Hybrid Ensemble Deep Learning-Based Approach for Time Series Energy Prediction

An AI-Based Newly Developed Analytical Formulation for Discharging Behavior of Supercapacitors with the Integration of a Review of Supercapacitor Challenges and Advancement Using Quantum Dots

A supercapacitor is a type of electrical component that has larger capacitance, due to asymmetric behavior with better power density, and lower ESR (effective series resistance) than conventional energy-storage components. Supercapacitors can be used with battery technology to create an effective energy storage system due to their qualities and precise characterization. Studies have shown that the use of quantum dots as electrodes in supercapacitors can significantly increase their effectiveness. In this research article, we have used a Drude model based on free electrons (asymmetric nature) to describe the supercapacitor’s discharging characteristics. Commercially available Nippon DLA and Green-cap supercapacitors were used to verify the Drude model by discharging them through a constant current source using a simple current mirror circuit. The parameters of both the fractional-order models and our suggested method were estimated using the least-squares regression fitting approach. An intriguing finding from the Drude model is the current-dependent behavior of the leakage-parallel resistance in the constant current discharge process. Instead of using the traditional exponential rule, supercapacitors discharge according to a power law. This work reflects the strong symmetry of different aspects of designing a hybrid supercapacitor with high efficiency and reliability.

Toward Efficient Intrusion Detection System Using Hybrid Deep Learning Approach

The increased adoption of cloud computing resources produces major loopholes in cloud computing for cybersecurity attacks. An intrusion detection system (IDS) is one of the vital defenses against threats and attacks to cloud computing. Current IDSs encounter two challenges, namely, low accuracy and a high false alarm rate. Due to these challenges, additional efforts are required by network experts to respond to abnormal traffic alerts. To improve IDS efficiency in detecting abnormal network traffic, this work develops an IDS using a recurrent neural network based on gated recurrent units (GRUs) and improved long short-term memory (LSTM) through a computing unit to form Cu-LSTMGRU. The proposed system efficiently classifies the network flow instances as benign or malevolent. This system is examined using the most up-to-date dataset CICIDS2018. To further optimize computational complexity, the dataset is optimized through the Pearson correlation feature selection algorithm. The proposed model is evaluated using several metrics. The results show that the proposed model remarkably outperforms benchmarks by up to 12.045%. Therefore, the Cu-LSTMGRU model provides a high level of symmetry between cloud computing security and the detection of intrusions and malicious attacks.

Symmetry in Renewable Energy and Power Systems II—Including Wind Energy and Fluid Energy

This Special Issue has focused on symmetry in renewable energy and energy systems II—including wind energy and fluid power [...]

Advanced ML-Based Ensemble and Deep Learning Models for Short-Term Load Forecasting: Comparative Analysis Using Feature Engineering

Short-term load forecasting (STLF) plays a pivotal role in the electricity industry because it helps reduce, generate, and operate costs by balancing supply and demand. Recently, the challenge in STLF has been the load variation that occurs in each period, day, and seasonality. This work proposes the bagging ensemble combining two machine learning (ML) models—linear regression (LR) and support vector regression (SVR). For comparative analysis, the performance of the proposed model is evaluated and compared with three advanced deep learning (DL) models, namely, the deep neural network (DNN), long short-term memory (LSTM), and hybrid convolutional neural network (CNN)+LSTM models. These models are trained and tested on the data collected from the Electricity Generating Authority of Thailand (EGAT) with four different input features. The forecasting performance is measured considering mean absolute percentage error (MAPE), mean absolute error (MAE), and mean squared error (MSE) parameters. Using several input features, experimental results show that the integrated model provides better accuracy than others. Therefore, it can be revealed that our approach could improve accuracy using different data in different forecasting fields.

LogLS: Research on System Log Anomaly Detection Method Based on Dual LSTM

System logs record the status and important events of the system at different time periods. They are important resources for administrators to understand and manage the system. Detecting anomalies in logs is critical to identifying system faults in time. However, with the increasing size and complexity of today’s software systems, the number of logs has exploded. In many cases, the traditional manual log-checking method becomes impractical and time-consuming. On the other hand, existing automatic log anomaly detection methods are error-prone and often use indices or log templates. In this work, we propose LogLS, a system log anomaly detection method based on dual long short-term memory (LSTM) with symmetric structure, which regarded the system log as a natural-language sequence and modeled the log according to the preorder relationship and postorder relationship. LogLS is optimized based on the DeepLog method to solve the problem of poor prediction performance of LSTM on long sequences. By providing a feedback mechanism, it implements the prediction of logs that do not appear. To evaluate LogLS, we conducted experiments on two real datasets, and the experimental results demonstrate the effectiveness of our proposed method in log anomaly detection.