J.JAYAKUMAR
@karunya.edu
Professor
Karunya Institute of Technology and Sciences
RESEARCH INTERESTS
Power system
Renewable Energy
Machine Learning
Artificial Intelligence
Optimization
FUTURE PROJECTS
Development of Smart Grid Test bed system
Developing 5 bus system
Applications Invited
Knowledge in smart grid
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
Khammampati R. Sreejyothi, P. Venkatesh Kumar, and J. Jayakumar
Institute of Advanced Engineering and Science
This paper presents fractional order sliding mode control (FOSMC) based distribution system compensator (DSTATCOM) for power quality improvement in the distribution system. The three-phase two-level inverter-based voltage source converter (VSI) with DC-link capacitor is used as DSTACOM. In this paper, the FOSMC-based DSTATCOM improves supply current harmonics, load balancing, and reactive power and reduces THD. The sinusoidal pulse width modulation (SPWM) is generating gating pulses for VSI. The performance of the presented system is verified in MATLAB/Simulink software. The simulations are verified source voltage, current and load current as well as compensating current. The FOSMC has maintained a constant supply current when connecting non-linear load. The hardware results are also presented in the manuscript. The hardware results are supply current, voltage, compensating current, and load current.
Jayakumar Jayaraj, Dakka Obulesu, Hemaprabha Govindaraj, Francisxavier Thomas, Nagalingam Rajeswaran, Chilakala Rami Reddy, Abdullah S. Algarni, Abdullah Alwabli and Saeed Faisal Malky
A smart battery electric vehicle control framework is proposed in this paper. The specific controller empowers ceaseless observation and management of the battery's state with the scope of extending the vehicle's driving range under varying temperature and driving pattern conditions. The proposed method utilizes an incorporated scheme for dealing with a crossover energy stockpiling framework to expand a battery's lifespan while further ensuring its smooth activity.
Karunakar Thadkapally, Francisxavier Thomas Josh, Jeyaraj Jency Joseph, and Jayaraj Jayakumar
Institute of Advanced Engineering and Science
High voltage direct current (HVDC) transmission is flexible towards the power control (produced by solar or wind) and can be transported over thousands of kilo meters with minimal losses over the high voltage alternative current (HVAC). It allows solar power to be integrated into the current power grid on a large scale. The author view in this article aims at providing an overview of methods used to integrate HVDC and solar systems. MATLAB/Simulink is used to simulate the solar power integration with HVDC transmission link. This article emphaises solar energy and grid integration, which results in quality and controlled electricity to the grid. Further the simulation studies are compared with real time data between the stations Pugalur AC grid (high solar energy region) and Thrissur AC grid (low solar energy region). Obtained results from the simulation, voltage and currents and power quality stresses the superiority towards the solar integration. The comparison studies enumerate the need to go situation for HVDC technology during the penetration of solar voltaic penetration into the utility network.
Blessy A Rahiman, J. Jayakumar and R. Meenal
Nowadays, in transportation systems, the clean energy aspect of solar photovoltaic (PV) energy is becoming more and more popular. However, the nonlinear environmental dependence of solar PV is its main drawback. Voltage management and effective Maximum Power Point Tracking (MPPT) techniques are essential to maximize the power produced from PV systems. This proposed work aims to integrate an Artificial Neural Network (ANN) based MPPT for PV-tied grid systems with a Boost converter. The fluctuating DC voltage from the PV panels is converted by the proposed Boost converter into a stable and appropriate voltage level for grid integration with high efficiency and low Total Harmonic Distortion (THD). Additionally, this work uses the ANN-based MPPT technique to track the PV system's optimal power, leading to better tracking accuracy and faster convergence. The single phase VSI converts the DC input to AC output for power supply to the grid system with the aid of a PI controller. The MATLAB/Simulink is used to implement the entire proposed system, and a comparison is made with the existing topologies (MPPT, P&O Based MPPT) to demonstrate the significance of the implemented work.
