Electric Vehicle Charging System in the Smart Grid Using Different Machine Learning Methods

The transport sector significantly contributes to global greenhouse gas emissions, making electromobility crucial in the race toward the United Nations Sustainable Development Goals. In recent years, the increasing competition among manufacturers, the development of cheaper batteries, the ongoing policy support, and people’s greater environmental awareness have consistently increased electric vehicles (EVs) adoption. Nevertheless, EVs charging needs—highly influenced by EV drivers’ behavior uncertainty—challenge their integration into the power grid on a massive scale, leading to potential issues, such as overloading and grid instability. Smart charging strategies can mitigate these adverse effects by using information and communication technologies to optimize EV charging schedules in terms of power systems’ constraints, electricity prices, and users’ preferences, benefiting stakeholders by minimizing network losses, maximizing aggregators’ profit, and reducing users’ driving range anxiety. To this end, accurately forecasting EV charging demand is paramount. Traditionally used forecasting methods, such as model-driven and statistical ones, often rely on complex mathematical models, simulated data, or simplifying assumptions, failing to accurately represent current real-world EV charging profiles. Machine learning (ML) methods, which leverage real-life historical data to model complex, nonlinear, high-dimensional problems, have demonstrated superiority in this domain, becoming a hot research topic. In a scenario where EV technologies, charging infrastructure, data acquisition, and ML techniques constantly evolve, this paper conducts a systematized literature review (SLR) to understand the current landscape of ML-based EV charging demand forecasting, its emerging trends, and its future perspectives. The proposed SLR provides a well-structured synthesis of a large body of literature, categorizing approaches not only based on their ML-based approach, but also on the EV charging application. In addition, we focus on the most recent technological advances, exploring deep-learning architectures, spatial-temporal challenges, and cross-domain learning strategies. This offers an integrative perspective. On the one hand, it maps the state of the art, identifying a notable shift toward deep-learning approaches and an increasing interest in public EV charging stations. On the other hand, it uncovers underexplored methodological intersections that can be further exploited and research gaps that remain underaddressed, such as real-time data integration, long-term forecasting, and the development of adaptable models to different charging behaviors and locations. In this line, emerging trends combining recurrent and convolutional neural networks, and using relatively new ML techniques, especially transformers, and ML paradigms, such as transfer-, federated-, and meta-learning, have shown promising results for addressing spatial-temporality, time-scalability, and geographical-generalizability issues, paving the path for future research directions.

The adoption of Electric Vehicle (EV) can shave the peak load and flatten the load profile in an urban area. However, the uncontrolled patterns of simultaneous and randomised EV charging may increase the peak load and thus destabilise the power grid. To address this problem effectively, this paper proposes an optimal charging scheme with the objective of lowering the power fluctuation level. The charging scheme takes into account the uncertainty of EV's driver behaviour and EV charging demand model with minimal impacts on daily routine of EV users. Firstly, a power fluctuation level problem is formulated and a novel EV charging scheme based on Genetic Algorithm is further proposed to solve the problem. The simulation results have shown the robustness of the proposed scheme in lowering the power fluctuation level and the overall peak demand significantly in the grid system.

The fast-expanding electric vehicle market requires efficient high-voltage charging methods. The documentation introduces a new PV-based switched inductor-switched capacitor (SL-SC) high voltage gain boost converter that addresses high-voltage EV charging requirements. The proposed converter design offers high voltage gain performance together with increased efficiency and diminished stress on its components. Recursive circuit analysis includes modeling of the circuit design alongside operational principle research and performance assessment. The simulation together with experimental studies prove that the proposed circuit design outperforms traditional boost converters concerning operational effectiveness. Efficient power converters that provide maximum voltage gain and intelligent control designs must be established because high-voltage electric vehicle (EV) charging systems need more effective solutions. This research explores the implementation of a high voltage gain boost converter with PV-supplied SL-SC topology which utilizes ANN control for high-voltage EV charging systems. SL-SC networks integrated through the proposed topology produce both high voltage conversion ratios and minimal semiconductor component stress that improves system performance and efficiency. The controller based on ANN optimizes the converter operation across different solar irradiation and load ranges by providing rapid system responses alongside improved voltage regulation. The proposed system proves better than conventional boost and coupled inductor-based converters through comparative analysis of voltage gain along with efficiency and transient response performance. Testing results together with simulation data support that this proposed structure represents an effective solution for future high-voltage systems which enable EV charging sustainability.

