term wind-speed forecasting, a multi-step prediction model based on variational mode decomposition (VMD), temporal convolutional network (TCN), and a transformer is proposed. Initially, the Dung Beetle Optimizer (DBO) is utilized to optimize VMD for decomposing non-stationary wind-speed series data. Subsequently, the TCN is used to extract features from the input sequences. Finally, the processed data are fed into the transformer model for prediction. The effectiveness of this model is validated by comparison with six other prediction models across three datasets, demonstrating its superior accuracy in short-term wind-speed forecasting. Experimental findings from three distinct datasets reveal that the developed model achieves an average improvement of 52.1% for R2. To the best of our knowledge, this places our model at the leading edge of wind-speed prediction for 8 h and 12 h forecasts, demonstrating MSEs of 1.003 and 0.895, MAEs of 0.754 and 0.665, and RMSEs of 1.001 and 0.946, respectively. Therefore, this research offers significant contributions through a new framework and demonstrates the utility of the transformer in effectively predicting short-term wind speed.

Interpretable short-term carbon dioxide emissions forecasting based on flexible two-stage decomposition and temporal fusion transformers

Carbon emissions play a pivotal role in exacerbating the global warming crisis and driving climate change. Accurate and consistent projections of carbon emissions are of utmost importance for nations worldwide, as they shape emission reduction strategies and expedite the pursuit of carbon peaking and carbon neutrality goals. While previous studies have focused on hybrid methodologies for carbon emission forecasting, yielding commendable predictive performance, these approaches often overlook the significance of internal interpretability within the forecasting models. In light of this gap, this study introduces a groundbreaking and elucidating hybrid carbon emission forecasting model that amalgamates the two-stage layer decomposition method, adaptive differential evolution with optional external archive (JADE), and temporal fusion transformers (TFT). To begin with, a series of sub-sequences is derived by employing a flexible two-stage decomposition strategy, which leverages a linear-nonlinear decomposition criterion to thoroughly extract the fluctuating characteristics inherent in the carbon emission series. Subsequently, the JADE algorithm intelligently and efficiently optimizes the parameter combinations within the TFT model, ensuring both stability and reliability of the prediction framework. Empirical investigations conclusively demonstrate the remarkable applicability and efficacy of the proposed model in short-term carbon emission forecasting. By delving into the interpretability of the model's results, the study enhances the capacity of policymakers to devise well-informed strategies based on comprehensive insights gleaned from the forecasting process.

A hybrid prediction interval model for short-term electric load forecast using Holt-Winters and Gate Recurrent Unit

Short-term load forecasting (STLF) is essential for power system planning and operation decision-making. Researchers in this field have devoted themselves to building point prediction models in recent years. However, traditional point forecasting treats the forecast outcome as a deterministic variable. Due to the inherent complexity, volatility, and instability of power load, deviations in traditional point forecasting methods are inevitable and significant. Considering the difficulty of accurate point prediction, interval prediction can tolerate increased uncertainty and provide more information for actual operation decision-making. In order to solve this problem, we proposed a novel hybrid model based on Holt-Winters (HW) method and gated recurrent unit (GRU) network for short-term load interval forecasting. First, considering the factors affecting the load trend, the weather type, date type, and historical load data are processed and normalized. Then, the raw data is decomposed into linear components and nonlinear residuals using a moving average (MA) filter. Next, the HW method establishes a linear prediction model to predict the linear component. Finally, an interval prediction model based on gated recurrent unit neural network is established by taking linear prediction results, nonlinear residuals, weather types, date types, and original data as inputs. In order to verify the performance of the proposed hybrid method, based on the data set provided by the 2022 "Teddy Cup" data mining challenge, taking 15-minute load data as an example, the traditional model and the advanced interval prediction model were compared. The results show that the proposed model is a high-quality method. Compared with models built by other methods, it has a higher prediction interval coverage probability and a narrower prediction interval width.

Short-term prediction of photovoltaic power generation based on ICEEMDAN-SE-GAPSO-LSTM

This study proposes an improved adaptive noise-complete ensemble empirical mode decomposition (ICEEMDAN), sample entropy (SE), and genetic particle swarm optimization (GAPSO) algorithm-based short-term solar power forecast model. The photovoltaic power data is first decomposed using the ICEEMDAN algorithm to produce a number of eigenmode components with various properties. The sample entropy of each component is then calculated, and the components with similar sample entropy values are combined to create new modal components. These new modal components are then input into the GAPSO-optimized LSTM model for prediction, and the prediction results of each component are summed and reconstructed to produce the final prediction. The results completely validate the efficacy and dependability of the suggested method, using the measured data from a photovoltaic power station in Xinjiang, China as an example.