Sravankumar Jogunuri, Josh F.T, Albert Alexander Stonier, Geno Peter, Jayakumar Jayaraj, Jaganathan S, Jency Joseph J and Vivekananda Ganji
To maintain grid stability, the energy levels produced by sources within the network must be equal to the energy consumed by customers. In current times, achieving energy balance mainly involves regulating the electrical energy sources, as consumption is typically beyond the control of grid operators. For improving the stability of the grid, accurate forecasting of photovoltaic power output from largely integrated solar photovoltaic plant connected to grid is required. In the present study, to improve the forecasting accuracy of the forecasting models, onsite measurements of the weather parameters and the photovoltaic power output from the 20 kW on‐grid were collected for a typical year which covers all four seasons and evaluated the random forest techniques and other techniques like deep neural networks, artificial neural networks and support vector regression (reference in this study). The simulation results show that the proposed random forest technique for the forecasting horizon of 15 and 30 min is performing well with 49% and 50% improvements in the accuracy respectively over reference model for the study location 22.78°N, 73.65°E, College of Agricultural Engineering and Technology, Anand Agricultural University, Godhra, India.
Jayashree S. Awati and Mahesh Kumbhar
FOREX Publication
Fast Computer-Aided Diagnostic Systems (CAD) have become instrumental in diagnosing diseases. Brain tumors, in particular, pose a significant health challenge. Traditional tumor detection methods relied on radiologists and biopsy, which are time-consuming and detrimental to patients. Early detection is crucial for effective treatment. This system leverages image processing, SWARM intelligence, and Support Vector Machines (SVMs) to detect and classify brain tumors swiftly and accurately. Image processing encompasses preprocessing, segmentation, and feature extraction, with the Particle Swarm Optimization (PSO) method optimizing feature selection. SVMs identify tumor types. While various techniques exist for tumor detection, none achieve 100% accuracy. This system is engineered to provide precise detection.
J. Jayakumar, Arunraj Ebanesar, and Sneha Gautam
Springer Science and Business Media LLC
Anita Philips and J. Jayakumar
IEEE
Data analytics using machine learning technologies when applied to the energy consumption data can provide valuable inputs for maintaining the perfect supply demand balance in a smart electrical grid system. In particular, the accurate predictions of energy consumption for future periods of time aids significantly in cost-cutting and energy saving for utility companies. Making use of the popular method of time-series forecasting and the Artificial Neural Networks (ANN) models, here in this paper, one of the variants of the Recurrent Neural Networks (RNN) model, the Long Short Term Memory (LSTM) model is applied for household electricity consumption forecasting. Real datasets from consumption building are used for experimenting the model and applied through Tensorflow platform with the keras functions in Python. The results obtained show significantly accurate values in predicting future consumption derived from models training with actual values of current consumption. Hence, this work provides yet another proof that the LSTM machine learning forecasting methods can be efficiently applied for household electricity forecasting.
S. Vijai, J. Jayakumar, P. S. Hency Jose, K. Rajasekaran, and P. A. Christu Raj
Institution of Engineering and Technology
Senthil Kumar A, Selvaraj Kesavan, Jayakumar J, Ananda Kumar K S, and Prasad Maddula
IEEE
The use of technology to assist visually impaired individuals is crucial in addressing the global issue of vision impairment. Worldwide more than billion people suffer from a vision impairment that should have been avoided or is yet unaddressed. According to the statistics, there is a significant need for solutions that can help those who are visually impaired, mainly in the middle- and low-income countries where the vision impairment population is higher. It is anticipated that population expansion and ageing will increase the likelihood that more people may get vision impairment. The efficientnetB3 deep learning algorithm will be used in this project to caption images for blind people. so, they can learn about object identification, distance, and position. This has been accomplished by utilizing advanced picture captioning techniques, efficient net B3 algorithms, and tokenization approaches, where the computer learns the scenes with various captions. The computer recognizes and forecasts any image that is acquired using the camera. The significant objects are also anticipated, and the camera's distances are determined. Following the prediction, the user receives an audio output that can be used to determine the object's position and distance. Hence, with the aid of this research, we give the blind artificial eyesight that can give them confidence when they move on their own. The aim is to step forward in addressing the global issue of vision impairment. The use of technology to assist visually impaired individuals is crucial in providing them with the tools they need to navigate their environment and live their lives with greater ease. By utilizing advanced algorithms and image captioning techniques, the quality of life can be improved for people worldwide who are affected by vision impairment. The intension is to develop an artificial vision for vision impaired people by detecting real time objects, distance and the position of it from the person using Audio Output and to develop a model for image captioning to predict the captions.