Many countries around the globe, including Tanzania, are investing in renewable energy, partly because of the need to increase electric power generation and meet the ever-increasing electricity demands, and partly because of the need to combat global climate change caused by carbon emissions from fossil fuel-based electricity production. Kishapu Solar Project, located in Kishapu District, Shinyanga Region, Tanzania, is one of the renewable energy projects with a planned generation of 150 MW of electric power once completed, using solar photovoltaic technology. Accurate forecasting of solar radiation is important in managing and maintaining solar energy plants. Inaccurate forecasting of solar radiation can lead to poor harvest of solar energy and poor management of solar energy plants, which directly impacts electricity contribution to the national electricity grid. Long Short-Term Memory (LSTM) and its variant, PeepHole LSTM, are examples of Deep Learning models that can be used to predict solar radiation. The purpose of PeepHole LSTM is to introduce “peephole” connections in the LSTM model, which allow LSTM gates to directly inspect memory cell state and hence have richer information to process. However, there is still a research gap on the impact of “peephole” connections on the prediction performance of the LSTM model, especially in the context of forecasting solar radiation in Kishapu District, where the Kishapu Solar Project is located. The purpose of this study is to fill this research gap by developing both LSTM and PeepHole LSTM models and comparing their performances in forecasting solar radiation in Kishapu District. The 14-year Kishapu District daily solar radiation (Downward Shortwave Radiation) dataset was first pre-processed by scaling (normalizing) it using Standard Scaler and then split into training set (the first 70%), validation set (the next 15%) and test set (the last 15%) before being utilized to train and test the developed LSTM and PeepHole LSTM models. Both LSTM and PeepHole LSTM models used the previous 5 days' solar radiation values as inputs to predict the output (next day (6th day) solar radiation value). The trained and better-performing model between the two was finally saved in .h5 format and integrated with a Gradio based Web Application to provide a user interface for officials in Kishapu District and at Kishapu Solar Project to predict daily solar radiation. The findings from performance evaluation revealed that the LSTM model outperformed the PeepHole LSTM model in predicting solar radiation by achieving test Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE) scores of 26.22 W/m2 and 36.65 W/m2, respectively, compared to MAE and RMSE scores of 30.84 W/m2 and 41.88 W/m2, respectively, achieved by the PeepHole LSTM model, concluding that “peephole” connections reduce the performance of the LSTM model rather than increasing it when used to forecast solar radiation in Kishapu District. This study’s recommendation to Artificial Intelligence (AI) software developers and researchers is to use the LSTM rather than the PeepHole LSTM Deep Learning model when forecasting solar radiation in Kishapu District and in locations with similar climatic conditions

Accurate pollutant prediction is essential in fields such as meteorology, meteorological disasters, and climate change studies. In this study, long short-term memory (LSTM) and deep neural network (DNN) models were applied to six pollutants and comprehensive air-quality index (CAI) predictions from 2015 to 2020 in Korea. In addition, we used the network method to find the best data sources that provide factors affecting comprehensive air-quality index behaviors. This study had two steps: (1) predicting the six pollutants, including fine dust (PM10), fine particulate matter (PM2.5), ozone (O3), sulfurous acid gas (SO2), nitrogen dioxide (NO2), and carbon monoxide (CO) using the LSTM model; (2) forecasting the CAI using the six predicted pollutants in the first step as predictors of DNNs. The predictive ability of each model for the six pollutants and CAI prediction was evaluated by comparing it with the observed air-quality data. This study showed that combining a DNN model with the network method provided a high predictive power, and this combination could be a remarkable strength in CAI prediction. As the need for disaster management increases, it is anticipated that the LSTM and DNN models with the network method have ample potential to track the dynamics of air pollution behaviors.

