Papers by Dharma Teja Valivarthi
International Journal of Research in Engineering Technology (IJORET), 2019
Efficient cloud resource management is crucial for optimizing performance, reducing costs, and en... more Efficient cloud resource management is crucial for optimizing performance, reducing costs, and ensuring scalability in dynamic cloud environments. This paper proposes a novel framework that integrates ARIMA (Auto Regressive Integrated Moving Average) for forecasting resource demand, Reinforcement Learning (RL) for dynamic resource scaling, and Cuckoo Search (CS) for hyperparameter optimization. The framework leverages the Cloud Computing Performance Metrics Dataset to predict future resource needs and optimize the allocation of cloud resources. The ARIMA model is used to forecast CPU, memory, and network utilization, which are fed into the RL agent to make real-time resource scaling decisions. Cuckoo Search fine-tunes the parameters of both the ARIMA and RL models to enhance their performance. Experimental results demonstrate that the proposed framework achieves a 99% accuracy, 98% resource utilization efficiency, 100 ms latency, and a cost efficiency value of 1.0. These results significantly outperform traditional methods such as Random Forest (RF) and Bi-LSTM, which show accuracy rates of 88% and 80%, respectively. This framework offers a comprehensive and efficient solution for cloud resource optimization, providing both high performance and cost savings. The combination of forecasting and real-time decision-making distinguishes this approach, making it an effective tool for modern cloud environments.
International Journal of Information Technology and Computer Engineering, 2019
Background: This revolutionizes the framework of manufacturing due to the adoption of cloud compu... more Background: This revolutionizes the framework of manufacturing due to the adoption of cloud computing into robotics and automation, allowing the sharing of resources, real-time management of tasks, and enhancement of productivity. The paper reviews optimized cloud manufacturing frameworks for advanced task scheduling in robotic and automation systems, indicating the benefits toward smart manufacturing. Objectives: The paper's objectives include optimization of the task scheduling within the cloudbased framework for robotics and automation systems with the aid of improved resource utilization and better efficiency in operational work. This paper focuses on real-time management of tasks for improvement in responsiveness, scalability in the manufacturing environments. Methods: This paper suggests a cloud architecture integrating task scheduling algorithms, cloud robotics, and automation systems. The methods apply machine learning to predict and optimize, real-time data processing, and cloud computing for resource allocation Results: The Optimized Cloud Manufacturing Framework discussed above would benefit to enhance efficiency in task scheduling by 41%, latency improvement by 47%, and enhanced utilization of the resources by 35% in real-time coordination flows in robotics and automation workflows. Conclusion: This cloud manufacturing framework proposed with advanced techniques of task scheduling enhances operational efficiency, reduces cost, and scales well. It provides a robust solution to integrate robotics and automation in the smart manufacturing environment.