Combining Recurrent Neural Network and Sigmoid Growth Models for Short-Term Temperature Forecasting and Tomato Growth Prediction in a Plastic Greenhouse

Compared with open-field cultivation, greenhouses can provide favorable conditions for crops to grow through environmental control. The prediction of greenhouse microclimates is a way to reduce environmental monitoring costs. This study used several recurrent neural network models, including long short-term memory (LSTM), gated recurrent unit, and bi-directional LSTM, with varying numbers of hidden layers and units, to establish a temperature forecasting model for a plastic greenhouse. To assess the generalizability of the proposed model, the most accurate forecasting model was used to predict the temperature in a greenhouse with different specifications. During a test period of four months, the best proposed model’s R2, MAPE, and RMSE values were 0.962, 3.216%, and 1.196 °C, respectively. Subsequently, the outputs of the temperature forecasting model were used to calculate growing degree days (GDDs), and the predicted GDDs were used as an input variable for the sigmoid growth models to simulate the leaf area index, fresh fruit weight, and aboveground dry matter of tomatoes. The R2 values of the growth model for the three growth traits were all higher than 0.80. Moreover, the fitted values and the parameter estimates of the growth models were similar, irrespective of whether the observed GDD (calculated using the actual observed data) or the predicted GDD (calculated using the temperature forecasting model output) was used. These results indicated that the proposed temperature forecasting model could accurately predict the temperature changes inside a greenhouse and could subsequently be used for the growth prediction of greenhouse tomatoes.

Analysis of Statistical and Deep Learning Techniques for Temperature Forecasting

Abstract: In the field of meteorology, temperature forecasting is a significant task as it has been a key factor in industrial, agricultural, renewable energy, and other sectors. High accuracy in temperature forecasting is needed for decision-making in advance. Since temperature varies over time and has been studied to have non-trivial long-range correlation, non-linear behavior, and seasonal variability, it is important to implement an appropriate methodology to forecast accurately. In this paper, we have reviewed the performance of statistical approaches such as AR and ARIMA with RNN, LSTM, GRU, and LSTM-RNN Deep Learning models. The models were tested for short-term temperature forecasting for a period of 48 hours. Among the statistical models, the AR model showed notable performance with a r2 score of 0.955 for triennial 1 and for the same, the Deep Learning models also performed nearly equal to that of the statistical models and thus hybrid LSTM-RNN model was tested. The hybrid model obtained the highest r2 score of 0.960. The difference in RMSE, MAE and r2 scores are not significantly different for both Statistical and Vanilla Deep Learning approaches. However, the hybrid model provided a better r2 score, and LIME explanations have been generated for the same in order to understand the dependencies over a point forecast. Based on the reviewed results, it can be concluded that for short-term forecasting, both Statistical and Deep Learning models perform nearly equally.

Predictive Analytics of Air Temperature in Alaskan Permafrost Terrain Leveraging Two-Level Signal Decomposition and Deep Learning

Local weather forecasts in the Arctic outside of settlements are challenging due to the dearth of ground-level observation stations and high computational costs. During winter, these forecasts are critical to help prepare for potentially hazardous weather conditions, while in spring, these forecasts may be used to determine flood risk during annual snow melt. To this end, a hybrid VMD-WT-InceptionTime model is proposed for multi-horizon multivariate forecasting of remote-region temperatures in Alaska over short-term horizons (the next seven days). First, the Spearman correlation coefficient is employed to analyze the relationship between each input variable and the forecast target temperature. The most output-correlated input sequences are decomposed using variational mode decomposition (VMD) and, ultimately, wavelet transform (WT) to extract time-frequency patterns intrinsic in the raw inputs. The resulting sequences are fed into a deep InceptionTime model for short-term forecasting. This hybrid technique has been developed and evaluated using 35+ years of data from three locations in Alaska. Different experiments and performance benchmarks are conducted using deep learning models (e.g., Time Series Transformers, LSTM, MiniRocket), and statistical and conventional machine learning baselines (e.g., GBDT, SVR, ARIMA). All forecasting performances are assessed using four metrics: the root mean squared error, the mean absolute percentage error, the coefficient of determination, and the mean directional accuracy. Superior forecasting performance is achieved consistently using the proposed hybrid technique.