Electrification of the transportation sector can play an essential role in curbing fossil fuel scarcity and oil shortages in the world. Electric vehicles (EVs) can significantly reduce CO2 emissions, improve urban pollution. Apart from these advantages of EVs, they may also pose challenges to the distribution grid. Increasing penetration of EVs puts an extra burden and leads to affect the grid severely. Load congestions, voltage drops/regulation, overloading are some of the issues that might incur in the grid because of improper charging of EVs. The uncertain nature of EV owners makes it very difficult to predict the charging pattern. So the grid operator may face a daunting task to avoid overloading if huge EVs are charged without following any smart charging management strategies. We propose a framework that allows EV users to follow a well-coordinated charging schedule and fulfill various objectives like load variance minimization and social welfare maximization for both electric utility and EV owners. A proof of concept of distributed resource allocation for EV charging is implemented using the output consensus approach. Microgrids are components of a smart power distribution grid that can operate as a decentralized/localized grid when disconnected from the main grid. A microgrid can enhance the grid resiliency and provide adequate power to a community or a region in case of grid failure caused by natural disasters or any other disruptions. We also propose the optimal scheduling model for Distributed Energy Resources (DERs) including an EV charging station and battery energy storage system (BESS) in a community microgrid. This model also minimizes the cost incurred in operating the DERs, charging station, BESS, and the grid load. Due to the two-way power flow in the smart grid because of the EVs and distributed energy resources (DERs) involvement, the distribution system operator (DSO) must provide control & protection to equipment and manage the reverse power flow without violating system constraints. Artificial Intelligence (AI) leads the path for a promising smart grid future and helps the DSO tackle such challenges. Given the large size of data flow in the smart grid due to phasor measurement units (PMUs) and smart sensors, AI-based techniques help the grid operator to manage and analyze such data effectively and improve grid resiliency. Machine learning can help the grid operator forecast the uncertainty in supply-demand because of the integration of renewable energy sources. For system planning and operation, the utility needs to perform the

Wave runup prediction is necessary for offshore structure designs and early warnings. Data-driven methods based on machine learning have inspired reduced-order solutions for wave–structure interaction problems. This study provides the quantification of deep learning algorithms’ potential for wave runup prediction. Two prominent deep learning models were utilized to predict the wave runups along the fore column of semisubmersible under head seas. The long short-term memory (LSTM) and the temporal convolutional networks (TCNs) were comprehensively compared based on the datasets from a model test carried out in the deep ocean basin. The LSTM and TCN model structures were optimized to compare prediction accuracy and computational complexity reasonably. The results reveal that (1) both developed TCN and LSTM models had a satisfied prediction accuracy of over 90%. Their predictions were extended to 10 s into the future with accuracies over 80% and 45%, respectively. (2) With the noise-extended datasets, the LSTM model was robust to noises, while the TCN model showed better prediction performance on the extreme wave runup events. (3) The incident wave and dominant rotation provided the major information for wave runup prediction. TCN and LSTM models’ prediction accuracies were 91.5% and 89.3% based on the simplified input tensors composed of incident wave and pitch. The comparison showed the great potential of the TCN model to predict the nonlinear wave runup with less time and memory costs. The input tensors’ design and optimization based on physical understanding also play a significant role in the prediction performance.

Wired charging of electric vehicles comes with certain challenges and difficulties, such as handling bulky cables, risk of damage and compromised safety due to harsh climatic conditions such as heavy rain, wind or snow, and even vandalism. Wireless charging of electric vehicles is gaining prominence because it can mitigate the aforementioned challenges and difficulties and can also operate at the same power transfer efficiency as wired methods today. To design and optimize magnetically coupled coils of a wireless charging system for electric vehicles, numerous simulations utilizing the finite element method (FEM) need to be performed for the estimation of several parameters. This process is time-consuming and computational resource- intensive. In this paper, a real-time approach for obtaining quick estimated results for coupled coil parameters in an 11-kW wireless charging system for electric vehicles is presented. The proposed hybrid approach utilizes fitted curves obtained from the results of a single three-dimensional (3D) FEM simulation for a set of parameters and combines them with polynomial equations in order to estimate the values of the self-inductances of the coupled coils, their mutual inductance, the coupling coefficient and the power transfer efficiency of the wireless charging system. An experimental verification is conducted to compare the coupling coefficient values obtained from the real-time estimator with the measured coupling coefficients of an 11-kW wireless charging system laboratory prototype. The measured values of the coupling coefficient closely correlate with those predicted by the real-time estimator with a median error of 2.133%. Thus, the proposed approach opens up a new way for real-time estimation of parameters for coupled coils, which can save time during the initial developmental stage of an 11-kW wireless charging system for electric vehicles.