International Journal of Engineering and Science Research, 2023
Background information: Secure, low-latency data sharing has become more difficult as a result of... more Background information: Secure, low-latency data sharing has become more difficult as a result of the Internet of Things' explosive expansion. This paper suggests a fog computing system that uses Federated Byzantine Agreement (FBA) for safe and scalable data sharing, Directed Acyclic Graph (DAG) protocols, and Covariance Matrix Adaptation Evolution Strategy (CMA-ES) and Firefly Algorithm for optimization. By addressing latency and security, the method guarantees effective data sharing. In a variety of IoT scenarios, the results demonstrate increased throughput, security, and decreased latency. Methods: The project incorporates DAG protocols for data routing, FBA for consensus, and CMA-ES and Firefly Algorithm for optimization in fog computing settings. Using a decentralized, fault-tolerant architecture to optimize resource utilization and improve security, these methods guarantee reliable, low-latency data transfer. Objectives: The goal of this research is to create a framework for safe and effective IoT data sharing based on fog computing. Using CMA-ES and the Firefly Algorithm for optimization, it aims to lower latency and improve scalability. It also employs FBA for strong consensus processes and DAG protocols for organized data routing, guaranteeing data integrity and defence against malevolent attacks. Results: Data sharing was significantly enhanced by the suggested paradigm, which also showed increases in throughput of 94%, energy efficiency of 85%, and latency reduction of
International Journal of Advanced Research in Information Technology and Management Science, 2024
This paper introduces a novel method for detecting side-channel attacks in embedded system securi... more This paper introduces a novel method for detecting side-channel attacks in embedded system security by combining Long Short-Term Memory (LSTM), spectral analysis, and convolutional transformer networks. The proposed hybrid model achieves 97% detection accuracy, 95% precision, and 96% recall. It integrates Convolutional Neural Network (CNN) for spatial information extraction, Transformers for sequence data modeling, LSTM for analyzing temporal details, and spectral analysis for frequency domain insights. The framework demonstrates robust real-time performance in identifying subtle side-channel leakages, providing an effective solution for addressing security challenges in critical systems. Objectives: The main objectives of this research are to develop an advanced side-channel attack detection system for embedded security by utilizing a hybrid model that combines spatial, temporal, and frequency domain analyses. The model also aims to provide high detection accuracy and real-time performance to offer a comprehensive solution for cybersecurity challenges. Methods: The proposed method employs a hybrid approach combining CNNs for spatial data extraction, Transformers for sequence modeling, LSTM units for temporal investigation, and spectral analysis for insights from the frequency domain. This combination ensures accurate detection of side-channel attacks in embedded systems, with a focus on real-time applicability. Results: The hybrid model delivers a detection accuracy of 97%, precision of 95%, and recall of 96%. The integration of CNN, Transformer, LSTM, and spectral analysis offers robust performance in detecting subtle side-channel attacks, outperforming conventional methods in terms of detection rates and real-time capability. Conclusion: This hybrid LSTM-Spectral Analysis and convolutional transformer network model provides an efficient and comprehensive solution to detecting side-channel attacks in embedded systems. Its high accuracy, precision, and recall, combined with real-time detection capability, make it a superior approach for enhancing security in critical systems facing evolving cyber threats.
International Journal of Applied Science Engineering and Management, 2022
Background: Disease detection has grown increasingly effective with the quick development of arti... more Background: Disease detection has grown increasingly effective with the quick development of artificial intelligence (AI) and cloud computing (CC), particularly through the real-time processing of large amounts of intricate medical data from Internet of Things (IoT) devices. Accurate and fast disease diagnosis is limited by traditional approaches' difficulties with handling high-dimensional data. Objective: Utilizing the advantages of fuzzy logic and evolutionary optimization, this study attempts establishing a hybrid model that combines the Fuzzy Aggregation Convolutional Neural Network (FA-CNN) and Differential Evolutionary-Extreme Learning Machine (DE-ELM) to improve disease detection accuracy, sensitivity, and computational efficiency in healthcare. Methods: In order to maximize classification accuracy, the suggested model combines DE-ELM with FA-CNN for processing ambiguous healthcare data. The system is more resilient to noisy IoT data if data preprocessing is used, such as feature extraction and normalization. Analyzed and contrasted with conventional techniques are performance parameters such computation time, sensitivity, specificity, and accuracy. Results: FA-CNN + DE-ELM outperformed current models by achieving superior outcomes with a computation time of 65 seconds, accuracy of 95%, sensitivity of 98%, and specificity of 95%. High efficacy in early disease identification and real-time healthcare monitoring is demonstrated by this hybrid technique. Conclusion: A reliable approach to disease identification that maximizes data processing and diagnostic precision is provided by the FA-CNN + DE-ELM hybrid model. The model is positioned as a viable tool for proactive, real-time healthcare diagnostics by combining fuzzy logic with evolutionary algorithms, that improves handling of inaccurate medical data.
