Category Archives: Uncategorized

Authors: Assistant Professor Shekhar P Kale, Assistant Professor Vishal K Paithankar

Abstract: Trapping of sediments in rivers is done by various methods as is is tedious job; But still many researches have shown different techniques. By using artificial obstacles for collection of trap we can minimize transfer and deposition of trap in our reservoir. Along with obstacles some river training works found to be useful for collection and deposition of trap at particular location so that it will not get transferred close to the dam site. This research suggests the experiment analysis of trap collection in the river channel prior to dam site. Perennial rivers in which there is no chance to collect or remove the trap in dry period. It is quite possible for seasonal rivers therefore collection of trap in wet season and removal of it in dry season is quite possible in most of the states of India. Reservoir sedimentation has become one of the major problems facing water resources development projects in many countries around the world. However, only a limited number of studies has been reported in this field, particularly addressing the trap efficiency of reservoirs. The most important practical and critical problem related to the performance of reservoirs is the estimation of storage capacity loss due to sedimentation process.. A small-scaled laboratory model was set-up in representing a reservoir and a series of tests were conducted by varying inflow rate, inflow sediment concentration, reservoir capacity and outflow rate. The experimental results were compared with the available theories

DOI: https://doi.org/10.5281/zenodo.20808352

Published by: vikaspatanker

Authors: Assistant Professor Shekhar P Kale, Assistant Professor Vishal K Paithankar

Abstract: The paper addresses the dual environmental challenges of urban waterlogging and the accumulation of non-biodegradable plastic waste 1. This study investigates the feasibility of developing sustainable pervious concrete by partially replacing natural coarse aggregates with waste plastic aggregates at varying levels of 5%, 10%, 15%, and 20%. Experimental specimens, cast as 150 mm x 150 mm x 150 mm cubes using 10 mm aggregates and a water-cement ratio of 0.35, were subjected to rigorous testing for compressive strength, permeability, and workability after 14 days of curing. The results indicate that while increasing the plastic content leads to a reduction in compressive strength and a slight decrease in permeability due to modifications to the void structure, a replacement level of up to 10% offers an optimum balance, maintaining sufficient structural integrity for light-load applications. Ultimately, this research demonstrates that integrating plastic waste into pervious concrete not only aids in groundwater recharge by effectively reducing surface runoff but also provides a viable waste management solution for sustainable infrastructure development.

DOI: https://doi.org/10.5281/zenodo.20808288

Published by: vikaspatanker

Authors: Nilesh.P.Dabe, Yogesh R. Patni, Deepak Kadam, Kulkarni Kirti S

Abstract: Accurate electricity load forecasting is critical for maintaining stability, reliability, and cost efficiency in modern smart grids, especially with the growing integration of renewable energy sources. However, the inherent intermittency and uncertainty of renewables such as solar and wind introduce significant challenges for traditional forecasting models. This paper proposes a Hybrid Generative AI–Enhanced Load Forecasting Model that combines Generative Adversarial Networks (GANs) with deep learning architectures to improve prediction accuracy under varying renewable energy conditions. The generative component synthesizes high-variance energy patterns that capture extreme fluctuations, while the predictive module leverages a hybrid CNN–LSTM network for temporal–spatial learning. Experimental results on real-world datasets demonstrate substantial improvements, with reductions of 40.1% in MAE, 38.2% in RMSE, and enhanced robustness against high-uncertainty renewable inputs. The proposed model also reduces load–supply mismatch by 42.4% and energy imbalance cost by 41.3%, leading to more efficient power distribution and operational cost savings. These findings highlight the potential of Hybrid Generative AI to significantly enhance smart grid forecasting performance and support resilient, data-driven energy management strategies.

DOI: https://doi.org/10.5281/zenodo.20808188

Published by: vikaspatanker

Authors: Nilesh.P.Dabe, Yogesh R. Patni, Deepak Kadam, Kulkarni Kirti S

Abstract: Precise prediction of residential power consumption, and effective management of load are important tasks in smart grid. The current research proposes a novel hybrid model of ANN with NSGA-II to solve the multi-objective optimization problems for smart grid operations. The model incorporates four important inputs to simultaneously predict forecast demand and load management reliability: time-of-day, temperature, consumer type, and historical load. The ANN model optimized by NSGA-II offers improved forecasting, resulting in the best fitness value of 855.176 kWh, and the resulting high correlation coefficient R = 0.97432 for the load forecasting. Meanwhile, the model also maintained a high level of load management reliability as present an best Fitness 86.7012 % and a correlation R = 0.93381. Pareto front analysis demonstrated a trade-off solution between forecast accuracy (855.928–855.934 kWh) and reliability (84.043% to 84.086%) and therefore it is flexible in advising grid operator. This NSGA-II-ANN hybrid approach has wide range of applications for real-time load prediction, and better resource allocation and control for increasing smart grid stability in dynamic operation condition.