Machine and deep learning approaches for forecasting electricity price and energy load assessment on real datasets

This article aims to propose short-term forecasting for a combined model of the hourly electricity price and the hourly load. Where both the independent system operators and the market participants must deal with the uncertainty and volatility of the day-ahead electricity price. Therefore, an accurate prediction model has been needed for a combined short-term forecasting model for both the hourly electricity price and the hourly load in the deregulated market. To get a better prediction, real-time data for the day-ahead electricity price and the hourly load are provided from the ISO New England Control Area (ISO-NE-CA) market. This study presents the combined model based on four featured machine and deep learning algorithms: Feed Forward Artificial Neural Network, Adaptive Neuro-Fuzzy Inference System, Long Short-Term Memory, and Gated Recurrent Units. The results are obtained from two scenarios, In the first scenario, the data has been trained and tested without depending on other factors such as temperatures and calendar. In the second scenario, the data has been trained and tested depending on the previously mentioned factors. The obtained results from the four algorithms have been compared to show their performance and their efficiency in the values of Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), Normalized Root Mean Squared Error (NRMSE), and Mean Absolute Percentage Error (MAPE). The four featured algorithms prove their good performance with less error in the forecasting model.

Revealing the Effects of Data Heterogeneity in Federated Learning Regression Models for Short-Term Solar Power Forecasting

Revealing the Effects of Data Heterogeneity in Federated Learning Regression Models for Short-Term Solar Power Forecasting

Performance enhancement of short-term wind speed forecasting model using Realtime data.

The ever-increasing demand for electricity has presented a grave threat to traditional energy sources, which are finite, rapidly depleting, and have a detrimental environmental impact. These shortcomings of conventional energy resources have caused the globe to switch from traditional to renewable energy sources. Wind power significantly contributes to carbon-free energy because it is widely accessible, inexpensive, and produces no harmful emissions. Better and more efficient renewable wind power production relies on accurate wind speed predictions. Accurate short-term wind speed forecasting is essential for effectively handling unsteady wind power generation and ensuring that wind turbines operate safely. The significant stochastic nature of the wind speed and its dynamic unpredictability makes it difficult to forecast. This paper develops a hybrid model, L-LG-S, for precise short-term wind speed forecasting to address problems in wind speed forecasting. In this research, state-of-the-art machine learning and deep learning algorithms employed in wind speed forecasting are compared with the proposed approach. The effectiveness of the proposed hybrid model is tested using real-world wind speed data from a wind turbine located in the city of Karachi, Pakistan. Moreover, the mean square error (MSE), root mean square error (RMSE), and mean absolute error (MAE) are used as accuracy evaluation indices. Experimental results show that the proposed model outperforms the state-of-the-art legacy models in terms of accuracy for short-term wind speed in training, validation and test predictions by 98% respectively.

Enhancing short-term streamflow forecasting of extreme events: A wavelet-artificial neural network hybrid approach

Accurate short-term streamflow forecasting models are crucial for effective water resource management, enabling timely responses to extreme flood or drought events and mitigating potential socioeconomic damage. This study proposes robust hybrid Wavelet Artificial Neural Network (WANN) models for real-world hydrological applications. Two WANN variants, WANNone and WANNmulti, are proposed for short-term streamflow forecasting of extreme (high and low) flows at eight gauging stations within Brazil's Paraíba do Sul River basin. WANNone directly feeds both the original streamflow data and the decomposed components obtained through an À Trous wavelet transform into the ANN architecture. Conversely, WANNmulti utilizes separate ANNs for the original data, with the final streamflow estimate reconstructed via the inverse wavelet transform of the individual ANN outputs. The performance of these WANN models is then compared against conventional ANN models. In both approaches, Bayesian optimization is employed to fine-tune the hyperparameters within the ANN architecture. The WANN models achieved superior performance for 7-day streamflow forecasts compared to conventional ANN models. WANN models yielded high R2 values (>0.9) and low MAPE (4.8%–14.7%) within the expected RMSE range, demonstrating statistically significant improvements over ANN models (71% and 75% reduction in RMSE and MAPE, respectively, and 69% increase in R2). Further analysis revealed that WANNmulti models generally exhibited superior performance for low extreme flow predictions, while WANNone models achieved the highest accuracy for high extreme flows at most stations. WANN models' strong performance suggests their value for real-time flood warnings, enabling improved decision-making in areas like flood/drought mitigation and urban water planning.