P. H. Femy and J. Jayakumar
Walter de Gruyter GmbH
Abstract Energy consumption in the field of transportation comes next to industrial consumption worldwide. If transportation is completely powered by renewable energy, the utilization of fossil fuels can be drastically reduced, which will result in a lesser amount of greenhouse gas emissions. Electric vehicles (EVs) can act as an alternative to make transportation pollution-free. Large-scale usage of EVs causes high electricity demand on the supply system. This problem can be overcome by utilizing renewable energy sources (RESs) for Electric Vehicle charging. Due to the unpredictability of RESs, coordinating EV charging with other loads and renewable generation is problematic. By using EVs as energy units, power fluctuations in the electric grid can be compensated. This paper presents a summary of recent research in the domain of integration of electric vehicles (EVs) to the smart grid. Electric vehicles-smart grid integrated systems face several issues related to communication, grid infrastructure and control in the future power system. Smart grid technologies are summarized in Section 2. The existing research articles in this area are classified into two based on the purpose: EVs integration into the electric grid and Vehicle to grid services. Finally, the research gaps and future scope of incorporating electric vehicles with renewable energy sources and the Smart grid are highlighted.
Reshma Jose, Shanty Chacko, J. Jayakumar, and T. Jarin
World Scientific Pub Co Pte Ltd
Image processing plays a significant role in various fields like military, business, healthcare and science. Ultrasound (US), Magnetic Resonance Imaging (MRI) and Computed Tomography (CT) are the various image tests used in the treatment of the cancer. Detecting the liver tumor by these tests is a complex process. Hence, in this research work, a novel approach utilizing a deep learning model is used. That is Deep Belief Network (DBN) with Opposition-Based Learning (OBL)-Grey Wolf Optimization (GWO) is used for the classification of liver cancer. This process undergoes five major processes. Initially, in pre-processing the color contrast is improved by Contrast Limited Adaptive Histogram Equalization (CLAHE) and the noise is removed by Wiener Filtering (WF). The liver is segmented by adaptive thresholding following pre-processing. Following that, the kernelizedFuzzy C Means (FCM) method is used to segment the tumor area. The form, color, and texture features are then extracted during the feature extraction process. Finally, these traits are categorized using DBN, and OBL-GWO is employed to enhance system performance. The entire evaluation is done on Liver Tumor Segmentation (LiTS) benchmark dataset. Finally, the performance of the proposed DBN-OBL-GWO is compared to other models and their achievements are proved. The proposed DBN-OBL-GWO achieves a better accuracy of 0.995, precision of 0.948 and false positive rate (FPR) of 0.116, respectively.
Chitra S, Jayakumar J, Venkateshkumar P, Shanty Chacko, and Sivabalan
FOREX Publication
In many residential buildings the electrical wires of individual houses are laid in the same conduit pipe and some mistakes could be made in identifying similar coloured wires when they are laid in same conduit pipe. Most of the faults are caused by the neutral interconnection in the wiring system. Usually neutral wires are connected to neutral bus within the panel board or switchboard, and are "bonded" to earth ground. In our secondary distribution, tree system of supply is mostly utilized. The voltage of each phase to neutral will be maintained at rated value even during the unbalanced load conditions. If neutral wire connection is poor the voltage at each phase will be different from one another, such an isolated neutral point is called floating neutral and the voltage of the point is always changing. This is the reason for over voltage causing damage to appliance’s which should be protected. In this paper, a smart system that identifies power leakage and provides over voltage protection to the residential building is proposed.
Honey Baby, Jayaraj Jayakumar, Mobi Mathew, Mohamed G. Hussien, and Nallapaneni Manoj Kumar
Institution of Engineering and Technology (IET)
Dr. K. Sasikala, Dr. J. Jayakumar, Dr. A. Senthil Kumar, Dr. Shanty Chacko, and Dr. Hephzibah Jose Queen
FOREX Publication
The main aim of this paper is to highlight the benefits of Machine Learning in the power system applications. The regression-based machine learning model is used in this paper for predicting the power system analysis and Economic analysis results. In this paper, Predictive ML models for two modified IEEE 14-bus and IEEE-30 bus systems, integrated with renewable energy sources and reactive power compensative devices are proposed and developed with features that include an hour of the day, solar irradiation, wind velocity, dynamic grid price, and system load. An hour-wise input database for the model development is generated from monthly average data and hour-wise daily curves with normally distributed standard deviations. A very significant Validation technique (K Fold cross validation technique) is explained. Correlation between Input and output variable using spearman’s correlation analysis using Heat maps. Followed by the Multiple Linear Regression based Training and testing of the Modified IEEE 14 and IEEE30 Bus systems for base load case, 10% and 20% load increment with the 5-fold cross validation is also presented. Comparative analysis is performed to find the best fit ML Model for our research.
