Long Short-term Memory Prediction Model Research Articles

A dynamic prediction model of landslide displacement based on VMD–SSO–LSTM approach

Addressing the limitations of existing landslide displacement prediction models in capturing the dynamic characteristics of data changes, this study introduces a novel dynamic displacement prediction model for landslides. The proposed method combines Variational Mode Decomposition (VMD) with Sparrow Search Optimization (SSO) and Long Short-Term Memory (LSTM) techniques to formulate a comprehensive VMD–SSO–LSTM model. Through the application of VMD, the method dissects cumulative displacement and rainfall data, thereby extracting distinct components such as trend, periodicity, and fluctuation components for displacement, as well as low-frequency and high-frequency components for rainfall. Furthermore, leveraging Gray Correlational Analysis, the interrelationships between the periodic component of displacement and the low-frequency component of rainfall, as well as the fluctuation component of displacement and the high-frequency component of rainfall, are established. Building upon this foundation, the SSO–LSTM model dynamically predicts the interrelated displacement components, synthesizing the predicted values of each component to generate real-time dynamic forecasts. Simulation results underscore the effectiveness of the proposed VMD–SSO–LSTM model, indicating root-mean-square error (RMSE) and mean absolute percentage error (MAPE) values of 1.2329 mm and 0.1624%, respectively, along with a goodness of fit (R2) of 0.9969. In comparison to both back propagation (BP) prediction model and LSTM prediction model, the VMD–SSO–LSTM model exhibits heightened predictive accuracy.

Short-Term Prediction of the Intermediate Point Temperature of a Supercritical Unit Based on the EEMD–LSTM Method

The quality of the intermediate point temperature control of a supercritical unit is directly related to the quality of the coal–water ratio and main steam temperature control of the supercritical unit, which is also related to the economy and safety of the unit. In order to improve the accuracy of short-term predictions of the intermediate point temperature, a short-term prediction model of the intermediate point temperature based on the EEMD (Ensemble Empirical Mode Decomposition)-LSTM (Long Short-Term Memory) model is proposed. This model uses the data of a 600 MW thermal power station in 2022 as a sample. The EEMD method is used to decompose the historical data into IMF components and residual components, and the correlation between each component and the original data is calculated. The relevant components are sent to the LSTM neural network, and all the sub-components are superimposed to obtain the final intermediate point temperature prediction results. At the same time, the BP and LSTM models are built to compare the errors with the proposed model. The results show that the single model will produce large errors when predicting the factors of large data fluctuations. The EEMD–LSTM coupling model can fully extract the detailed features and the prediction effect is obvious. The prediction accuracy of the EEMD–LSTM prediction model built in this paper is significantly better than that of the other two models. It has certain application value in the research field of intermediate point temperature prediction and can meet the requirements of short-term predictions of the intermediate point temperature.

Spatiotemporal evolution of deformation and LSTM prediction model over the slope of the deep excavation section at the head of the South-North Water Transfer Middle Route Canal

Slope deformation is one of the focal issues of concern during the normal operation and maintenance of the South-North Water Transfer Middle Route Project. To study the slope deformation evolution in the deep excavation section at the head of the canal, we applied 88 views of Sentinel-1A ascending image data from 2017 to 2019 and MT-InSAR(Multi-temporal InSAR) deformation monitoring technology to obtain long-time series deformation rates and cumulative deformation fields over the slope in the study area. Based on the analysis of the time-series monitoring data of the deformation field sample points, a LSTM (Long Short Term Memory Network) slope deformation predictive model was constructed to predict the slope deformation for the next 12 months at 12 sample points of the deep excavation slope. The impact of rainfall on slope deformation was investigated, and the reliability of the LSTM model was verified by using the measured data. The results show that the average annual deformation rate of the slope ranges from 10mm/a to 25mm/a, the maximum cumulative deformation is about 60 mm, and the slope of the excavated section is generally in an uplifted state. The rainfall-induced repeated uplift or subsidence of the canal slopes together with the peak deformation was closely related to the amount of rainfall during the wet season, and the longer the duration of the wet season, the more obvious the crest. Among the12 sample sites, the minimum and maximum deformation predicted using the LSTM model were 51.7 mm and 73.9 mm respectively, with the lowest correlation coefficient of 0.994 and the highest of 0.999. The maximum and minimum values of RMSE (Root Mean Square Error) were 4.4 mm and 3.6 mm respectively, indicating reliable prediction results. The results of the study can provide reference for the prevention and control of geological hazards in the South-North Water Transfer Canal.

