Search

Today, methodologies based on learning models are utilized to generate precise conversion techniques for renewable sources. The methods based on Computational Intelligence (CI) are considered an effective way to generate renewable instruments. The energy-related complexities of developing such methods are dependent on the vastness of the data sets and number of parameters needed to be covered, both of which need to be carefully examined. The most recent and significant researchers in the field of learning-based approaches for renewable challenges are addressed in this article. There are several different Deep Learning (DL) and Machine Learning (ML) approaches that are utilized in solar, wind, hydro, and tidal energy sources. A new taxonomy is formed in the process of evaluating the effectiveness of the strategies that are described in the literature. This survey evaluates the advantages and the drawbacks of the existing methodologies and helps to find an effective approach to overcome the issues in the existing methods. In this study, various methods based on energy conversion systems in renewable source of energies like solar, wind, hydro power, and tidal energies are evaluated using ML and DL approaches.

Electric vehicles (EVs) and photovoltaic (PV) systems have been progressively incorporated into the grid in recent years principally due to two factors: reduced energy costs and lower pollutants. Numerous studies have investigated how integrating PV and EVs into the grid may affect specific people. It is crucial to understand that the electricity grid will experience the combined effects of PV–EV integration as PV and EV penetration increases. The primary motivation for PV’s integration with Vehicle-to-Grid (V2G) and Grid-to-Vehicle (G2V) services is the aim to reduce charging costs from discharging; moreover, another prerequisite must be satisfied before PV arrays will be able to provide V2G services. The range between the driving limit and EV battery degradation should be reasonable. The way EVs charge and discharge will be impacted by these factors. Numerous analyses are required in order to control the power between various source and load scenarios. In order to balance grids and manage frequency, controllers such as Improved Particle Swarm Optimization (IPSO), Improved Ant Colony Optimization (IACO), and Improved Mayfly Optimization (IMO) are used. As a result, V2G/G2V helps feed electricity back into the grid. By providing the proper duty cycle ratio, the proposed controller regulates converter switching. This study allowed for the performance analysis and operation simulation of a grid-connected PV/EV/Grid system. The purpose of this system was to maximize PV self-consumption while maintaining power quality characteristics like harmonics, grid voltage/current, and power factor.

The objective of the proposed work is to develop a Maximum Power Point Tracking (MPPT) controller and inverter controller by applying the adaptive least mean square (LMS) algorithm to control the total harmonics distortion of a solar photovoltaic system. The advantage of the adaptive LMS algorithm is given by its simplicity and reduced required computational time. The adaptive LMS algorithm is applied to modify the Perturb and Observe (P&O), MPPT controller. In this controller, the adaptive LMS algorithm is used to predict solar photovoltaic power. The adaptive LMS maximum power point tracking controller gives better optimal solutions with less steady error 0.7% (6 watts) and 0% peak overshot in power with the tradeoff being more settling time at 0.33 s. The development of the inverter control law is performed using the d-q frame theory. This helps to reduce the number of equations to build a control law. The load current, grid current and grid voltage are sensed and transformed into d and q components. This adaptive LMS control law is used to extract the reference grid currents and, later, to compare them with the actual grid currents. The result of this comparison is used to generate the switching gate pulses for the inverter switches. The proposed controllers are developed and implemented with a solar PV system in MATLAB Simulink. The total harmonics distortion in grid and load current (3.25% and 7%) and voltage (0%) is investigated under linear and non-linear load conditions with changes in solar irradiations. The analysis is performed by selecting step incremental values and sampling time.

In an electric vehicle (EV), using more than one energy source often provides a safe ride without concerns about range. EVs are powered by photovoltaic (PV), battery, and ultracapacitor (UC) systems. The overall results of this arrangement are an increase in travel distance; a reduction in battery size; improved reaction, especially under overload; and an extension of battery life. Improved results allow the energy to be used efficiently, provide a comfortable ride, and require fewer energy sources. In this research, energy management between the PV system and the hybrid energy storage system (HESS), including the battery, and UC are discussed. The energy management control algorithms called Artificial Neural Network (ANN) and Aquila Optimizer Algorithm (AOA) are proposed. The proposed combined ANN–AOA approach takes full advantage of UC while limiting the battery discharge current, since it also mitigates high-speed dynamic battery charging and discharging currents. The responses’ behaviors are depicted and viewed in the MATLAB simulation environment to represent load variations and various road conditions. We also discuss the management among the PV system, battery, and UC to achieve the higher speed of 91 km/h when compared with existing Modified Harmony Search (MHS) and Genetic Algorithm-based Proportional Integral Derivative (GA-PID). The outcomes of this study could aid researchers and professionals from the automotive industry as well as various third parties involved in designing, maintaining, and evaluating a variety of energy sources and storage systems, especially renewable ones.

In recent decades, big data analysis has become the most important research topic. Hence, big data security offers Cloud application security and monitoring to host highly sensitive data to support Cloud platforms. However, the privacy and security of big data has become an emerging issue that restricts the organization to utilize Cloud services. The existing privacy preserving approaches showed several drawbacks such as a lack of data privacy and accurate data analysis, a lack of efficiency of performance, and completely rely on third party. In order to overcome such an issue, the Triple Data Encryption Standard (TDES) methodology is proposed to provide security for big data in the Cloud environment. The proposed TDES methodology provides a relatively simpler technique by increasing the sizes of keys in Data Encryption Standard (DES) to protect against attacks and defend the privacy of data. The experimental results showed that the proposed TDES method is effective in providing security and privacy to big healthcare data in the Cloud environment. The proposed TDES methodology showed less encryption and decryption time compared to the existing Intelligent Framework for Healthcare Data Security (IFHDS) method.