Neuromorphic Computing-Based Model for Short-Term Forecasting of Global Horizontal Irradiance in Saudi Arabia

Neuromorphic Computing-Based Model for Short-Term Forecasting of Global Horizontal Irradiance in Saudi Arabia

A comparative study of Machine Learning and Deep Learning methods for flood forecasting in the Far-North region, Cameroon

Flood crises are the consequence of climate change and global warming, which lead to an increase in the frequency and intensity of heavy rainfall. Floods are, and remain, natural disasters that result in huge loss of lives and material damage. Flood risks threaten all countries of the globe in general. The Far-North region of Cameroon has suffered of flood crises on several occasions, resulting in significant loss of human lives, infrastructural and socio-economic damage, with the destruction of homes, crops and grazing areas, and the halting of economic activities. The models used for flood forecasting in this region are generally physical-based, and produce unsatisfactory results. The use of artificial intelligence based methods for flood forecasting in order to limit its consequences is a way to be explored in the Far-North region of Cameroon. The aims of the present research work is to design and compare the performance of Machine Learning and Deep Learning based models such as one dimensional Convolutional Neural Network, Long and Short Term Memory and Multi Layer Perceptron for short-term and long-term flood forecasting in the Far-North region of Cameroon. The models designed take as input the temperature and rainfall time series recorded in this region. Performance criteria used for evaluating models are Nash–Sutcliffe Efficiency, Percent Bias, Coefficient of Determination and Root Mean Squared Error. As the results of the design and performance comparison of the models, the best model for short-term flood forecasting is the LSTM model , and the best model for long-term flood forecasting is still the LSTM model. The best models obtained from the comparisons have satisfactory performance and good generalization capabilities, as reflected by the performance criteria. The results of our research work can be used for implementation of floods warning systems and for definition of an effective and efficient flood risk management policies in order to make the Far-North region of Cameroon more resilient to flood crises.

Modeling cryptocurrency market dynamics using machine learning tools

The article analyzes the dynamics of the cryptocurrency market (Bitcoin) using econometric estimation tools based on machine learning models. The forecasting method is improved based on time series decomposition and lagged shifts of financial indicators. An ensemble of short-term forecast models for the Bitcoin exchange rate is built, and its accuracy is analyzed and compared to individual component models. Time series models are used along with calculated financial indicators (ADODS, NATR, TRANGE, ATR, OBV, RSI, ADTV). The absolute deviation of the short-term forecast amounted to $9.5, which is 0.06% of the absolute value.

Mode decomposition-based short-term multi-step hybrid solar forecasting model for microgrid applications

Mode decomposition-based short-term multi-step hybrid solar forecasting model for microgrid applications

Forecasting daily COVID-19 cases with gradient boosted regression trees and other methods: evidence from U.S. cities.

There is a vast literature on the performance of different short-term forecasting models for country specific COVID-19 cases, but much less research with respect to city level cases. This paper employs daily case counts for 25 Metropolitan Statistical Areas (MSAs) in the U.S. to evaluate the efficacy of a variety of statistical forecasting models with respect to 7 and 28-day ahead predictions. This study employed Gradient Boosted Regression Trees (GBRT), Linear Mixed Effects (LME), Susceptible, Infectious, or Recovered (SIR), and Seasonal Autoregressive Integrated Moving Average (SARIMA) models to generate daily forecasts of COVID-19 cases from November 2020 to March 2021. Consistent with other research that have employed Machine Learning (ML) based methods, we find that Median Absolute Percentage Error (MAPE) values for both 7-day ahead and 28-day ahead predictions from GBRTs are lower than corresponding values from SIR, Linear Mixed Effects (LME), and Seasonal Autoregressive Integrated Moving Average (SARIMA) specifications for the majority of MSAs during November-December 2020 and January 2021. GBRT and SARIMA models do not offer high-quality predictions for February 2021. However, SARIMA generated MAPE values for 28-day ahead predictions are slightly lower than corresponding GBRT estimates for March 2021. The results of this research demonstrate that basic ML models can lead to relatively accurate forecasts at the local level, which is important for resource allocation decisions and epidemiological surveillance by policymakers.