Research on Time Series-Based Pipeline Ground Penetrating Radar Calibration Angle Prediction Algorithm.

The pipeline ground-penetrating radar stands as an indispensable detection device for ensuring underground space security. A wheeled pipeline robot is deployed to traverse the interior of urban underground drainage pipelines along their central axis. It is subject to influences such as resistance, speed, and human factors, leading to deviations in its posture. A guiding wheel is employed to rectify its roll angle and ensure the precise spatial positioning of defects both inside and outside the pipeline, as detected by the radar antenna. By analyzing its deflection factors and correction trajectories, the intelligent correction control of the pipeline ground-penetrating radar falls into the realm of nonlinear multi-constraint optimization. Consequently, a time-series-based correction angle prediction algorithm is proposed. The application of the long short-term memory (LSTM) deep learning model facilitates the prediction of correction angles and torque for the guiding wheel. This study compares the performance of LSTM with an autoregressive integrated moving average model under identical dataset conditions. The subsequent findings reveal a reduction of 4.11° and 8.25 N·m in mean absolute error, and a decrease of 10.66% and 7.27% in mean squared error for the predicted correction angles and torques, respectively. These outcomes are achieved utilizing the three-channel drainage pipeline ground-penetrating radar device with top antenna operating at 1.2 GHz and left/right antennas at 750 MHz. The LSTM prediction model intelligently corrects its posture. Experimental results demonstrate an average correction speed of 5 s and an average angular error of ±1°. It is verified that the model can correct its attitude in real-time with small errors, thereby enhancing the accuracy of ground-penetrating radar antennas in locating pipeline defects.

An Empirical Modal Decomposition-Improved Whale Optimization Algorithm-Long Short-Term Memory Hybrid Model for Monitoring and Predicting Water Quality Parameters

Prediction of water quality parameters is a significant aspect of contemporary green development and ecological restoration. However, the conventional water quality prediction models have limited accuracy and poor generalization capability. This study aims to develop a dependable prediction model for ammonia nitrogen concentration in water quality parameters. Based on the characteristics of the long-term dependence of water quality parameters, the unique memory ability of the Long Short-Term Memory (LSTM) neural network was utilized to predict water quality parameters. To improve the accuracy of the LSTM prediction model, the ammonia nitrogen data were decomposed using Empirical Modal Decomposition (EMD), and then the parameters of the LSTM model were optimized using the Improved Whale Optimization Algorithm (IWOA), and a combined prediction model based on EMD-IWOA-LSTM was proposed. The study outcomes demonstrate that EMD-IWOA-LSTM displays improved prediction accuracy with reduced RootMean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE) in comparison to the LSTM and IWOA-LSTM approaches. These research findings better enable the monitoring and prediction of water quality parameters, offering a novel approach to preventing water pollution rather than merely treating it afterwards.

Predictive AC Control Using Deep Learning: Improving Comfort and Energy Saving

The growing global population and the availability of energy-hungry smart devices are critical factors in today's alarmingly high electricity usage. The majority of energy used in urban areas is consumed by buildings, with heating, ventilation, and air conditioning (AC) systems accounting for a significant amount of energy use. This project proposes an AC controlling algorithm that uses the Internet of Things sensors and a deep learning framework in temperature prediction to control a single AC unit. The algorithm consists of a Long Short-Term Memory (LSTM) model to predict the indoor temperature for the next J minutes. The highlight of this model is its capacity to predict the future temperature based on the predetermined AC status, whether it is switched on or off. The AC unit will be turned off if the J-minute predicted temperature is within the desired thermal comfort range, and it will be turned back on if the sensor readings exceed the upper pre-set threshold. The experiment is performed on the dataset collected by Chulalongkorn University Building Energy Management System (CU-BEMS). The LSTM prediction model developed using CU-BEMS data yields an average Root Mean Squared Error and Mean Absolute Error of 0.08 and 0.03, respectively. A half-day simulation is also performed in controlling the AC unit from 7:39 a.m. to 11:35 a.m. The proposed algorithm shows that 49.00% of the time, the AC unit can be turned off while the thermal range is maintained between 27ºC to 27.9ºC, providing a strategy for managing the AC unit and achieving energy savings.

