Search

Machine learning algorithms based on deep neural networks have been widely used in many fields especially in computer vision, with impressive results. However, these models are vulnerable to different types of attacks like adversarial ones, which require attention to the model security and confidentiality. This study proposes a defense strategy to improve the insurance of white-box models while minimizing adversarial attacks against Fast Gradient Sign Method (FGSM)-based attacks and tackling the issue of adversarial training to improve their robustness. Mainly, we proposed a CNN model based on personalized activation functions using Beta function and its primitive. Then, the new resulted low degree polynomials are used to approximate the ReLU, Sigmoid and Tanh activation functions. Batch normalization was evoked to significantly improve the learning capacity of neural networks. The obtained results, using Mnist dataset prove the effectiveness of the proposed model.

A novel smart metering technique capable of anomaly detection was proposed for real-time home power management system. Smart meter data generated in real-time were obtained from 900 households of single apartments. To detect outliers and missing values in smart meter data, a deep learning model, the autoencoder, consisting of a graph convolutional network and bidirectional long short-term memory network, was applied to the smart metering technique. Power management based on the smart metering technique was executed by multi-objective optimization in the presence of a battery storage system and an electric vehicle. The results of the power management employing the proposed smart metering technique indicate a reduction in electricity cost and amount of power supplied by the grid compared to the results of power management without anomaly detection.

A challenging engineering optimization problem in electrical power generation is the unit commitment problem (UCP). Determining the scheduling for the economic consumption of production assets over a specific period is the premier objective of UCP. This paper presents a take on solving UCP with Binary Slime Mould Algorithm (BSMA). SMA is a recently created optimization method that draws inspiration from nature and mimics the vegetative growth of slime mould. A binarized SMA with constraint handling is proposed and implemented to UCP to generate optimal scheduling for available power resources. To test BSMA as a UCP optimizer, IEEE standard generating systems ranging from 10 to 100 units along with IEEE 118-bus system are used, and the results are then compared with existing approaches. The comparison reveals the superiority of BSMA over all the classical and evolutionary approaches and most of the hybridized methods considered in this paper in terms of total cost and convergence characteristics.

Faults and system failure components are primarily two causes of unstable or deteriorating control performance of power system. In this study, we present a novel approach to the decentralized restoration of large DC microgrids using fault-tolerant control (FTC). The microgrid achieves decentralization by partitioning into several smaller grids. Each independent grid views the actions of the other grids as an external disturbance. The malfunction of the controller is represented in the input matrix as a norm-bounded uncertainty. The disturbance impact is diminished due to the proposed invariant-set approach. The proposed control can address simultaneous failures in actuators with random placement and degradation levels. In a passive FTC system, when the defect cannot be detected (or the fault may not have been clearly addressed), the proposed technique is utilized. After the fault has occurred, it can be viewed as an uncertainty in system dynamics. The controller that stabilizes the system is obtained by solving iteratively bilinear matrix inequalities as linear matrix inequalities. In addition, this study presents and discusses positive outcomes of applying this method to a system of six interconnected DC microgrids in the event of multiple fault types. The proposed control successfully stabilizes the severe case of simultaneous actuator faults.

This paper introduces a novel approach to addressing the security challenges of the Internet of Things (IoT) by presenting a secure Chaos-based lightweight cryptosystem. The proposed design incorporates a Pseudo-Chaotic Numbers Generator combined with the Speck64/128 lightweight block cipher, to meet the stringent requirements of security and lightweight characteristics. First, we subject the cryptosystem to a battery of rigorous tests, including various cryptanalytics such as brute-force, differential attacks, and statistical attacks. The results of these tests clearly demonstrate the cryptosystem’s exceptional security resilience and its capacity to effectively withstand these attacks. Then, the novel cryptosystem architecture, specifically designed for resource-limited applications like IoT, was implemented on a Xilinx PYNQ-Z2 XC7Z020 FPGA platform, which aligns perfectly with the constraints of IoT devices. The investigation comprises a thorough analysis and evaluation of the developed cryptosystem according to the algorithm complexity and the achieved precision, hardware area, maximum operational frequency, throughput, efficiency, and power consumption. The findings prove the effectiveness of our approach in terms of computational complexity, memory requirements, and power consumption. Eventually, after reviewing and comparing our results to the existing literature, our cryptosystem’s superiority becomes evident. The simulation results and performance analysis show that the proposed Chaos-Based Lightweight Cryptosystem (SCBLC) can be considered an ideal choice for securing communication in IoT devices with limited resources, making significant strides toward enhancing IoT network security.

Effective machine learning regression models are useful toolsets for managing and planning energy in PV grid-connected systems. Machine learning regression models, however, have been crucial in the analysis, forecasting, and prediction of numerous parameters that support the efficient management of the production and distribution of green energy. This article proposes multiple regression models for power prediction using the Sharda University PV dataset (2022 Edition). The proposed regression model is inspired by a unique data pre-processing technique for forecasting PV power generation. Performance metrics, namely mean absolute error (MAE), mean squared error (MSE), root mean squared error (RMSE), R2-score, and predicted vs. actual value plots, have been used to compare the performance of the different regression. Simulation results show that the multilayer perceptron regressor outperforms the other algorithms, with an RMSE of 17.870 and an R2 score of 0.9377. Feature importance analysis has been performed to determine the most significant features that influence PV power generation.

