Full Research Paper – Page 5 – NPS Australia Submission System

Machine Learning-based Active Power Loss Forecasting in Distribution Systems

This paper introduces an optimal model that utilizes machine learning algorithms to predict the
active power losses during the allocation and sizing of distributed generation (DG) units in power distribution networks. The model incorporates the technique of Gradient Boosting Machine Regression (GBMR). This study estimates DG location, bus voltages, DG size, and active
losses without conventional power flow calculations.
The results demonstrate that the suggested estimations of power losses and DG sizing method are effective, practical, and adaptable. The accuracy of the proposed estimation methods has been validated using R-squared and mean absolute percentage error (MAPE) metrics. In the case of fixed load, the GBMR outperforms with a very low (MAPE) (0.9281%), a root mean square error (RMSE) of 1.748, and 0.999 accuracy in predicting
active power losses. When the normalized load variation (NLV), the R-squared 0.9991 value with low MAPE (1.9815%). This approach enables grid operators to effectively manage DG unit integration by providing precise estimates and forecasts of power loss. The effectiveness of the proposed strategy is validated in the IEEE 33 bus test system using MATLAB software.

A Novel Approach to Verification of Neural Cyber-physical Systems

The verification of Cyber-physical System (CPS),
particularly those incorporating neural networks for safety-critical
functions remains an ongoing challenge due to the lack
of advanced verification and validation frameworks. Current
methods are often limited in their scalability and ability to
comprehensively verify system-level and component-level properties,
leading to potential vulnerabilities in these systems. This
issue becomes even more pronounced when dealing with hybrid
systems that integrate physical processes and neural network-based
controllers [2]. We propose a novel verification framework
tailored for complete CPS verification using a decomposition-based
approach to address this challenge. Our method performs
sequential-distributed verification, ensuring each component
adheres to compositional Metric Interval Temporal Logic
(MITL). By applying this framework to a model (CPS), we use
backward induction to verify that component-level and system-level
properties remain within predefined operational ranges,
derived from simulation data. Implemented in MATLAB,
this approach enhances the verification process by identifying
potential failure points across subsystems, providing a scalable
solution for verifying complex hybrid systems. This method
significantly improves verification accuracy and enables precise
identification of faulty components, making it a highly effective
tool for robust system design and analysis.

A Novel Approach to Verification of Neural Cyber-physical Systems

The verification of Cyber-physical System (CPS),
particularly those incorporating neural networks for safety-critical
functions remains an ongoing challenge due to the lack
of advanced verification and validation frameworks. Current
methods are often limited in their scalability and ability to
comprehensively verify system-level and component-level properties,
leading to potential vulnerabilities in these systems. This
issue becomes even more pronounced when dealing with hybrid
systems that integrate physical processes and neural network-based
controllers. We propose a novel verification framework
tailored for complete CPS verification using a decomposition based
approach to address this challenge. Our method performs
sequential-distributed verification, ensuring each component
adheres to compositional Metric Interval Temporal Logic
(MITL). By applying this framework to a model (CPS), we use
backward induction to verify that component-level and system-level
properties remain within predefined operational ranges,
derived from simulation data. Implemented in MATLAB,
this approach enhances the verification process by identifying
potential failure points across subsystems, providing a scalable
solution for verifying complex hybrid systems. This method
significantly improves verification accuracy and enables precise
identification of faulty components, making it a highly effective
tool for robust system design and analysis.

A Novel Approach to Verification of Neural Cyber-physical Systems

The verification of Cyber-physical System (CPS),
particularly those incorporating neural networks for safety-critical
functions remains an ongoing challenge due to the lack
of advanced verification and validation frameworks. Current
methods are often limited in their scalability and ability to
comprehensively verify system-level and component-level properties,
leading to potential vulnerabilities in these systems. This
issue becomes even more pronounced when dealing with hybrid
systems that integrate physical processes and neural network-based
controllers. We propose a novel verification framework
tailored for complete CPS verification using a decomposition-based
approach to address this challenge. Our method performs
sequential-distributed verification, ensuring each component
adheres to compositional Metric Interval Temporal Logic
(MITL). By applying this framework to a model (CPS), we use
backward induction to verify that component-level and system-level
properties remain within predefined operational ranges,
derived from simulation data. Implemented in MATLAB,
this approach enhances the verification process by identifying
potential failure points across subsystems, providing a scalable
solution for verifying complex hybrid systems. This method
significantly improves verification accuracy and enables precise
identification of faulty components, making it a highly effective
tool for robust system design and analysis.

A Reconfigurable and Efficient Architecture for Modular Polynomial Multiplier in Post-Quantum Cryptography

Quantum-resistant cryptographic algorithms have been proposed to prevent the security attacks from future Quantum Computers. The modular polynomial multiplication is the frequent and time-consuming arithmetic operation in Lattice Based Quantum-resistant Cryptography. In this paper, an efficient and reconfigurable architecture for modular polynomial multiplier is proposed in Lattice Based Post-Quantum Cryptography which can be implemented serially or parallelly depending on the application environments. The proposed modular polynomial multiplier is easily embedded in a crypto-processor to provide security services in the time of Quantum Computing.

An Interactive Learning Platform

This work helps learners engage in remote learning at their own pace whilst giving them the opportunity to also engage in in-depth assistance through the deployment of AI tools.

An Interactive Learning Platform

This work helps learners engage in remote learning at their own pace whilst giving them the opportunity to also engage in in-depth assistance through the deployment of AI tools.

An Interactive Learning Platform

This work helps learners engage in remote learning at their own pace whilst giving them the opportunity to also engage in in-depth assistance through the deployment of AI tools.

The Adoption of Internet of Things in Higher Education: Opportunities, Challenges, the Role of vision 2030 in Saudi Arabia

The research highlights the growing yet uneven adoption of IoT in Saudi universities, identifying key benefits like improved pedagogy and decision-making, while also addressing challenges such as infrastructure, financial, and cultural barriers. It provides strategic recommendations to enhance IoT integration in line with Vision 2030.

Quantifying the Effectiveness of Cloud and Edge Servers on Energy-Saving of Mobile Real-time Systems

Our findings provide insights into designing optimized task offloading configurations tailored to specific mobile system characteristics, balancing the benefits of cloud and edge environments.

Paper Type: Full Research Paper