Renewable Energy, Green Computing, and Sustainable Development

Technology with renewable energy have crucial Solar energy plays a crucial role in tackling the worldwide shift towards sustainable energy sources. Photovoltaic (PV) systems and fuel cells are two prominent sources of clean energy; however, they exhibit intermittent and variable power generation patterns, hindering their widespread adoption. This paper proposes a novel approach to improve performance of Hybrids (SPV-FCH) through the integration of Artificial Intelligence (AI) techniques. The synergy aims to create more reliable, continuous power generation system with joining nature renewable energy which includes consistent contribution of fuel cells. The integration of AI algorithms offers an intelligent control mechanism that optimizes the operation of the hybrid system, thereby overcoming fluctuations in irradiance of solar, the dynamic nature of energy demand. The AI-enabled control system employs predictive analytics and machine learning algorithms to forecast solar irradiance patterns, weather conditions, and energy consumption trends. By leveraging real-time data and historical patterns, the system can dynamically adjust both the components, optimizing their performance for maximum energy output, efficiency, and overall system reliability. Furthermore, the AI system enables proactive maintenance and fault detection, enhancing the overall resilience and longevity of the hybrid system. Through continuous learning and adaptation, the AI controller refines its predictions and control strategies, ensuring optimal performance under varying environmental conditions. This paper discusses the design and implementation of the AI-enabled control system for SPV-FCH hybrids, highlighting its effectiveness in achieving improved energy yield, grid stability, and cost-effectiveness. The proposed approach not only addresses the intermittent challenges associated with solar PV but also maximizes the utilization of both technologies, contributing advancement sustainable including resilient power solutions. The findings presented in this paper contribute valuable insights into the integration of AI in renewable energy systems, paving the way for smarter and more efficient hybrid power generation technologies.

The detection of fraudulent actions has become a major challenge for upholding the integrity of financial systems in today’s complex and ever-changing financial world. This study recommends a novel method for detecting and preventing financial network fraud by combining the strengths of graph analytics and machine learning. To begin, the paper defines financial networks and describes the intricate relationships and transactions that characterize them. The subtle patterns and abnormalities that indicate fraudulent behaviours in these networks are difficult for conventional fraud detection technologies to capture. Using the abundant structural information available in financial graphs, our proposed integration of graph analytics and machine learning fills this void. When it comes to modelling the complex relationships between entities in financial networks, graph analytics provides a natural framework. An exhaustive graph structure is generated, capturing the complex web of relationships, by modelling entities as nodes and monetary transactions as edges. The use of sophisticated graph algorithms allows us to unearth previously unseen patterns and identify outliers that may point to fraudulent behaviour. Machine learning approaches complement graph analytics by providing the capacity to learn complicated patterns from massive datasets. The graph structure, transaction history, and context data are mined using these methods in our method. When graph-derived characteristics are combined with machine learning algorithms, subtle, high-dimensional patterns that could otherwise go undetected might be found. We run trials on real-world financial datasets, contrasting the results with those of more conventional methods, to verify the efficacy of our proposed approach. The outcomes show a considerable improvement in fraud detection accuracy, with fewer false positives. We also demonstrate the model’s flexibility by using an incremental learning framework to account for new forms of fraud. This paper presents a novel approach to tackling the difficulties of financial network fraud detection by combining graph analytics and machine learning. Our method demonstrates a resilient and flexible way to tackle the ever-changing landscape of financial fraud by combining the structural insights of graph analytics with the pattern recognition skills of machine learning.

An issue with power quality is one that arises from an abrupt increase in an abnormal voltage, current, or frequency. Poor power quality or non-linear loads can lead to a distribution system’s voltage sag, swell, interruptions, harmonics, and transients, among other issues. Various compensating devices are utilized nowadays to enhance power quality. To provide quick, adaptable, and effective solutions for different power disturbances which include devices like DVR Voltage Re-storer and DSTATCOM are taking into consideration advancements in power electronic technologies like converter with various magnitudes. These tools rectify magnitude, current, source disturbances brought on by various defects and loads. In order to test it and lower total harmonic distortion, they are connected to the main distribution network using the IEEE 14 Bus standard. To improve power quality in the utility, the use of sophisticated instruments for power quality analysis is becoming more and more important every day. In order to reduce harmonics in bus voltages and bus currents, DSTATCOM and DVR employ optimal PI-based neural network techniques and linear regression techniques, which are analyzed and compared in this study.

Diabetes mellitus, characterized as a chronic metabolic condition, presents a notable global health concern. Timely detection and intervention play a crucial role in the effective management and enhancement of patient outcomes. This research paper explores the application of logistic regression as a predictive tool for diabetes diagnosis. Leveraging a substantial dataset containing clinical and patient-related variables, our study demonstrates the feasibility and efficacy of logistic regression pinpoint individuals susceptible to developing diabetes. By analyzing relevant features, and calculating the sigmoid function, cost function, and gradient descent from scratch and employing an optimal threshold, the logistic regression model exhibits commendable accuracy, sensitivity, and specificity. These findings highlight its potential as an early diagnostic tool. Such predictive models hold promise for healthcare practitioners, enabling them to proactively identify high-risk individuals and initiate preventive measures. As a cost-effective and accessible method, logistic regression aids in the early diagnosis and management of diabetes, ultimately leading to enhanced healthcare strategies and patient care.