In recent decades, tool wear monitoring has played a crucial role in the improvement of industrial production quality and efficiency. In the machining process, it is important to predict both tool cost and life, and to reduce the equipment downtime. The conventional methods need enormous quantities of human resources and expert skills to achieve precise tool wear information. To automatically identify the tool wear types, deep learning models are extensively used in the existing studies. In this manuscript, a new model is proposed for the effective classification of both serviceable and worn cutting edges. Initially, a dataset is chosen for experimental analysis that includes 254 images of edge profile cutting heads; then, circular Hough transform, canny edge detector, and standard Hough transform are used to segment 577 cutting edge images, where 276 images are disposable and 301 are functional. Furthermore, feature extraction is carried out on the segmented images utilizing Local Binary Pattern (LBPs) and Speeded up Robust Features (SURF), Harris Corner Detection (HCD), Histogram of Oriented Gradients (HOG), and Grey-Level Co-occurrence Matrix (GLCM) feature descriptors for extracting the texture feature vectors. Next, the dimension of the extracted features is reduced by an Improved Dragonfly Optimization Algorithm (IDOA) that lowers the computational complexity and running time of the Deep Belief Network (DBN), while classifying the serviceable and worn cutting edges. The experimental evaluations showed that the IDOA-DBN model attained 98.83% accuracy on the patch configuration of full edge division, which is superior to the existing deep learning models.

The Electric Energy Consumption Prediction (EECP) is a complex and important process in an intelligent energy management system and its importance has been increasing rapidly due to technological developments and human population growth. A reliable and accurate model for EECP is considered a key factor for an appropriate energy management policy. In recent periods, many artificial intelligence-based models have been developed to perform different simulation functions, engineering techniques, and optimal energy forecasting in order to predict future energy demands on the basis of historical data. In this article, a new metaheuristic based on a Long Short-Term Memory (LSTM) network model is proposed for an effective EECP. After collecting data sequences from the Individual Household Electric Power Consumption (IHEPC) dataset and Appliances Load Prediction (AEP) dataset, data refinement is accomplished using min-max and standard transformation methods. Then, the LSTM network with Butterfly Optimization Algorithm (BOA) is developed for EECP. In this article, the BOA is used to select optimal hyperparametric values which precisely describe the EEC patterns and discover the time series dynamics in the energy domain. This extensive experiment conducted on the IHEPC and AEP datasets shows that the proposed model obtains a minimum error rate relative to the existing models.

Nowadays, many organizations and individual users are employing cloud services extensively due to their efficiency, reliability and low cost. A key aspect for cloud data centers is to achieve management methods to reduce energy consumption, increasing the profit and reducing the environmental impact, which is critical in the deployment of leading-edge technologies today such as blockchain and digital finances, IoT, online gaming and video streaming. In this review, various clustering, optimization, and machine learning methods used in cloud resource allocation to increase the energy efficiency and performance are analyzed, compared and classified. Specifically, on the one hand, we discuss how clustering methods and optimization techniques are widely applied in energy management due to their capacity to provide solutions for energy consumption reduction. On the other hand, we study how multi-objective optimization methods focus on reducing energy consumption as well as service level agreement (SLA) violation, and improving quality of services (QoS) simultaneously. Also, we discuss how optimization methods such as the firefly algorithm, whale optimization algorithm (WOA), particle swarm optimization (PSO) and genetic algorithm (GA) provide the highest performance in the field. Moreover, we analyze how machine learning methods such as deep neural network (DNN), random forest, and support vector machine (SVM) are applied to the prediction of energy consumption in the cloud, showing an accurate performance in this prediction. Nevertheless, we study how the existing methods still have limitations of low convergence, trap into local optima and overfitting.

Visible Light Communication (VLC) is a promising field in optical wireless communications, which uses the illumination infrastructure for data transmission. The important features of VLC are electromagnetic interference-free, license-free, etc. Additionally, Multiple-Input-Multiple-Output (MIMO) techniques are enabled in the VLC for enhancing the limited modulation bandwidth by its spectral efficiency. The data transmission through the MIMO-VLC system is corrupted by different interferences, namely thermal noise, shot noise and phase noise, which are caused by the traditional fluorescent light. In this paper, an effective precoding technique, namely Block Bi-Diagonalization (BBD), is enabled to mitigate the interference occurring in the indoor MIMO-VLC communications. Besides, a Quadrature Amplitude Modulation (QAM) is used to modulate the signal before transmission. Here, the indoor MIMO-VLC system is developed to analyze the communication performance under noise constraints. The performance of the proposed system is analyzed in terms of Bit Error Rate (BER) and throughput. Furthermore, the performances are compared with three different existing methods such as OAP, FBM and NRZ-OOK-LOS. The BER value of the proposed system of scenario 1 is 0.0501 at 10 dB, which is less than that of the FBM technique.