Khammampati R Sreejyothi, P. Venkatesh Kumar, and J. Jayakumar
IEEE
The importance of the Micro grid is increasing day to day because of reducing transmission cost, In comparison to the grid, microgrids have more renewable energy sources and it is easier to spot faults. If the main grid goes down, the microgrid can keep consumers comfortable by supplying power to homes and businesses for a while. The microgrid is best suitable in hilly areas and remote locations. Microgrid delivers important loads with a high-quality, consistent energy supply. This paper presents a Power quality improvement in Micro Grid used SRF theory. The microgrid is the interconnection of hybrid sources and load. The hybrid sources are PV cell, Fuel Cell, and Super Capacitor. By integrating these small sources, microgrids are implemented in generating the electrical power at load demand. The voltage and reactive power support to the external grid are examined using rDSTATCOM deployed at various locations throughout the microgrid. The simulation results were verified in MATLAB/SIMULINK software.
Hephzibah Jose Queen, J. Jayakumar, and T. J. Deepika
Springer Singapore
Hephzibah Jose Queen, Jayakumar J., and Deepika T. J.
Institute of Advanced Engineering and Science
<p>The primary aim of this work is to feature the advantages of integrating natural source of energy from the solar and wind to the prevailing electric power systems. Two types of analysis are carried out in two test systems (standard and modified test systems) and the outcome of the test systems are compared. The two analyses are technical analysis and economic analysis. The stability of the voltage is analyzed under technical analysis and the price of energy consumed from the electric grid is calculated and analyzed under the economic analysis. Dynamic hourly load data, hourly solar radiation, hourly wind velocity, and dynamic electricity prices are considered for the standard IEEE system and modified test system (with the integration of RES). Voltage stability index (L-Index) and price of the electricity consumed from electric grid are found for standard test system and the outcome is compared with the outcome of modified test systems. MATLAB coding is done for techno-economic analysis for both test systems. It is inferred from the outcome that the integration of renewable energy sources fairly contributes to the economic benefit of the system by lowering the power purchased from the grid and enhance the stability of the system.</p>
Khammampati R Sree Jyothi, P. Venkatesh Kumar, and J. JayaKumar
EDP Sciences
This paper presents a review of DSTATCOM Topologies and power quality control Techniques. The used topologies are Three-phase Three-wire and Three-phase four-wire and control techniques are Instantaneous reactive power theory(IRP), Synchronous Reference Frame Theory(SRF), Model Predictive Control (MPC), Sliding mode control(SMC), Adaptive Neuro-fuzzy interface systems(ANFIS) and Artificial intelligence based controllers. These control techniques are used to mitigate the reactive power compensation, load balancing, Neutral current compensation, harmonics reduction and maintains the Total harmonic Distortion in IEEE519 standards. Performance investigated in Single-phase Distribution systems by connecting with STATCOM and without DSTATCOM in MATLAB/SIMULINK
Manjinder Singh and Harpreet Kaur
FOREX Publication
Filling dead pixels or eliminating unwanted things is typically preferred within the applications of remotely sensed images. In proposed article, a competent image imprinting technique is demonstrated to resolve this drawback, relied nonlocal total variation. Initially remotely sensed images are effected by ill posed inverse problems i.e. image destripping, image de-noising etc. So it is required to use regularization technique to makes these problems well posed i.e. NLTV method, which is the combination of nonlocal operators and total variation model. Actually this method can make use of the good features of non-local operators for textured images and total variation method in edge preserving for color images. To optimize the proposed variation model, an Ant Colony Optimization algorithm is used in order to get similarity with the original image. And evaluate the outcomes of proposed technique with the existing technique i.e. MNLTV optimized by Bregmanized-operator-splitting algorithm which is a prediction based method. The investigation of all outcomes confirms the efficacy of this rule.
RECENT SCHOLAR PUBLICATIONS
MOST CITED SCHOLAR PUBLICATIONS
RESEARCH OUTPUTS (PATENTS, SOFTWARE, PUBLICATIONS, PRODUCTS)
Patent Number: 202041011809
Intelligent Integrated Control System for Electric Vehicle Battery