Technical papers from ArXiv - for readers interested in academic research
Summary
The SMART+ Framework is a structured model designed to address the challenges associated with AI systems in various industries, particularly focusing on safety, accountability, and regulatory compliance. The framework provides a comprehensive approach to evaluating and governing AI systems across industries, enabling responsible AI adoption and ensuring auditability. By integrating operational safeguards, oversight procedures, and strengthened privacy and governance controls, SMART+ demonstrates risk mitigation, trust-building, and compliance readiness.
Read Full Paper →
Key Takeaways
- The SMART+ Framework addresses the challenges of AI systems in various industries by incorporating multiple pillars such as Safety, Monitoring, Accountability, Reliability, and Transparency.
- The framework aligns with evolving mechanisms and regulatory guidance to integrate operational safeguards, oversight procedures, and strengthened privacy and governance controls.
- By providing a structured approach to evaluating and governing AI systems, SMART+ enables responsible AI adoption and ensures auditability, ultimately demonstrating risk mitigation, trust-building, and compliance readiness.
Summary
This article presents a novel approach to vulnerability assessment in modern power networks, which integrates N-2 contingency analysis with small-signal stability evaluation. The proposed Risk Index (Ri) framework uses probabilistic weighting to prioritize critical components based on reliability data and failure frequencies. By leveraging High-Performance Computing techniques, the authors demonstrate the feasibility of this approach for large-scale network assessments.
Read Full Paper →
Key Takeaways
- The article proposes a new methodology that integrates N-2 contingency analysis with small-signal stability evaluation to assess vulnerability in modern power networks.
- A probabilistic Risk Index (Ri) framework is introduced to prioritize critical components based on reliability data and failure frequencies, providing a more comprehensive approach than traditional deterministic screening methods.
- High-Performance Computing techniques are used to implement the proposed methodology, enabling the exhaustive exploration of massive contingency sets and processing large numbers of scenarios for validation.
Summary
This paper proposes a hierarchical operation control approach for microgrids with high renewable energy shares, aiming to ensure optimal operation under varying circumstances. The approach combines primary control layers with droop control and autonomous limitations, enabling the use of constant power setpoints under certain conditions. A case study demonstrates the viability of the proposed control design.
Read Full Paper →
Key Takeaways
- The paper presents a hierarchical power system control approach for microgrids with high renewable energy shares.
- The approach uses a primary control layer with droop control and autonomous limitations to enable optimal operation under certain conditions, specifically when using constant power setpoints.
- The solution is further enhanced by combining it with an energy management system that solves a robust unit commitment problem within a model predictive control framework.
Summary
The article discusses how AI-driven CAD systems are transforming the design of water and power transportation infrastructure, improving efficiency, effectiveness, and sustainability. These systems use automation, predictive modeling, and real-time data analytics to enhance design workflows, minimize human error, and optimize resource allocation. The integration of AI in CAD systems enables faster project delivery, enhanced design precision, and increased resilience.
Read Full Paper →
Key Takeaways
- AI-driven CAD systems improve the design of water and power transportation infrastructure by embedding automation, predictive modeling, and real-time data analytics.
- These systems can enhance design workflows, minimize human error, and optimize resource allocation for projects in underdeveloped environments.
- The integration of AI-powered CAD enables faster project delivery, enhanced design precision, and increased resilience to environmental and logistical constraints.