Harnessing digitalization and internet of things for sustainable energy: A comprehensive study Gautam Solaimalai, S. Anitha Janet Mary, Vidya Kamma, Malini K. V., K. Karthikumar, et al. Navigating the Circular Age of A Sustainable Digital Revolution, 2024 This chapter explores the relationship between digitalization, IoT, and sustainable energy, highlighting their potential in transforming the energy landscape, driving efficiency, and enabling smarter energy management. It discusses the role of data analytics, AI, and machine learning in optimizing energy systems, enhancing predictive maintenance, and enabling demand-side management. The chapter also addresses cybersecurity risks and data privacy concerns in implementing digital solutions. It calls for collaboration among stakeholders to foster innovation and accelerate sustainable energy solutions adoption. It also calls for policy frameworks to incentivize investment in digital infrastructure and IoT-enabled devices. The chapter concludes by offering recommendations for policymakers, industry leaders, and researchers to utilize digital technologies for a sustainable and equitable energy future.
DFIG in Wind Energy Applications with High Order Sliding Mode Observer-based Fault-Tolerant Control Scheme using Sea Gull Optimization Sarika. S, Anitha Janet Mary. S International Journal of Electrical and Electronics Research, 2024 This paper describes a new method for maximizing power extraction from a wind energy conversion system (WECS) by using a doubly fed induction generator (DFIG) that operates below nominal wind speed. To maximize the collected power of a wind turbine (WTG) exposed to actuator failure, a fault-tolerant high-order sliding mode observer (HOSMO) and Seagull Optimization Algorithm with a model predictive controller (MPC) technique is proposed. Evaluate both the real state and the sensor error simultaneously using a higher-order sliding-mode observer. Active fault tolerant controllers are designed to regulate wind turbine rotor speed and power in the presence of actuator defects and uncertainty. With the growing interest in employing wind turbines (WTGs) as the primary generators of electrical energy, fault tolerance has been seen as essential to improving efficiency and reliability. This research focuses on optimal fault-tolerant pitch control, which is used to modify the pitch angle of wind turbine blades in the event of sensor, actuator, and system failures. A Seagull Optimization Algorithm (SOA) is proposed to tune controller parameters to improve the performance of WT. The proposed method has achieved 92% of power tracking performance when compared to existing method.
Energy Consumption Prediction for Home Appliances with Recurrent Neural Networks H. Mickle Aancy, S. Anitha Janet Mary, T. Manikumar, G. Saravanan, V. Mohanavel, et al. Proceedings 2024 International Conference on Expert Clouds and Applications Icoeca 2024, 2024 Efficient energy management requires a thorough understanding of individual appliance energy consumption in both residential and business environments. Because of the growing number of Internet of Things (loT) devices in smart homes, household appliances are a significant source of total energy consumption. Commonly used equipment such as heating systems, washing machines, and vacuum cleaners have a substantial impact on daily energy consumption. Significant energy savings can only be realized by careful management and forecasting of these appliances' energy consumption. This research employs Recurrent Neural Network (RNN) models for energy forecasting of housing appliances, with Long Short-Term Memory (LSTM) and a hybrid model known as Bi-LSTM-Attention Network. A Kaggle dataset with 28 features is used in this study, which is then reduced to 17 using a correlation plot. The processed data is used in both the training and testing phases of the RNN models. Many metrics are used to evaluate the performance of the models, including R-squared (R2), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE). The Bi- LSTM-Attention Network achieves excellent performance, with training and testing R2 values of 0.9978 and 0.9835, respectively. In addition, lower MSE and RMSE values demonstrate that Bi-LSTM-Attention Network constantly outperforms LSTM. The findings show that the proposed Bi-LSTM-Attention Network is capable of accurately predicting the amount of energy household appliances will consume.