International Journal of Information Technology and Computer Engineering, 2021
Background: Cloud computing (CC) and artificial intelligence (AI) are causing a rapid evolution i... more Background: Cloud computing (CC) and artificial intelligence (AI) are causing a rapid evolution in healthcare, meeting the requirement for accurate and effective disease diagnosis and management through wearable IoT devices and sophisticated algorithms. Objective: To develop a BBO-FLC and ABC-ANFIS system that works together for better disease prediction accuracy and real-time monitoring. Methods: Implemented on a scalable cloud architecture, the system combines IoT-enabled sensors for data gathering, ABC for feature optimization, BBO for fuzzy rule refining, and ANFIS for disease categorization. Results: The suggested solution outperformed conventional techniques with 96% accuracy, 98% sensitivity, and 95% specificity at a 60-second computation time reduction. Conclusion: The precision, scalability, and real-time healthcare applications for complicated disease prediction and monitoring could be greatly improved by this integrated system.
International Journal of Applied Science Engineering and Management, 2021
Background Information: The paper explores the integration of Blockchain, AI, MPC, Sparse Matrix ... more Background Information: The paper explores the integration of Blockchain, AI, MPC, Sparse Matrix Storage, and Predictive Control to enhance Human Resource Management (HRM). Current HRM systems are centralized, posing security and efficiency challenges. The proposed system aims to improve data security, scalability, and decision-making using decentralized technologies. Objectives: To design a secure and efficient HRM system by leveraging blockchain technology for decentralized data storage and enhancing decision-making using AI and ML, while incorporating MPC, Sparse Matrix, and Predictive Control for privacy and optimization in data management. Methods: The proposed model integrates Blockchain for security, AI/ML for decision-making, MPC for privacy, Sparse Matrix Storage for efficient data handling, and Predictive Control for risk management. An ablation study evaluates the performance of individual and combined components across various metrics. Results: The full model demonstrates superior performance in data security, scalability, and predictive analytics compared to partial configurations, offering significant improvements in HR data management efficiency and security. Conclusion: Integrating Blockchain with AI, MPC, and other advanced technologies significantly enhances HRM processes by improving data security, scalability, and efficiency. The study emphasizes the importance of combining these components for optimal performance in managing sensitive HR data.
Journal of IoT in Social, Mobile, Analytics, and Cloud, 2025
The rapid development of the Internet of Things (IoT) and its widespread applications in fog comp... more The rapid development of the Internet of Things (IoT) and its widespread applications in fog computing environments have underscored the urgent need for secure, scalable, and energy-efficient data exchange mechanisms. This study introduces a hybrid consensus architecture designed to address these challenges by combining Delegated Proof of Stake (DPoS) and Whale Optimization Techniques (WOT). The primary objective of this model is to optimize resource allocation, enhance security, and minimize energy consumption while ensuring scalable and efficient data sharing within fog-based IoT networks. The proposed methodology utilizes DPoS to limit node validation to a select group of trusted delegates, reducing computational overhead and improving scalability by streamlining the consensus process. Meanwhile, WOT enhances decision-making by mimicking the bubble-net feeding behavior of humpback whales, allowing for dynamic and efficient optimization of resource allocation. The integration of these two techniques significantly boosts system performance. Empirical results demonstrate that the hybrid model achieves a 95% increase in security and a 94% improvement in energy efficiency compared to conventional IoT consensus methods.