Presents corrections to the paper, (Corrections to “Defending CNN Against FGSM Attacks Using Beta-Based Personalized Activation Functions and Adversarial Training”).

An optimal energy mix of various renewable energy sources and storage devices is critical for a profitable and reliable hybrid microgrid system. This work proposes a hybrid optimization method to assess the optimal energy mix of wind, photovoltaic, and battery for a hybrid system development. This study considers the hybridization of a Non-dominant Sorting Genetic Algorithm II (NSGA II) and the Grey Wolf Optimizer (GWO). The objective function was formulated to simultaneously minimize the total energy cost and loss of power supply probability. A comparative study among the proposed hybrid optimization method, Non-dominant Sorting Genetic Algorithm II, and multi-objective Particle Swarm Optimization (PSO) was performed to examine the efficiency of the proposed optimization method. The analysis shows that the applied hybrid optimization method performs better than other multi-objective optimization algorithms alone in terms of convergence speed, reaching global minima, lower mean (for minimization objective), and a higher standard deviation. The analysis also reveals that by relaxing the loss of power supply probability from 0% to 4.7%, an additional cost reduction of approximately 12.12% can be achieved. The proposed method can provide improved flexibility to the stakeholders to select the optimum combination of generation mix from the offered solutions.

Photovoltaic (PV) and wind energy are widely considered eco-friendly renewable energy resources. However, due to the unpredictable oscillations in solar and wind power production, efficient management to meet load demands is often hard to achieve. As a result, precise forecasting of PV and wind energy production is critical for grid managers to limit the impact of random fluctuations. In this study, the kernel recursive least-squares (KRLS) algorithm is proposed for the prediction of PV and wind energy. The wireless sensor network (WSN) typically adopted for data collection with a flexible configuration of sensor nodes is used to transport PV and wind production data to the monitoring center. For efficient transmission of the data production, a link scheduling technique based on sensor node attributes is proposed. Different statistical and machine learning (ML) techniques are examined with respect to the proposed KRLS algorithm for performance analysis. The comparison results show that the KRLS algorithm surpasses all other regression approaches. For both PV and wind power feed-in forecasts, the proposed KRLS algorithm demonstrates high forecasting accuracy. In addition, the link scheduling proposed for the transmission of data for the management of distributed renewable energy resources is compared with a reference technique to show its comparable performance. The efficacy of the proposed KRLS model is better than other regression models in all assessment events in terms of an RMSE value of 0.0146, MAE value of 0.00021, and R2 of 99.7% for PV power, and RMSE value of 0.0421, MAE value of 0.0018, and R2 of 88.17% for wind power. In addition to this, the proposed link scheduling approach results in 22% lower latency and 38% higher resource utilization through the efficient scheduling of time slots.

Point cloud registration is a fundamental task in many applications such as localization, mapping, tracking, and reconstruction. Successful registration relies on extracting robust and discriminative geometric features. Though existing learning-based methods require high computing capacity for processing a large number of raw points at the same time, computational capacity limitation is not an issue thanks to powerful parallel computing process using GPU. In this paper, we introduce a framework that efficiently and economically extracts dense features using a graph attention network for point cloud matching and registration (DFGAT). The detector of the DFGAT is responsible for finding highly reliable key points in large raw data sets. The descriptor of the DFGAT takes these keypoints combined with their neighbors to extract invariant density features in preparation for the matching. The graph attention network (GAT) uses the attention mechanism that enriches the relationships between point clouds. Finally, we consider this as an optimal transport problem and use the Sinkhorn algorithm to find positive and negative matches. We perform thorough tests on the KITTI dataset and evaluate the effectiveness of this approach. The results show that this method with the efficiently compact keypoint selection and description can achieve the best performance matching metrics and reach the highest success ratio of 99.88% registration in comparison with other state-of-the-art approaches.

Wireless sensor networks (WSNs) have been widely used due to their extensive range of applications [...]

Intelligent Transportation System (ITS) has evolved into a system for provision of traffic information and traffic control with the help of advanced IT technologies [...]