Recent transformations from internal combustion engines (ICE) to electric vehicles (EVs) are challenged by limited the driving range per charge, thereby requiring the improvement or substantial deployment of rapid charging infrastructure to stimulate sufficient confidence in EV drivers. This study aims to establish the necessary level of EV motorway service station infrastructure for the United Kingdom (UK) based market. The investigation is founded on increasing the appropriate rapid charger availability and shorter charging times. EV charging patterns are determined, focusing on two Volkswagen iD3 EV models by measuring power curves across field-based rapid chargers at one-minute intervals. Datasets are analysed throughout rapid charging field tests. Additionally, variance synthesis is applied to establish variables within this study’s assessment for rapid charger capacity requirements in the UK. The operational performance for the utilised rapid chargers is correspondingly recorded, whilst the EV range is calculated at 3 miles per kWh, revealing a mean power delivery rate of just 27 kW per hour using a 50 kW rapid charger. Time-of-day charging sessions are used to generate data that is then amalgamated into our previous study data, confirming that rapid charging points on UK motorways are used primarily for EV journey range extension. If fully utilised for an entire 24h period, 434 chargers (with a variance consolidation number of 81) are required to service the UK-based motorway EV user base. Moreover, this study establishes that simply replacing current fuel pumps with individual rapid chargers on a like-for-like basis reduces availability and support for novel and existing users and may impact short-term grid availability.

The long short-term memory (LSTM) model is widely used in multiple areas, mainly for speech recognition, natural language processing and activity recognition. In the last few years, we started to see many variants of LSTM for recurrent neural networks since its inception in 1997. However, there weren’t many studies that have addressed the LSTM’s gating mechanism. In this paper, we propose a novel LSTM framework where we modify the architecture of the LSTM unit by adding a new layer that we call the “outlier gate”. The latter controls the flow of information that goes into the LSTM cell. This added signal allows us to avoid both the carry-over effect that the outliers have on the forecasted point and a bias in the estimates of our LSTM model – caused by unusual or non-repetitive events. The proposed architecture led us to an end-to-end trainable model that we applied in this paper to a financial time-series forecasting problem. Our results demonstrate that the new proposed LSTM architecture achieves better performance than the state-of-the-art original LSTM model.

Accurate prediction of temporal evolution of turbulent flames represents one of the most challenging problems in the combustion community. In this work, predictive models for turbulent flame evolution were proposed based on machine learning with long short-term memory (LSTM) and convolutional neural network-long short-term memory (CNN-LSTM). Two configurations without and with mean shear are considered, i.e., turbulent freely propagating premixed combustion and turbulent boundary layer premixed combustion, respectively. The predictions of the LSTM and CNN-LSTM models were validated against the direct numerical simulation (DNS) data to assess the model performance. Particularly, the statistics of the fuel (CH4 for the freely propagating flames and H2 for the boundary layer flames) mass fraction and reaction rate were examined in detail. It was found that generally the performance of the CNN-LSTM model is better than that of the LSTM model. This is because that the CNN-LSTM model extracts both the spatial and temporal features of the flames while the LSTM model only extracts the temporal feature of the flames. The errors of the models mainly occur in regions with large scalar gradients. The correlation coefficient of the mass fraction from the DNS and that from the CNN-LSTM model is larger than 0.99 in various flames. The correlation coefficient of the reaction rate from the DNS and that from the CNN-LSTM model is larger than 0.93 in the freely propagating flames and 0.99 in the boundary layer flames. Finally, the profiles of the DNS values and predictions conditioned on axial distance were examined, and it was shown that the predictions of the CNN-LSTM model agree well with the DNS values. The LSTM model failed to accurately predict the evolution of boundary layer flames while the CNN-LSTM model could accurately predict the evolution of both freely propagating and boundary layer flames. Overall, this study shows the promising performance and the applicability of the proposed CNN-LSTM model, which will be applied to turbulent flames a posteriori in future work.