Associating deep learning and the news headlines sentiment for Bursa stock price prediction

Accurate stock price prediction is appealing to academics, economists, and financial analysts for its potential to increase profits. Although remarkable progress has been made in stock prediction accuracy, studies to explore the relationship between public sentiments and the prediction of stock price movement based on online news portals in Malaysia context are limited. Therefore, this study aims to determine whether news sentiments influence the movement of the Bursa stock price. The stock prediction model was implemented using long short-term memory (LSTM), with stock data from Bursa Malaysia between January 2017 and April 2022, and the root mean squared error (RMSE) value was calculated. In addition, LSTM prediction model was compared to the decision tree algorithm, and LSTM performed significantly better than the decision tree, particularly when using the New York stock exchange (NYSE) dataset. Furthermore, sentiment analysis was carried out using a Malaysian online news portal's business and financial news. The findings showed that i) news has a significant impact on Malaysian stock market price movement; ii) the RMSE of the LSTM model was improved by adding a parameter (news polarity values); and iii) the RMSE value generated is less than one for every company stock and is influenced by stock price and price change magnitude.

Using Social Network Sentiment Analysis and Genetic Algorithm to Improve the Stock Prediction Accuracy of the Deep Learning-Based Approach

Traditionally, most investment tools used to predict stocks are based on quantitative variables, such as finance and capital flow. With the widespread impact of the Internet, investors and investment institutions designing investment strategies are also referring to online comments and discussions. However, multiple information sources, along with uncertainties accompanying international political and economic events and the recent pandemic, have left investors concerned about information interpretation approaches that could aid investment decision-making. To this end, this study proposes a method that combines social media sentiment, genetic algorithm (GA), and deep learning to predict changes in stock prices. First, it employs a hybrid genetic algorithm (HGA) combined with machine learning to identify chip-based indicators closely related to fluctuations in stock prices and then uses them as input for long short-term memory (LSTM) to establish a prediction model. Next, this study proposes five sentiment variables to analyze PTT social media on TSMC’s stock price and performs a grey relational analysis (GRA) to identify the sentiment variables most closely related to stock price fluctuations. The sentiment variables are then combined with the selected chip-based indicators as input to build the LSTM prediction model. To improve the efficiency of the LSTM analysis, this study applies the Taguchi method to optimize the hyper-parameters. The results show that the proposed method of using HGA-screened chip-based variables and social media sentiment variables as input to establish an LSTM prediction model can effectively improve the prediction accuracy of stock price fluctuations.

Prediction of the standardized precipitation index based on the long short-term memory and empirical mode decomposition-extreme learning machine models: The Case of Sakarya, Türkiye

This research predicted the meteorological drought of Sakarya province in northwest Türkiye using long short-term memory (LSTM). This deep learning algorithm has gained popularity in prediction studies. The standardized precipitation index (SPI), which can only be derived using precipitation data, was utilized for 1, 3, and 6-month time scales. SPI-1, SPI-3, and SPI-6-month time scales drought data calculated from the monthly precipitation data of the Sakarya Meteorology Station between 1960 and 2020 were taken as input data in the LSTM model. SPI drought data were used between 1960 and 2005 as training data and 2006–2020 as test data. Drought at t+1 output time was predicted using SPI values at t, t-1, t-2, and t-3 lag times as input variables. In addition, the results were compared with the empirical mode decomposition (EMD)-extreme learning machine (ELM) hybrid model to understand the capabilities of the standalone LSTM prediction model. The LSTM model yielded the best results (MAE = 0.11, NSE = 0.97, R2 = 0.97) for the SPI-1-month time scale and the best results (MAE = 0.18, NSE = 0.92, R2 = 0.94) for 3-month time scale. The EMD-ELM hybrid model yielded the best results (MAE = 0.22, NSE = 0.95, R2 = 0.96) for the SPI-6-month time scale. Due to the high performance of this study's proposed standalone LSTM model, it was concluded that drought time series do not need to be subjected to pre-processing techniques.

A hybrid hour-ahead wind power prediction model based on variational mode decomposition and bio-inspired LSTM

Wind power, as an eco-friendly renewable energy, has been widely integrated into modern power systems. The prediction accuracy of wind power is crucial to the secure operation of power systems. To improve the prediction accuracy, a hybrid hour-ahead wind power prediction method is presented in this paper. First, the variational mode decomposition (VMD) is used to decompose the original wind power sequences into a set of intrinsic mode functions (IMFs) with different frequencies. Then, the prediction model is formulated by using the long short-term memory (LSTM) network for each IMF. To enhance the LSTM, a bio-inspired algorithm named Harris Hawks optimization (HHO) is blended to optimize the parameters of each LSTM prediction model. The final prediction output power is thus obtained by integrating all prediction results from these individual IMFs, so that the novel VMD–HHO–LSTM prediction strategy is developed. Finally, case studies based on the real historical dataset are performed, demonstrating that the proposed hybrid hour-ahead wind power prediction model named VMD–HHO–LSTM has better prediction performance and higher applicability to multiple dataset scenarios.

