Microgrids driven by distributed energy resources are gaining prominence as decentralized power systems offering advantages in energy sustainability and resilience. However, optimizing microgrid operation faces challenges from the intermittent nature of renewable sources, dynamic energy demand, and varying grid electricity prices. This paper presents an AI-driven day-ahead optimal scheduling approach for a grid-connected AC microgrid with a solar panel and a battery energy storage system. Genetic Algorithm generates demand response strategies and optimizes battery dispatch, while LightGBM forecasts solar power generation and building load consumption. The approach aims to minimize operational costs and ensure microgrid sustainability, using a battery degradation cost function to extend its lifespan. Simulation results in that are conducted in the University of Moratuwa microgrid show a significant 14.22% decrease in electricity costs under Sri Lanka’s current tariff structure, attributed to intelligent energy dispatch scheduling. Proactive demand response management has the potential to minimize costs further. This research contributes to microgrid optimization knowledge, promoting the adoption of intelligent and sustainable energy systems.

Manufacturing of composites using Automated Fibre Placement(AFP) is a complicated process which involves large number of processing conditions and variables. Improper selection of these parameters adversely affect the quality and integrity of the manufactured laminates. Thus,it is important to develop a predictive model which can assess how changes in critical process conditions alter the outputs of the manufacturing process.The goal of this investigation is to learn the complex behaviour of composites by developing an intelligent model which can subsequently be used for the prediction of various characteristics of the composites. However,manufacturing of AFP composites is both expensive and time-consuming and therefore the available data samples are less,from the prospective of machine learning,which leads to the small data learning problem. This study first solves this problem through Virtual Sample Generation(VSG), then a Neural Network based predictive model is developed to accurately learn the complex relationships between various processing parameters in AFP.

This paper describes a groundbreaking design of a three-phase interleaved boost converter for PV systems, leveraging parallel-connected conventional boost converters to reduce input current and output voltage ripple while improving the dynamic performance. A distinctive feature of this study is the direct connection of a Li-Ion battery to the DC link, which eliminates the need for an additional charging circuit, which is a departure from conventional approaches. Furthermore, the combination of an MPPT controller and a closed-loop fuzzy controller with a current control mode ensures accurate switching signal generation for all three phases. The meticulously tuned system exhibits a remarkably low ripple content in the output voltage, surpassing calculated values, and demonstrates a superior dynamic performance. The investigation extends to a comprehensive analysis of losses, encompassing inductor copper loss and semiconductor conduction loss. In all scenarios, the converter exhibits an efficiency exceeding 93%, highlighting its robust performance as an effective solution for PV systems.

The rise of renewable energy integration in smart grids brings new cybersecurity challenges, prompting this study to examine vulnerabilities in Smart Cyber-Physical Power Systems (CPPS). The integration of renewable energy sources, such as wind and solar, into smart grids poses operational risks due to their decentralized and variable characteristics, particularly within the communication layers essential for real-time monitoring and control. While increasing integration of renewable energy sources does not directly impact cybersecurity vulnerabilities, the primary challenge arises from their decentralization. Addressing this decentralization requires the use of cyber layers between supply and demand, introducing vulnerabilities of cyber threats to the control and communication systems of the power system. These layers, vulnerable to diverse cyber-attacks like false data injection (FDI), denial of service (DoS), and replay assaults, might compromise grid stability and security. To address these risks, the research proposes a hybrid approach that integrates conventional cybersecurity strategies with machine learning (ML) approaches to improve cyber-attack detection. The research highlights the use of deep learning models, including Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks, for real-time anomaly identification in grid data. These models, developed using a PSCAD-simulated dataset augmented with synthetic cyber-attacks, exhibit considerable advancements in threat identification and mitigation. The study emphasizes the difficulties in identifying cyber risks in grids with significant renewable integration, such as frequency instability and diminished system inertia, and suggests energy storage alternatives and sophisticated forecasting models to mitigate these issues. By incorporating a novel pre-processing method that leverages feature derivatives, the proposed models achieve over 98% accuracy in detecting cyber threats, providing a robust framework for protecting smart power grids from evolving cyber risks.

Non-Intrusive Load Monitoring (NILM) is a method to determine the power consumption of individual appliances from the overall power consumption measured by a single measurement device, which is usually the main meter. Increase in the adoption of smart meters has facilitated large scale implementation of NILM, which can provide information about individual loads to the utilities and consumers. This will lead to significant energy savings as well as better demand-side management. Researchers have proposed several methods and have successfully implemented NILM for residential sectors that have a single-phase supply. However, NILM has not been successfully implemented for industrial and commercial buildings that have a three-phase supply, due to several challenges. These buildings consume significant amount of power and implementing NILM to these buildings has the potential to yield substantial benefits. In this paper, we propose a novel deep learning-based approach to address some of the key challenges in implementing NILM for buildings that have a three-phase supply. Our approach introduces an ensemble learning technique that does not require training of multiple neural network models, which reduces the computational requirements and makes it economically feasible. The model was tested on a three-phase system that consists of both three- phase loads and single-phase loads. The results show significant improvement in load disaggregation compared to the existing methods and indicate its applicability.

In recent years, a new paradigm in control engineering, called networked control system (NCS), has emerged due to the success of Internet and associated communication infrastructure. The NCS offers various advantages compared to the traditional control systems, which include increase of agility, wiring reduction, and easy maintenance and diagnosis. With an objective to investigate the effectiveness of various controllers in networked environment, the present study designs a $\Delta \Sigma$ -based single-bit PID controller for the rotor-side converter of a doubly fed induction generator (DFIG)-based wind energy conversion system. This consists of 20-DFIGs of 5 MW capacity each. A comparative performance investigation has been carried out with three other controllers; a conventional PID, Q-learning and dynamic fuzzy Q-Learning controller. The study considers various imperfections of a Zigbee protocol-based practical communication network, such as random delay and packet dropout. The results of both the simulation and experiment demonstrate that the $\Delta \Sigma$ -based single-bit PID controller shows better performance compared to other controllers.