Additionally, the model optimizes processing times, increases data throughput, and minimizes latency, facilitating real-time, low-latency communication that is essential for IoT applications. This combination of DPoS and WOT balances resource utilization and effectively addresses the trade-offs between security, energy efficiency, and scalability. Consequently, the hybrid DPoS-WOT consensus model emerges as a robust and practical solution for secure, efficient, and scalable IoT data sharing in fog computing environments
International journal of modern electronics and communication engineering, 2020
Background Information: This study amalgamates blockchain technology with artificial intelligence... more Background Information: This study amalgamates blockchain technology with artificial intelligence and Sparse Matrix Decomposition methodologies to tackle data management issues within Human Resource Management. Conventional HRM systems encounter constraints in security, scalability, and decision-making efficacy, particularly when dealing with extensive, partial datasets. Blockchain guarantees data security, whereas AI offers predictive analytics to enhance HRM functions. Objectives: The project seeks to create a secure, scalable, and effective HRM data management system by integrating blockchain's immutability with AI's predictive skills and Sparse Matrix Decomposition to manage extensive, sparse information and improve decision-making in HR processes. Methods: A prototype system was created utilizing blockchain for decentralized data storage, AI-driven predictive control for human resources trends, and Sparse Matrix Decomposition to handle extensive, incomplete datasets. The system's performance was evaluated based on critical parameters including security, scalability, processing time, and storage efficiency. Results: The proposed solution markedly enhanced data security (0.99), scalability (0.95), storage efficiency (0.96 GB), and prediction accuracy (0.95), surpassing alternative methods in HR data management. Conclusion: Integrating blockchain, artificial intelligence, and Sparse Matrix Decomposition yields a resilient and scalable system for Human Resource Management. It improves data security, prediction accuracy, and system efficiency, providing a revolutionary method for managing extensive HR datasets and enhancing decision-making processes.
International journal of modern electronics and communication engineering, 2023
The goal of the suggested security framework is to improve data security in cloud computing setti... more The goal of the suggested security framework is to improve data security in cloud computing settings by combining several cryptographic techniques with the Secure Hash Algorithm (SHA). With the design, implementation, and evaluation of the security architecture, this allencompassing method concentrates on guaranteeing data integrity, authenticity, and confidentiality. In order to strengthen data transmission and storage, the framework combines public-key encryption, digital signatures, and SHA-256 hash values. First, the message is prepped and hashed, and then the sender's private key is used to create a digital signature. Prior to transmission, the original message, hash, and digital signature are concatenated and encrypted using the recipient's public key. The data is decrypted and its validity and integrity checked upon reception. Strong key management procedures are also incorporated into the framework, which improves system reliability and user satisfaction. User satisfaction rose by 84%, while security efficacy was shown to have improved by 85%. Adherence to pertinent data privacy rules was confirmed by compliance testing. Performance analysis shows that RSA encryption and decryption, although being computationally demanding, offers robust security, whereas SHA-256 hash creation is effective. Large-scale cloud application support for the framework was validated through scalability testing. Data protection is strengthened by the incorporation of digital signatures, which guarantee authentication and non-repudiation. This architecture offers a dependable way to secure sensitive data during transmission and storage, addressing contemporary security issues in cloud and mobile environments. Future research will concentrate on improving user experience, fortifying security safeguards against new threats, and streamlining cryptographic procedures.
International Journal of Engineering & Science Researc, 2024
Improving big data processing performance, efficiency, scalability, and cost-effectiveness requir... more Improving big data processing performance, efficiency, scalability, and cost-effectiveness requires optimizing cloud computing systems. Ensuring data security, increasing energy efficiency, successfully managing resources, and preserving system reliability are some of the major obstacles. For best results, effective resource management strategies like load balancing, autoscaling, and dynamic resource allocation are crucial. Both vertical and horizontal scaling can be used to handle scalability; strong data security protocols and energy-efficient procedures are also essential. System dependability and cost-cutting are also important factors. Maintaining a streamlined cloud environment requires automation, network optimization, real-time monitoring, and adherence to compliance and governance standards. By using a comprehensive strategy, we hope to minimize operating costs and create a robust infrastructure that can manage a wide range of applications and workloads.
Uploads
Papers by Dharma Teja Valivarthi
Additionally, the model optimizes processing times, increases data throughput, and minimizes latency, facilitating real-time, low-latency communication that is essential for IoT applications. This combination of DPoS and WOT balances resource utilization and effectively addresses the trade-offs between security, energy efficiency, and scalability. Consequently, the hybrid DPoS-WOT consensus model emerges as a robust and practical solution for secure, efficient, and scalable IoT data sharing in fog computing environments