Abnormal identification of oil monitoring based on LSTM and SVDD

Oil monitoring has been considered as an essential tool in determining the operational state of an equipment. In other words, the data obtained from monitoring the oil represents the equipment's operational status. So, identifying the abnormal working status of the lubricating oil allows to understand its operating status in advance. Accordingly, the present study aims at proposing an anomaly identification model based on Long Short Term Memory (LSTM) and Support Vector Data Description (SVDD) for time series data of wear state collected by the oil online monitoring system. So, to predict the wear condition of the oil in the future, LSTM and grid search are utilized and a trend prediction model of oil monitoring metrics is constructed. Given that the fault is a gradual process, a multi-dimensional hypersphere classifier is generated by SVDD to train the healthy samples. The classifier is utilized to diagnose the lubricating oil condition data obtained by the LSTM prediction model as well as to realize the abnormal identification of the equipment's lubricating oil. The obtained experimental results corroborated the higher prediction accuracy and the lower prediction loss of the trend prediction model. Therefore, the future anomalies of the device can be argued to be reliably predicted in accordance with its actual performance using the LSTM-SVDD method. Furthermore, with regards to the actual operating conditions of the diesel engine, the alarm rate as well as the false alarm rate, the LSTM-SVDD method was demonstrated to be superior to the LSTM-PCA-SPE method. Hence, the novel model proposed in this study can be used to identify the status parameters of the lubricating oil abnormal wear. Moreover, the model can be argued to improve the accuracy of the abnormal identification as well as the online identification of the lubricating oil.

Research on a working face gas concentration prediction model based on LASSO-RNN time series data

The effective prediction of gas concentration trends and timely and reasonable extraction measures can provide valuable references for gas control. The gas concentration prediction model proposed in this paper has the advantages of a large sample size and long time span for training data selection. It is suitable for more gas concentration change scenarios and can be used to adjust the data prediction length according to demand. To improve the applicability and practicability of the model, this paper proposes a prediction model based on the LASSO-RNN (least absolute shrinkage and selection operator) for mine face gas concentration based on actual gas monitoring data from a mine. First, the LASSO method is used to select the key eigenvectors that affect the gas concentration change. Second, the basic structural parameters of the RNN prediction model are preliminarily determined based on the broad strategy. Then, the MSE (mean square error) and the running time are used as the evaluation indicators to select the appropriate batch size and number of epochs. Finally, the appropriate prediction length is selected based on the optimized gas concentration prediction model. The results show that the RNN gas concentration prediction model has a better prediction effect than the LSTM (long short-term memory) prediction model. The average mean square error of the model fit can be reduced to 0.0029, and the predicted average absolute error can be reduced to 0.0084. The maximum absolute error of 0.0202, especially at the time inflection point of the change in the gas concentration curve, can better reflect the superiority of the RNN prediction model, that is, higher precision, robustness and applicability than LSTM.

Forecasting smoked rubber sheets price based on a deep learning model with long short-term memory

<span>This research aimed to create suitable forecasting models with long-short term memory (LSTM) from time series data, the price of rubber smoked sheets (RSS3) using 2,631 data from the Rubber Authority of Thailand for the past 10 years. The data was divided into two sets: first series 2,105 data points were used to create the LSTM prediction model; second series 526 data points were used to estimate forecasting performance using the root mean square error (RMSE), the mean absolute percentage error (MAPE), and accuracy rate of the model. The results showed that the most suitable forecasting model for time series data, with a total of 9 LSTM layers comprised of 3 primary LSTMs. Each LSTM layer has the number of neurons 100, 150, and 200 to obtain an optimal neural network of the LSTM technique. The number of epochs and iteration was 30, 40, and 50. Dropout layers between each LSTM layer have a probability of 30%. The results of the test to measure the performance of the time series forecasting data showed that the 9-layer model with the LSTM model architecture of LSTM 3 layers gave the best forecast, with RMSE of 2.4121, MAPE of 0.0413 and 95.88% accuracy rate.</span>

Multiscale Decomposition Prediction of Propagation Loss for EM Waves in Marine Evaporation Duct Using Deep Learning