As the number of electric vehicles (EVs) significantly increases, the excessive charging demand of parked EVs in the charging station may incur an instability problem to the electricity network during peak hours. For the charging station to take a microgrid (MG) structure, an economical and energy-efficient power management scheme is required for the power provision of EVs while considering the local load demand of the MG. For these purposes, this study presents the power management scheme of interdependent MG and EV fleets aided by a novel EV charging/discharging scheduling algorithm. In this algorithm, the maximum amount of discharging power from parked EVs is determined based on the difference between local load demand and photovoltaic (PV) power production to alleviate imbalances occurred between them. For the power management of the MG with charging/discharging scheduling of parked EVs in the PV-based charging station, multi-objective optimization is performed to minimize the operating cost and grid dependency. In addition, the proposed scheme maximizes the utilization of EV charging/discharging while satisfying the charging requirements of parked EVs. Moreover, a more economical and energy-efficient PV-based charging station is established using the future trends of local load demand and PV power production predicted by a gated recurrent unit (GRU) network. With the proposed EV charging/discharging scheduling algorithm, the operating cost of PV-based charging station is decreased by 167.71% and 28.85% compared with the EV charging scheduling algorithm and the conventional EV charging/discharging scheduling algorithm, respectively. It is obvious that the economical and energy-efficient operation of PV-based charging station can be accomplished by applying the power management scheme with the proposed EV charging/discharging scheduling strategy.

Online accurate estimation of remaining useful life (RUL) of lithium-ion batteries is a necessary feature of any smart battery management system (BMS). In this paper, a novel partial discharge data (PDD)-based support vector machine (SVM) model is proposed for RUL prediction. The proposed algorithm extracts the critical features from the voltage and temperature of PDD to train the SVM models. The classification and regression attributes of SVM are utilized to classify and predict accurate RUL. The different ranges of PDD were analyzed to find the optimal range for training the SVM model. The SVM model trained with optimal PDD features classifies the RUL into six different classes for gross estimation, and the support vector regression is used to estimate the accurate value of the last class. The classification and predictive performance of SVM model trained using the full discharge data and PDD are compared for publicly available data. Results show that the SVM classification and regression model trained with PDD features can accurately predict the RUL with low storage pressure on BMS. The PDD-based SVM model can be utilized for online RUL estimation in electric vehicles.

Energy storage system (ESS) technology is still the logjam for the electric vehicle (EV) industry. Lithium-ion (Li-ion) batteries have attracted considerable attention in the EV industry owing to their high energy density, lifespan, nominal voltage, power density, and cost. In EVs, a smart battery management system (BMS) is one of the essential components; it not only measures the states of battery accurately, but also ensures safe operation and prolongs the battery life. The accurate estimation of the state of charge (SOC) of a Li-ion battery is a very challenging task because the Li-ion battery is a highly time variant, non-linear, and complex electrochemical system. This paper explains the workings of a Li-ion battery, provides the main features of a smart BMS, and comprehensively reviews its SOC estimation methods. These SOC estimation methods have been classified into four main categories depending on their nature. A critical explanation, including their merits, limitations, and their estimation errors from other studies, is provided. Some recommendations depending on the development of technology are suggested to improve the online estimation.

Reliable and accurate state of charge (SOC) monitoring is the most crucial part in the design of an electric vehicle (EV) battery management system (BMS). The lithium ion battery (LIB) is a highly complex electrochemical system, which performance changes with age. Therefore, measuring the SOC of a battery is a very complex and tedious process. This paper presents an online data-driven battery model identification method, where the battery parameters are updated using the Lagrange multiplier method. A battery model with unknown battery parameters was formulated in such a way that the terminal voltage at an instant time step is a linear combination of the voltages and load current. A cost function was defined to determine the optimal values of the unknown parameters with different data points measured experimentally. The constraints were added in the modified cost function using Lagrange multiplier method and the optimal value of update vector was determined using the gradient approach. An adaptive open circuit voltage (OCV) and SOC estimator was designed for the LIB. The experimental results showed that the proposed estimator is quite accurate and robust. The proposed method effectively tracks the time-varying parameters of a battery with high accuracy. During the SOC estimation, the maximum noted error was 1.28%. The convergence speed of the proposed method was only 81 s with a deliberate 100% initial error. Owing to the high accuracy and robustness, the proposed method can be used in the design of a BMS for real time applications.

The lithium-ion battery has high energy and power density, long life cycle, low toxicity, low discharge rate, more reliability, and better efficiency compared to other batteries. On the other hand, the issue of a reduction in charging time of the lithium-ion battery is still a bottleneck for the commercialization of electric vehicles (EVs). Therefore, an approach to charge lithium-ion batteries at a faster rate is needed. This paper proposes an efficient, real-time, fast-charging methodology of lithium-ion batteries. Fuzzy logic was adopted to drive the charging current trajectory. A temperature control unit was also implemented to evade the effects of fast charging on the aging mechanism. The proposed method of charging also protects the battery from overvoltage and overheating. Extensive testing and comprehensive analysis were conducted to examine the proposed charging technique. The results show that the proposed charging strategy favors a full battery recharging in 9.76% less time than the conventional constant-current–constant-voltage (CC/CV) method. The strategy charges the battery at a 99.26% state of charge (SOC) without significant degradation. The entire scheme was implemented in real time, using Arduino interfaced with MATLABTM Simulink. This decrease in charging time assists in the fast charging of cell phones and notebooks and in the large-scale deployment of EVs.