DOI: https://doi.org/10.5281/zenodo.20808126

Published by: vikaspatanker

Authors: Research scholar Dinesh V Malkhede, Associate professor Dr. Prabhat Sharma

Abstract: Demand Side Management (DSM) has emerged as a critical component of within smart grid frameworks to optimize energy efficiency and mitigate peak load scenarios, and facilitate the integration of renewable energy sources. With the evolution of smart grids, advanced communication infrastructures, intelligent control algorithms, and dynamic pricing mechanisms have significantly transformed DSM strategies. This study explores demand side management by examining its key concepts, goals, and implementation practices, while highlighting pricing-based demand response, optimized appliance scheduling, and smart energy management systems. The review synthesizes recent research contributions covering heuristic, metaheuristic, and artificial intelligence–based approaches, including game theory, evolutionary algorithms, and deep reinforcement learning. The review places special focus on residential DSM, electric vehicle integration, and energy storage technologies, while also outlining major challenges, open research problems, and future research opportunities relevant to researchers and industry professionals.

DOI: https://doi.org/10.5281/zenodo.20808055

Published by: vikaspatanker

Authors: Assistant Professor Bhupendra Deshmukh, Associate Professor Mohite Utkarsha Laxman, Assistant Professor Diksha M Ahire

Abstract: During islanded operation, AC microgrids operate without grid support, making voltage regulation a critical challenge due to load variations, intermittent renewable generation, and inverter-dominated dynamics. In such conditions, maintaining stable voltage becomes difficult without effective local control mechanisms. This paper presents a decentralized voltage control approach based on a PI-dominant PID controller applied at the primary control level. The proposed controller regulates the inverter output voltage to handle disturbances arising from load changes and renewable energy fluctuations, including photovoltaic and fuel cell sources. The control strategy is simple, does not require communication infrastructure, and is suitable for practical implementation. Simulation results obtained using MATLAB/Simulink demonstrate that the proposed method improves voltage stability, minimizes oscillations, and maintains acceptable performance under varying operating conditions.

DOI: https://doi.org/10.5281/zenodo.20807928

Published by: vikaspatanker

Authors: Henry Watson, Megan Foster, Ryan Thompson, Elizabeth Walker, Chaitanya Srinivas, Akhilesh Achari

Abstract: The increasing demand for personalized customer experiences, real-time engagement, and data-driven business strategies has accelerated the adoption of Artificial Intelligence (AI) within Customer Relationship Management (CRM) systems. This research examines AI-Driven CRM Automation Architectures for Modern Enterprise Ecosystems, focusing on the integration of machine learning, predictive analytics, intelligent process automation, cloud computing, and generative AI technologies to enhance customer-centric operations. The proposed architectural framework enables organizations to automate customer interactions, optimize sales and marketing processes, improve service delivery, and generate actionable insights from large volumes of customer data. By leveraging AI-powered recommendation engines, natural language processing, customer behavior analytics, and automated workflow orchestration, enterprises can achieve higher operational efficiency, increased customer satisfaction, and improved decision-making capabilities. The study further explores key architectural components, scalability requirements, security considerations, integration strategies, and governance mechanisms necessary for deploying intelligent CRM platforms in complex enterprise environments. Additionally, it highlights the role of AI-driven automation in fostering business agility, strengthening customer relationships, and supporting digital transformation initiatives. The findings indicate that modern AI-enabled CRM architectures provide a scalable and adaptive foundation for intelligent enterprise ecosystems, enabling organizations to enhance customer engagement, drive sustainable growth, and maintain competitive advantage in an increasingly digital and customer-focused marketplace.