A tropospheric duct (TD) is an anomalous atmospheric refraction structure in marine environments that seriously interferes with the propagation path and range of electromagnetic (EM) waves, resulting in serious influence on the normal operation of radar. Since the propagation loss (PL) can reflect the propagation characteristics of EM waves inside the duct layer, it is important to obtain an accurate cognition of the PL of EM waves in marine TDs. However, the PL is strongly non−linear with propagation range due to the trapped propagation effect inside duct layer, which makes accurate prediction of PL more difficult. To resolve this problem, a novel multiscale decomposition prediction method (VMD−PSO−LSTM) based on the long short−term memory (LSTM) network, variational mode decomposition (VMD) method and particle swarm optimization (PSO) algorithm is proposed in this study. Firstly, VMD is used to decompose PL into several smooth subsequences with different frequency scales. Then, a LSTM−based model for each subsequence is built to predict the corresponding subsequence. In addition, PSO is used to optimize the hyperparameters of each LSTM prediction model. Finally, the predicted subsequences are reconstructed to obtain the final PL prediction results. The performance of the VMD−PSO−LSTM method is verified by combining the measured PL. The minimum RMSE and MAE indicators for the VMD−PSO−PSTM method are 0.368 and 0.276, respectively. The percentage improvement of prediction performance compared to other prediction methods can reach at most 72.46 and 77.61% in RMSE and MAE, respectively, showing that the VMD−PSO−LSTM method has the advantages of high accuracy and outperforms other comparison methods.

Short-term photovoltaic power prediction based on modal reconstruction and hybrid deep learning model

Short-term photovoltaic (PV) power prediction is significant in improving power grid planning and dispatching capacity. However, the change of PV power has strong randomness and volatility, which will affect the prediction accuracy. A PV power short-term prediction model is proposed in this paper, which combines Pearson correlation coefficient (PCC), ensemble empirical modal decomposition (EEMD), sample entropy (SE), sparrow search algorithm (SSA), and long short-term memory (LSTM). Firstly, the anomalous data of the PV power plant is cleared and complemented, and the key meteorological features are selected as input using the PCC to realize the dimensionality reduction of the original data. Secondly, the input and output variables are decomposed into components of different frequencies using EEMD. Calculate the SE value of each component, and merge and reconstruct the components with similar SE values. Finally, the LSTM prediction model of each reconstruction component is established. The SSA is used to optimize the LSTM structure parameters, and the optimal parameter combination is selected to reduce the prediction error. The predicted values of the reconstructed component are summed, and the final prediction results are analyzed according to R2, MAE, and RMSE. The results show that the PCC-EEMD-SSA-LSTM model proposed in this paper has a minimum prediction error of PV power under different weather, verifying that the proposed hybrid model has superior prediction accuracy.

The Prediction of Enterprise Stock Change Trend by Deep Neural Network Model.

This study aims to accurately predict the changing trend of stocks in stock trading so that company investors can obtain higher returns. In building a financial forecasting model, historical data and learned parameters are used to predict future stock prices. Firstly, the relevant theories of stock forecasting are discussed, and problems in stock forecasting are raised. Secondly, the inadequacies of deep neural network (DNN) models are discussed. A prediction trend model of enterprise stock is established based on long short-term memory (LSTM). The uniqueness and innovation lie in using the stock returns of Bank of China securities in 2022 as the training data set. LSTM prediction models are used to perform error analysis on company data training. The 20-day change trend of the company's stock returns under different models is predicted and analyzed. The results show that as the number of iterations increases, the loss rate of the LSTM training curve keeps decreasing until 0. The average return price of the LSTM prediction model is 14.01. This figure is closest to the average real return price of 13.89. Through the forecast trend analysis under different models, LSTM predicts that the stock change trend of the enterprise model is closest to the changing trend of the actual earnings price. The prediction accuracy is better than other prediction models. In addition, this study explores the characteristics of high noise and complexity of corporate stock time series, designs a DNN prediction model, and verifies the feasibility of the LSTM model to predict corporate stock changes with high accuracy.