On demand with green generation in sustainable development. Renewable sources assure fascinating parameters for reduced operating cost along with increased life span. Technological developments in the domains of wind generators and turbines made the investors opt for wind energy generation. Varied speed with IGs is an attractive option with initial price independent watt less. Due to the advantage of harvesting huge amounts, Power system Operators (PSOs) to incline towards DFIGs. LVRT watt-less power using RFO & ANN controller and Grey Wolf Optimization (GWO) controller.

The passive islanding detection methodologies for the integrated DG approach are the primary subject of this study. Combined with fossil fuel sources and utilized in a cumulative manner, renewable energy generation and the grid are helping to satisfy the growing load demand. Unintentional islanding is the primary challenge of renewable arrangement coordination with grid connectivity. In the event of energy system islanding, the DG will detach from the main grid and begin supplying electricity to locally linked loads. According to many interconnections of DG systems, islanding will be recognized within 2 s using the techniques now in use for isolating the DG hardware from the grid. ‘Remote controlling procedures’ refer to islanding techniques that operate from the utility side, whereas ‘local controlling procedures’ are those that are implemented on the DG side. The methods for detecting passive islanding and the characteristics by which they may be evaluated are the topic of this study. The study provides a thorough discussion of the pros and cons, energy concerns, Zone of Non-Detection, islanding detection of balanced state, and merits of many different passive islanding detection approaches. For researchers developing advanced islanding detection systems, this paper’s thorough explanation of Passive islanding strategies is a valuable resource.

In this paper, a new iterative process called NIP is introduced and some convergence theorems for approximation of fixed points (FPs) of contractive and non-expansive maps are proved. It is also shown that NIP converges rapidly than many existing iterative processes. This new iterative scheme requires least number of iterations as compared with the existing iteration procedures like Picard, Mann, Ishikawa, Noor, Agarwal, Abbas and many others. Further, the same is validated numerically as well as graphically by considering some standard functions.

A design-based model can effectively involve various phases, such as defining Functional Specifications, Design Specifications, Testing and Authentication, and Implementation. However, this paper’s case study will only cover the first two stages. The results obtained from this study will provide insights into how system designers can make decisions based on complex execution that may accurately rely both basic and complex designs, approaching practical models with great precision. However, there is a trade-off between precision and design complexity when making decisions. While necessary models with accurateness are considered, determining values, especially in the initial stage of model development, can be challenging. Additionally, simulating these accurate models can be time-consuming. Therefore, a more detailed level of simulation model is necessary. Consequently, system designers require a comprehensive understanding of system power flow during the initial modeling phase. In the second phase, it is crucial to design more accurate models for different systems, including selecting appropriate parameters for energy management systems and types of converters. This paper emphasizes that a model behavior which has high reliability enables necessary adjustments.

Because of lower stress in terms of rate of voltage, current, and harmonic content, most Inverters which include Multilevel are frequently used in applications like different power converters. This study primarily focuses on a new parallel H-bridge Current Source Multilevel Inverter (CSMLI) circuit arrangement for power system applications. The suggested circuit operates by coupling a DC source to the H-bridge CSI to produce the multi-level output current waveform. Othered power device count, inverter losses, and other novel features can be found in the suggested circuit. The effectiveness of the selected nine-level H-bridge CSI is evaluated through the MATLAB/Simulink program and a Multicarrier PWM control approach.

Hybrid photovoltaic systems have become a common solution for reducing energy consumption in specific objects and for customers in the present time. The efficiency of the entire system also depends on the technology of the battery inverter used. Generally, DC coupled inverters are known to be more energy efficient. However, in certain cases, AC coupled systems can provide better results. The ongoing aggression by Russia against Ukraine has escalated the problem of internal migration, which can only be solved by constructing new communities of emergency shelters. The integration of these units into the overloaded and damaged distribution grids in Ukraine must be carefully planned to limit power consumption and injection. Significant savings can be achieved by properly applying AC or DC coupled systems.

This article discusses this phenomenon based on specific real cases that are defined by consumption profiles, battery storage system management, climate conditions, and PV system design. Simulations presented in the article demonstrate the expected annual energy flows for both technologies in a model situation. The differences between DC coupling and AC coupling solutions are explained through in-depth analyses of inverter behavior, battery behavior, charging strategies, charging losses, discharging losses, state of charge (SOC), cycle load, and the correlation between own consumption and inverter self-consumption. The results show that choosing the right battery inverter technology can lead to significant energy savings from the installed PV system. In certain cases, AC coupled systems not only offer higher flexibility and modularity but also higher energy efficiency for the hybrid system, lower grid feed-in, and better economic profitability.