DOI: http://doi.org/10.5281/zenodo.20802461

Published by: vikaspatanker

Authors: Abigail Collins, Jonathan Price, Dr. Natalie Stewart, Michael Reed, Chaitanya Srinivas, Akhilesh Achari

Abstract: The rapid advancement of Artificial Intelligence (AI), machine learning, cloud computing, and intelligent automation is transforming traditional enterprises into autonomous, data-driven organizations. This research explores AI-Orchestrated Enterprise Platforms that leverage autonomous decision intelligence to optimize business operations, enhance strategic decision-making, and improve organizational agility. The proposed framework integrates AI-driven analytics, predictive modeling, knowledge graphs, large language models (LLMs), robotic process automation (RPA), and continuous feedback loops to enable real-time decision orchestration across enterprise environments. By combining contextual awareness, adaptive learning, and autonomous execution capabilities, these platforms can proactively identify opportunities, mitigate risks, and automate complex operational workflows with minimal human intervention. The study examines the architectural components, implementation strategies, benefits, and challenges associated with deploying AI-orchestrated enterprise ecosystems, including scalability, governance, security, explainability, and regulatory compliance. Furthermore, it highlights the role of decision intelligence in fostering resilient, self-optimizing, and intelligent enterprises capable of responding dynamically to evolving business conditions. The findings suggest that AI-orchestrated enterprise platforms represent a significant step toward autonomous digital enterprises, enabling enhanced operational efficiency, improved business outcomes, and sustainable competitive advantage in the era of intelligent automation.

DOI: http://doi.org/10.5281/zenodo.20797625

Published by: vikaspatanker

Authors: Olivia Parker, Rebecca Turner, Samantha Green, Katherine Lewis, Chaitanya Srinivas, Akhilesh Achari

Abstract: The emergence of Generative Artificial Intelligence (Generative AI) is transforming software engineering practices by introducing intelligent automation across the software development lifecycle. In cloud computing environments, where applications must continuously evolve to meet dynamic scalability, performance, security, and reliability requirements, traditional software engineering approaches often face challenges related to complexity, resource management, and rapid deployment demands. This research explores the concept of Autonomous Cloud Software Engineering Through Generative AI Technologies, a framework that leverages advanced AI models to automate software design, code generation, testing, deployment, monitoring, maintenance, and optimization processes within cloud platforms. By integrating large language models, machine learning algorithms, cloud-native architectures, and DevOps practices, the proposed approach enables intelligent decision-making, self-adaptive system behavior, and continuous software improvement with minimal human intervention. The framework facilitates automated requirement analysis, intelligent code synthesis, predictive defect detection, infrastructure optimization, and autonomous operational management, thereby enhancing development productivity and software quality. Furthermore, Generative AI-driven automation supports rapid innovation, reduces development costs, accelerates release cycles, and improves system resilience in highly distributed cloud environments. The study examines the architectural components, enabling technologies, implementation strategies, benefits, and challenges associated with autonomous cloud software engineering and highlights its potential to redefine the future of intelligent software development. The findings suggest that the convergence of Generative AI and cloud computing establishes a robust foundation for creating adaptive, scalable, and self-managing software ecosystems capable of meeting the evolving demands of modern digital enterprises.

DOI: http://doi.org/10.5281/zenodo.20797458

Published by: vikaspatanker

Authors: Samantha Green, Richard Morgan, Katherine Lewis, Benjamin Scott, Chaitanya Srinivas, Akhilesh Achari

Abstract: Modern cloud-native applications increasingly rely on microservice architectures to achieve scalability, flexibility, and resilience. However, the growing complexity of distributed environments presents significant challenges in performance management, resource allocation, fault detection, and service coordination. This paper proposes an intelligent self-optimizing microservice framework driven by autonomous feedback loops that continuously monitor, analyze, and adapt system behavior in real time. The framework integrates feedback-driven control models, artificial intelligence techniques, and automated decision-making mechanisms to dynamically optimize service performance, resource utilization, and operational reliability. By leveraging continuous feedback from runtime metrics, system events, and workload patterns, the proposed approach enables proactive adaptation to changing environmental conditions and application demands without human intervention. The study investigates key architectural components, optimization strategies, and autonomous control mechanisms that support self-healing, self-scaling, and self-configuring capabilities within microservice ecosystems. Experimental analysis demonstrates notable improvements in response time, throughput, fault tolerance, and infrastructure efficiency when compared with conventional static management approaches. The results indicate that autonomous feedback-driven optimization provides a robust foundation for developing intelligent, adaptive, and resilient microservice-based systems capable of meeting the demands of modern cloud and edge computing environments.

DOI: http://doi.org/10.5281/zenodo.20797329

Published by: vikaspatanker