Memristor technology has grown rapidly since its beginnings and become a potential candidate to revolutionize how data is stored and processed throughout all of the circuit theory. The memristor-based digital logic circuits can be a promising alternative to traditional integrated circuit technology when examining any advanced computer systems. In this work, we propose a hardware design for memristor-based resistive random access memory (RRAM) using Verilog hardware description language (Verilog HDL). The implementation results of a 256-byte memory on Xilinx Vivado targeted for the Artix-7 FPGA board demonstrate that the memristor-based RRAM outperforms the conventional RAM in terms of power consumption. Furthermore, the proposed architectures use less than 8% of the available hardware resources on the Artix-7 board. Hence, the proposed approach can be integrated into Internet of Things (IoT) applications with limited hardware resources or extended to memory systems in memory systems with larger capacities.

This paper presents a novel approach for detecting faults in photovoltaic (PV) cells. The proposed method combines the power of You Only Look Once version 8 (YOLOv8) and Particle Swarm Optimization (PSO) architecture. Unlike existing methods, the proposed model leverages PSO to optimize the parameters of YOLOv8, enhancing detection accuracy. To evaluate the efficacy of the proposed approach, two experimental cases are conducted, one with a 70% training set and the other with an 80% training set. The PV system data is used as input for the model, and YOLOv8 is utilized to extract necessary features before detecting fault cells from the data. We use PSO algorithm to optimize the model’s parameters to achieve the best detection accuracy. The experimental results demonstrate that the proposed approach achieves the highest mean Average Precision (mAP) of 94% at an intersection over union (IoU) threshold of 0.5, outperforming existing fault detection methods in terms of accuracy and robustness. Moreover, by leveraging the power of YOLOv8 and PSO, the approach offers a promising solution for reliable and efficient fault detection in PV systems, thus making it a practical solution to enhance the system’s performance and reduce maintenance expenses.

In the past few years, accurate wind speed forecasting has become progressively important due to the growing demand for renewable energy sources. In this study, we propose a novel artificial model, Grey Wolf Optimization (GWO)-nested Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN)-Convolutional Neural Network (CNN)-Bidirectional Long Short-Term Memory (BiLSTM), for wind speed forecasting. The proposed model integrates three powerful techniques: CEEMDAN, CNN, and BiLSTM. Firstly, CEEMDAN with two nested layers is used to decompose the wind speed time series into a set of intrinsic mode functions (IMFs) to enhance the accuracy of the model. CNN is then applied to extract features from the IMFs, and BiLSTM is used to capture the temporal dependencies and make accurate predictions. To improve the performance of the model further, we also introduce GWO and apply it to select the best hyperparameters for the forecasting models based on decomposition results. The model is tested using wind speed data collected in Basel in 2022. The final combination result demonstrates that the proposed model achieve a better performance compared to several modern AI-base models in the wind speed forecasting field, with high accuracy reflected by a mean absolute percentage error (MAPE) of nearly 3%.

This study aims to address the increasing complexity of cyber attacks and the sensitivity of wind speed data by exploring the combination of Artificial Intelligence (AI) and cyber security measures for improved wind speed prediction accuracy and security. The collected wind speed dataset is pre-processed and encrypted using the ring learning with errors (ring-LWE) encryption algorithm, which is known for its high level of security. The encrypted data is then input to the Ensemble Empirical Mode Decomposition (EEMD) to split the encrypted signal and reduce the impact of encryption noise. The combination of Convolutional Neural Networks and Long Short-Term Memory (CNN-LSTM) models are also applied to each intrinsic mode function (IMFs) of the decomposition result. Furthermore, the parallel programming framework is also employed during the training phase, significantly improving the processing speed and efficiency. The results of the predictions are decrypted and compared with the testing set, and other works to evaluate the proposed model. The Mean Absolute Percent Error (MAPE) ranges from 7% to 10%, indicating a high level of accuracy. The findings of the study have practical implications for wind energy production and the development of smart grid systems. The study highlights the importance of considering both accuracy and security when using AI and suggests future directions for research in this area, including the development of more advanced encryption algorithms and the integration of AI and cyber security into real-world wind energy systems.