Data-Driven Prediction of COVID-19 Daily New Cases through a Hybrid Approach of Machine Learning Unsupervised and Deep Learning

Air pollution is associated with respiratory diseases and the transmission of infectious diseases. In this context, the association between meteorological factors and poor air quality possibly contributes to the transmission of COVID-19. Therefore, analyzing historical data of particulate matter (PM2.5 and PM10) and meteorological factors in indoor and outdoor environments to discover patterns that allow predicting future confirmed cases of COVID-19 is a challenge within a long pandemic. In this study, a hybrid approach based on machine learning and deep learning is proposed to predict confirmed cases of COVID-19. On the one hand, a clustering algorithm based on K-means allows the discovery of behavior patterns by forming groups with high cohesion. On the other hand, multivariate linear regression is implemented through a long short-term memory (LSTM) neural network, building a reliable predictive model in the training stage. The LSTM prediction model is evaluated through error metrics, achieving the highest performance and accuracy in predicting confirmed cases of COVID-19, using data of PM2.5 and PM10 concentrations and meteorological factors of the outdoor environment. The predictive model obtains a root-mean-square error (RMSE) of 0.0897, mean absolute error (MAE) of 0.0837, and mean absolute percentage error (MAPE) of 0.4229 in the testing stage. When using a dataset of PM2.5, PM10, and meteorological parameters collected inside 20 households from 27 May to 13 October 2021, the highest performance is obtained with an RMSE of 0.0892, MAE of 0.0592, and MAPE of 0.2061 in the testing stage. Moreover, in the validation stage, the predictive model obtains a very acceptable performance with values between 0.4152 and 3.9084 for RMSE, and a MAPE of less than 4.1%, using three different datasets with indoor environment values.

Construction and Simulation of Market Risk Warning Model Based on Deep Learning

The market is intricate and complicated, and the existing risk warning models have problems of low efficiency and poor generalization in predicting market risk data. Aiming at the problems, this study takes stock market risk warning as the research object and proposes a market risk warning model based on LSTM-VaR. 15 variables in the three categories of basic transaction data, statistical technical indicators, and moving interval data are selected as the stock market characteristic indicators, the LSTM(Long Short Term Memory) prediction model is constructed and the standard deviation of stock returns is predicted. Based on the predicted results, the probability distribution of return rate under the conditional distribution is obtained, and the VaR(Value at Risk) is calculated. 1% and 5% sample quantiles are taken as the warning line, and the LSTM-VaR warning model is obtained. The results show that the RMSE value of the model is the smallest, which is 0.013762, when the activation function of the LSTM-VaR model is the Leaky ReLu function, the training periods epochs are 10, the time window length N is 9, the batch size is 8, the number of neurons in each layer is 50, the dropout probability is 0.1, and adam is used as the optimizer. Compared with traditional prediction models such as MLP, the proposed model has better performance and can well realize market risk warning.

Prediction of Process Quality Performance Using Statistical Analysis and Long Short-Term Memory

In the manufacturing industry, the process capability index (Cpk) measures the level and capability required to improve the processes. However, the Cpk is not enough to represent the process capability and performance of the manufacturing processes. In other words, considering that the smart manufacturing environment can accommodate the big data collected from various facilities, we need to understand the state of the process by comprehensively considering diverse factors contained in the manufacturing. In this paper, a two-stage method is proposed to analyze the process quality performance (PQP) and predict future process quality. First, we propose the PQP as a new measure for representing process capability and performance, which is defined by a composite statistical process analysis of such factors as manufacturing cycle time analysis, process trajectory of abnormal detection, statistical process control analysis, and process capability control analysis. Second, PQP analysis results are used to predict and estimate the stability of the production process using a long short-term memory (LSTM) neural network, which is a deep learning algorithm-based method. The present work compares the LSTM prediction model with the random forest, autoregressive integrated moving average, and artificial neural network models to convincingly demonstrate the effectiveness of our proposed approach. Notably, the LSTM model achieved higher accuracy than the other models.

Deep Learning Network for Energy Storage Scheduling in Power Market Environment Short-Term Load Forecasting Model

In the electricity market, fluctuations in real-time prices are unstable, and changes in short-term load are determined by many factors. By studying the timing of charging and discharging, as well as the economic benefits of energy storage in the process of participating in the power market, this paper takes energy storage scheduling as merely one factor affecting short-term power load, which affects short-term load time series along with time-of-use price, holidays, and temperature. A deep learning network is used to predict the short-term load, a convolutional neural network (CNN) is used to extract the features, and a long short-term memory (LSTM) network is used to learn the temporal characteristics of the load value, which can effectively improve prediction accuracy. Taking the load data of a certain region as an example, the CNN-LSTM prediction model is compared with the single LSTM prediction model. The experimental results show that the CNN-LSTM deep learning network with the participation of energy storage in dispatching can have high prediction accuracy for short-term power load forecasting.