A Comprehensive Review Of Load Demand Forecasting And Optimal Sizing In Stand Alone Hybrid Renewable Energy Systems Remya VR, S. Anitha Janet Mary 2023 Annual International Conference on Emerging Research Areas International Conference on Intelligent Systems Aicera Icis 2023, 2023 The rising global energy consumption necessitates a shift towards sustainable energy sources. While optimal sizing makes sure that the renewable energy system (RES) has enough capacity to satisfy the demand, accurate forecasting aids in recognizing the energy need. Forecasting load demand and selecting the right size are crucial for advancing sustainable energy practices. These methods aid in the integration of off-grid power systems with renewable energy sources like solar PV and wind turbines. This review of the literature seeks to present an overview of stand-alone hybrid RESs' ideal size and load demand forecasting. The assessment emphasizes how crucial load forecasting and ideal sizing are when constructing dependable and affordable off-grid power systems. The numerous elements that affect load demand, including as weather conditions, seasonal variations, and changes in consumer behaviour, are initially covered in the paper. The article then looks at the various load forecasting methodologies, including AI approaches. The best size for standalone hybrid RESs is the next topic of the review. A summary of the difficulties and restrictions associated with load demand forecasting approaches are also given in the literature study. The review emphasizes the significance of precise data collection, model construction, and model validation, as well as the necessity of including uncertainty and variability in the forecasting process. The study focusses on developing more accurate and robust forecasting models for load demand and optimizing the size of hybrid RES to enhance their efficiency and effectiveness in meeting energy demand while minimizing environmental impact.
Fault Diagnosis and Control Techniques for Wind Energy Conversion System: A Systematic Review Sarika. S, S. Anitha Janet Mary Proceedings of the 2022 3rd International Conference on Intelligent Computing Instrumentation and Control Technologies Computational Intelligence for Smart Systems Icicict 2022, 2022 In the recent years, wind is one of the quickest growing non-conventional resources, responsible for nearly 3 percentage of worldwide usage of electricity. As a consequence, the output & efficiency of particular types of power converters on wind turbine (WT) have been rising. Wind power converters were, nevertheless, susceptible to many types of component failure, because of the severe operational environment, as well as a multiple distinct operational conditions. According to data, the fault rate of Wind power converters (WPC) in wind energy conversion systems is substantially greater than that of hardware components and generators. The aim to minimize equipment failure and prevent hydraulic faults, fault detection (FD) for onsite grid-connected devices has received immense attention. As a result, the aim of this study is to provide the most recent technology evaluation of Fault diagnosis (FDs), that includes both pattern and model-based techniques. It aims to cover a wide range of topics, including converter operational FDs for varied converter, stress, device failure mechanisms, algorithm performance requirement, and design concerns. The main objective of this study is to demonstrate the state of converter FD research as well as useful reference for researcher in this field.
Comparative performance analysis of different controllers for a nonlinear multivariable system Anita Mary, L. Padma Suresh, S.H. Krishna Veni Proceedings of IEEE International Conference on Emerging Technological Trends in Computing Communications and Electrical Engineering Icett 2016, 2017 In the process industry, PID controllers are commonly used for control applications. PID controllers are simple and easy to construct. It provides more flexibility and stability while controlling the processes. The determination of proportional, integral and derivative constants KP, Ki and Kd are known as tuning of PID controller. Tuning of PID controller gains are easy if the system is a linear system. But many industrial plants are nonlinear systems. They have the problems such as higher order, instability, time delays, harmonics, poor damping and time-varying dynamics etc. Hence the perfect tuning of multi-loop multivariable PID controller for nonlinear process is a challenging work. This paper describes a comparative analysis of optimal tuning algorithms called simulated annealing algorithm and artificial bee colony algorithm used to tune the multivariable proportional integral derivative (PID) controller parameters for a non linear system. Better performance of SA-PID and ABC-PID controller are studied and compared.
Optimization of PID controller for a nonlinear MIMO system and comparative performance analysis International Journal of Mechanical Engineering and Technology, 2017
An optimization tuning method for multivariable PID controller using artificial bee colony algorithm for nonlinear system International Journal of Applied Engineering Research, 2015
