PNPraveen Kumar Nalli

Praveen Kumar Nalli

*This is an algorithmically generated author record based on publicly available information.

Praveen Kumar Nalli has a total of 17 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Optimizing Energy Systems Using Machine Learning and Artificial Intelligence

    by Praveen Kumar Nalli, K. P. Manikandan, G. Padmapriya, Dhowmya Bhatt, Nayanjyoti Talukdar, R. Premkumar

    This chapter discusses the potentially transformative role of ML and AI technologies to improve energy systems in terms of efficiency, reliability, and sustainability. Some of the applications of AI and ML in energy systems are advanced algorithms, predictive modeling, and online data analysis. The field of power optimization and fault detection systems is a significant area of focus. The chapter explores advanced energy pricing techniques, including reinforcement learning, deep learning for renewable energy integration, IoT-enabled predictive maintenance, and ethical challenges in these areas. Case studies and real-life insights demonstrate the potential of AI in energy management to enhance decision-making and promote sustainable energy development. The guidelines serve as a foundation for researchers, engineers, and policymakers to harness the potential of AI to significantly transform the global energy landscape.


  • Harnessing Artificial Intelligence for Smart Energy Management System

    by Praveen Kumar Nalli, Ashok Kumar P. S., Thippeswamy G. R., Shalini Sharma, Kalai Priya V., M. Sudhakar

    The chapter explores the potential of AI in transforming SEMS. AI-based technologies, such as machine learning, neural networks, and IoT integration, can monitor energy consumption in real time, predict future energy consumption patterns, and modify or alter energy consumption accordingly within residential, commercial, and industrial sectors. In short, AI optimizes the usage and distribution of energy to make it efficient, save money, and save the environment. Such applications as demand forecasting, load balancing, and integration of renewable energy systems highlight AI's contribution toward sustainability in energy usage. Moreover, the chapter sheds light on some challenges such as data privacy, system interoperability, and cost of implementation with proposals of innovative solutions. On future developments of AI-powered SEMS, decentralized energy grids, and personalization in energy management shall also be addressed.

  • Newfangled Multilevel Inverter fed V/f Controlled Induction Motor Drive with Multicarrier PWM Strategy

    by Durga Prasad Garapati, V. Jegathesan, Praveen Kumar Nalli, Ramu Bhukya, K.P. Swaroop, Sssr Sarathbabu Duvvuri

    In the modern industrial drive system, power electronic converters are employed not only to control the electromechanical energy conversion process, but also facilitate energy efficiency and continued automation. In the drive system, induction motor (IM) is a preferred energy conversion device because of its inherent features. Nowadays, power converters using MLI's playing vital role in the energy conversion process also multilevel configuration allow raising the power-handling capability of the system. Thus, in this paper fifteen level cascaded MLI fed closed loop V/f controlled IM drive is developed and its performance indicators have been analyzed for multicarrier carrier PWM strategy executed using MATLAB/Simulink.


  • Fault Diagnosis of the Newfangled Cascaded H-Bridge Multilevel Inverter

    by Durga Prasad Garapati, V. Jegathesan, Praveen Kumar Nalli, Ramu Bhukya, K.P. Swaroop, S.S.S.R. Sarathbabu Duvvuri

    In recent years multilevel inverters have been extensively worn in high voltage and high power applications for their unique performance. Reliability of the power electronic equipment is very essential to make sure that inverter operation should be stable and it is most important to detect and locate the faults as speedily as possible. This paper deals with open switch-fault finding method in a multilevel inverter using wavelet transformation tool. A fault diagnosis procedure is proposed and executed using MATLAB.


  • Performance Analysis of Cascaded Multilevel Inverter with Reduced Switched Topology

    by Durga Prasad Garapati, V Jegathesan, Praveen Kumar Nalli, Ramu Bhukya, Bommina Sravani Vijaya Bharathi, S.S.S.R. Sarathbabu Duvvuri

    Multilevel inverter plays a crucial role in industrial applications. The performance of cascaded multilevel inverter (CMLI) with reduced switch count is analyzed in this paper. If the switches have been increased the switching loss and THD will increase. The preferred topology is simulated for seven level and fifteen level by considering isolated DC source and PV. The reduced % THD is identified compare to other topologies. Four switches continuously working at fundamental switching frequency is considered as one of the advantage of the topology.