Wearable electroencephalography (EEG) devices for seizure detection accuracy and reliability are deep learning (DL) applications in the field of epilepsy diagnosis. In this study, we sought to increase the accuracy of seizure detection using advanced DL algorithms on the Children’s Hospital Boston - Massachusetts Institute of Technology (CHB-MIT) EEG database. First, a fully convolutional network (FCN) was trained and assessed using accuracy and recall/precision metrics, and the early stopping technique was used to avoid overfitting. To assess the performance, the FCN was evaluated in terms of various metrics, including accuracy, precision, recall, F1-score, and receiver operating characteristic (ROC)-area under the curve (AUC). In addition, two-dimensional (2D) convolutional neural networks (CNNs) and long short-term memory (LSTM) models were used to model the database, and their performance was thoroughly measured using different metrics, graphs, and confusion matrices. Using LSTM variants, such as standard LSTM, bidirectional LSTM, stacked LSTM, and LSTM attention mechanisms, hybrid convolutional LSTM (ConvLSTM) models were trained and compared. The comparison was conducted based on the training and validation accuracy and loss, as well as the graphs resulting from the precision–recall curves. Apart from DL approaches, EEG signal analysis using time–frequency techniques, such as wavelet transform and short-time Fourier transform, has also been investigated. These methods assisted in the analysis of the time–frequency features of EEG signals in combination with DL models. This study demonstrates that the performance of wearable EEG devices can be augmented using a combination of DL and seizure signal processing techniques. The FCN achieved an accuracy of 92%, with a recall for seizures of 33%, an F1-score of 0.03, and strong ROC-AUC results. The 2D CNN achieved 96% accuracy, a seizure recall of 70%, an F1-score of 0.12, and an ROC-AUC score of 78%. The baseline LSTM struggled with effectiveness at 53% accuracy with a seizure recall of 18%. In contrast, the LSTM model, which incorporated synthetic minority oversampling technique (SMOTE) balancing, was able to reach improvements of up to 89% accuracy, with a precision of 91%, a recall of 86%, an F1-score of 0.89, and a strong ROC curve performance. Among the models, the LSTM with SMOTE was the best performer, with 89% accuracy, 91% precision, 86% recall, and an F1-score of 0.89. These results provide evidence that applying techniques for data balancing in combination with certain DL network architectures significantly improves the detection of seizures using wearable EEG devices worn on the body. We believe that real-time monitoring and high-performance systems are feasible using optimized DL frameworks. The analysis of the performance of different models allows for the understanding of the possibilities of optimizing the architectures of DL algorithms for the modern diagnosis of epilepsy in real time. The source code used to carry out the experiments is publicly available at CHB-MIT EEG Dataset Python Scripts (https://www.kaggle.com/code/adnankust/adnaneeg1).

An accurate electrical Short-term Load Forecasting (STLF) is an eminent factor in the power generation, electrical load dispatching and energy planning for the power supply companies, specifically in developing countries. This paper proposes a novel temporal feature selection-based Long Short-term Memory (LSTM) model developed by the combination of standard Artificial Neural Network (ANN) layer and LSTM for electrical short term load forecasting. The LSTM model has excellent capability of predicting the stochastic nature of an hour ahead electrical loads. The standard ANN layer consisting 11 neurons is used as an input to LSTM cells. Such a combination of ANN layer with LSTM was never proposed before. The proposed model accommodates variations in weather as well as temporal inputs like humidity, holidays, and date-time features in the hourly load data of the power supply company situated in Johor, Malaysia. This paper gives the insights of hyper parameter tuning to capture the more generalized electrical load patterns in the dataset without compromising the time complexity of the proposed model. The proposed approach was compared with five existing approaches, namely: ANN, LSTM model 1, LSTM model 2, LSTM model 3 and Convolutional Neural Network-LSTM (CNN-LSTM) using hourly load dataset of Johor. The experimental results demonstrate that the proposed approach outperformed the existing approaches in terms of root mean square error, mean absolute percentage error and Diebold-Mariano statistical inference test within 95% confidence interval.