An adaptive bike prototype that employs a new manual charging mechanism to generate energy from renewable sources is the primary focus of this research. This study presents a sustainable method for short distance travel in response to the growing pollution from vehicles and the rising need for environmentally friendly modes of transportation. Proving that human power can effectively replace non renewable energy sources is the main goal of this study. By incorporating a smartly engineered adaptive bicycle, our goal is to transform the mechanical energy of rotation into electrical energy, which can then be stored in a dedicated battery. After that, the bike’s electric motor draws on the stored energy to propel the rider forward. Building and testing a prototype that efficiently collects and stores energy while pedalling is an important part of our technique. A thorough evaluation of the mechanical parts, the method of electrical conversion, and the effectiveness of battery storage are all part of the process. We test the adaptive bike’s ability to charge itself without any outside power sources by conducting a battery of controlled trials and performance assessments. With an average efficiency of X% in energy conversion, the data show that the manual charging method was successfully integrated. Adaptive bicycles, in particular, show great promise for widespread use as a green, efficient mode of transportation for shorter commutes. This fresh perspective emphasizes the possibility of incorporating renewable energy technologies with conventional transportation, encouraging a greener and more long lasting way to get about. The accomplishment of including a manual charging mechanism for bicycles is a noteworthy new discovery that enables sustainable and environmentally friendly short distance riding. Reducing reliance on non-renewable energy sources for transportation is one of the environmental challenges that this invention aims to solve.

This paper going to review the different optimization tools used in the distributed energy systems. Optimization tools are generally used to size the individual renewable sources.as well as used to analysis the economic part of the system in terms of cost of Energy (COE), Net present cost (NPC), Internal rate of return (IRR), simple payback period, Operating cost and capital cost of system. Due to rapid development in technology, various optimization tools such as Genetic Algorithm, Machine Learning Algorithm, Fuzzy logic, Artificial Intelligence was developed by the researcher for optimize hybrid renewable energy system (HRE). Because of global warming, penetration of renewable energy in the grid, commercial building, educational building and residential consumer was increasing gradually and it is very important to have a optimization tool to check the feasibility of the project before going for the real time installation of HRE system. In this paper various optimization tools used by the researcher is going to be investigated in detailed.

Enhancing Green Energy Development and Mitigating Emissions: A Dual-Focused Approach in Renewable Energy Initiatives The advancement of alternative green energy sources, such as wind energy, and the reduction of greenhouse gas emissions form a two-pronged strategy for renewable energy projects. The integration of power electronic-based controls has enabled Wind Energy Conversion Systems (WECS) to generate a consistent electric power output, irrespective of variations in the wind profile. As one of the most widely utilized renewable sources, wind energy plays a pivotal role in achieving sustainable power generation. This study canters on optimizing Perturb and Observe (P&O) algorithms, presenting a novel solution to address the shortcomings of current methods. Many existing approaches omit the initial tracking phase and assume an incorrect optimal generator speed, overlooking the inertia of WECS. The proposed Optimized Perturb and Observe (OPO) algorithm introduces a swift Maximum Power Point Tracking (MPPT) technique, employing innovative tracking methods to identify the optimal generator speed (Gs) in proximity to the Maximum Power Point (MPP). This enhances the efficiency and reliability of existing P&O algorithms. The research employs three control loops, incorporating Machine Learning (ML) techniques to optimize the P&O control. The primary focus is on analyzing and validating the performance of the proposed OPO algorithm for MPPT control systems. Leveraging the convergence capabilities of the optimization method and the global search capabilities of swarm intelligence, the research aims to maximize power output and contribute to the ongoing efforts in sustainable energy solutions.

Image inpainting is a method that can be employed to repair damaged images and remove distracting elements. The effectiveness of image inpainting approach heavily relies on the computation of patch priority and the selection of exemplar patches in exemplar-based methods. The occurrence of the dropping effect in the computation of the most significant patch priority and the occurrence of matching errors in the selection of the best patch are the primary concerns in example inpaint approaches. The upgraded priority calculation approach is utilized to prevent the dropping effect and introduces a new similarity evaluating procedure called Square of Mean Difference (SMD). The effectiveness of the suggested strategies is evaluated by qualitatively evaluating them with the existing methods. The results demonstrate that the suggested methods surpassed the performance of the existing strategies.

Main objective of line of reversible priority encoder depends on QCA. Among important stages and processes. A cutting-edge kind of nanotechnology is known as quantum-dot cellular automata (QCA). It could be used as the foundation for reversible and digital circuit construction. In this study, a proposal for a simple, reversible, and encoders with the ratio of four inputs and two outputs are considered. It is possible to construct a reversible encoder circuit by making use of the Toffoli gate design, which is simple and very inexpensive. The simulation tool QCA Designer is used in order to evaluate the suggested designs for their level of structural soundness.