Abstract. The information available on the internet nowadays is diverse and moves very quickly. Information is becoming easier to obtain by the general public with the numerous online media outlets, including news portals that provide up-to-date information insights. Various news portals earn revenue from advertising using pay-per-click methods that encourage article writers to use clickbait techniques to attract visitors. However, the negative effects of clickbait include a decrease in journalism quality and the spread of hoaxes. This problem can be prevented by using text classification to classify clickbait in news titles. One method that can be used for text classification is a neural network. Artificial neural networks use algorithms that can independently adjust input coefficient weights. This makes this algorithm highly effective for modeling non-linear statistical data. The artificial neural network algorithm, especially the Long Short-Term Memory (LSTM), has been widely used in various natural language processing fields with satisfying results, including text classification. To improve the performance of the neural network model, adjustments can be made to the model's hyperparameters. Hyperparameters are parameters that cannot be obtained through data and must be defined before the training process. In this research, the Long Short-Term Memory (LSTM) model was used in clickbait classification in news titles. Sixteen neural network models were trained with different hyperparameter configurations for each model. Hyperparameter tuning was carried out using the random search algorithm. The dataset used was the CLICK-ID dataset published by William & Sari, 2020[1], with a total of 15,000 annotated data. The research results show that the developed LSTM model has a validation accuracy of 0.8030, higher than William & Sari's research, and a validation loss of 0.4876. Using this model, researchers were able to classify clickbait in news titles with fairly good accuracy. Purpose: The study was to develop and evaluate a LSTM model with hyperparameter tuning for clickbait classification on news headlines. The thesis also aims to compare the performance of simple LSTM and bidirectional LSTM for this task. Methods: This study uses CLICK-ID dataset and applies different text preprocessing techniques. The dataset later was used to build and train 16 LSTM models with different hyperparameters and evaluates them using validation accuracy and loss. This study uses random search for hyperparameter tuning. Result: The results of the study show that the best model for clickbait classification on news headlines is a bidirectional LSTM model with one layer, 64 units, 0.2 dropout rate, and 0.001 learning rate. This model achieves a validation accuracy of 0.8030 and a validation loss of 0.4876. The results also show that hyperparameter tuning using random search can improve the performance of the LSTM models by avoiding zero probabilities and finding the optimal values for the hyperparameters. Novelty: This study compares and analyzes the different preprocessing methods on text and the different configurations of the models to find the best model for clickbait classification on news headlines. The study also uses hyperparameter tuning to tune the model into the best model and finding the optimal values for the hyperparameters.

The rapid proliferation of electric vehicles (EVs) has created unprecedented challenges for power grid infrastructure, particularly in managing the high-power demands of fast-charging stations. This research presents a novel approach to dynamic load balancing in EV fast-charging stations through machine learning integration with smart grid systems. The study develops and validates a predictive model that combines Long Short-Term Memory (LSTM) networks, Random Forest, and Gradient Boosting algorithms to optimize power distribution while maintaining grid stability. Using real-world data collected from 50 fast-charging stations across urban and suburban locations over a 12-month period, our proposed system demonstrates significant improvements over traditional methods. The results show a 27% improvement in load distribution efficiency and a 15% reduction in peak demand. Furthermore, the system achieves 92% accuracy in demand prediction and reduces charging waiting times by 8%. Grid stability metrics also improved substantially, with a 30% reduction in voltage fluctuations and a 20% improvement in power factor. The economic impact analysis reveals a 23% reduction in operational costs and a 35% improvement in energy utilization. The system's integration with smart grid infrastructure demonstrates robust scalability and adaptability to varying demand patterns. These findings suggest that machine learning-based load balancing can significantly enhance the reliability and efficiency of EV charging infrastructure while supporting grid stability. The proposed approach provides a promising foundation for future developments in smart charging systems, particularly in the context of increasing EV adoption rates and the growing need for sustainable transportation infrastructure.