arXiv subjects

Karl M. H. Lai

Publications and source records attributed to Karl M. H. Lai.

4 recordsLinked to original sources

arXiv2026

Potentials and Limitations on Different Busbar Protections in Industrial Applications

Busbar protection is a cornerstone of industrial power system reliability, as failures at switchgear can propagate rapidly and extend restoration times. The Taiwan "303 blackout" in 2022, initiated by a short-circuit fault and aggravated by CT supervision lockout, illustrates the severe consequences of inadequate designs on busbar protection in centralized grids. Despite extensive academic and industrial guidance, practical challenges remain in busbar protection design, including CT placement, dynamic zone selection, CT saturation, and evolving fault scenarios. Standards and guides often fail to reflect operational limitations under diverse system conditions. This paper provides a structured evaluation of busbar protection (BBP) schemes in industrial applications. Leakage-to-frame, high-impedance differential (87Z), interlocking overcurrent (ILOC), electronic (EBBP), and numerical (NBBP) schemes are examined with respect to their operating principles, implementation requirements, and suitability for different bus configurations. Comparative analysis highlights clear trade-offs in different busbar protection schemes. The main contributions are: (i) systematic review of classical and modern busbar protection schemes, (ii) identification of operational limitations with various busbar protection, and (iii) comparison on the integration of CT supervision, check zones, and directional checks in NBBP to mitigate maloperations. The discussion reinforces the role of robust busbar protection design in preventing cascading outages and maintaining system reliability.

eess.SY↗

arXiv2026

Comparative Analysis on Inertia Estimation Algorithms (IEAs) in Providing Proper Frequency Response

The inertia constant H[s] is a fundamental indicator of power system resilience, linking power imbalance between generation and load to frequency deviation. It is essential in frequency reserve dispatch under stability-constrained optimal power flow (OPF), demand response (DR) in ancillary service, system decoupling and frequency control in modern power system. While the inertia constant is traditionally defined as the intrinsic kinetic energy of synchronous generators on bar normalized to the power base, this neglects the releasable power under nonlinear dynamics and control inside HVDC and Inverter-based Resources (IBRs). Accurate real-time inertia estimation is therefore essential to perform proper frequency control and to indicate the risks of failure in frequency restoration. It, however, is challenging with noisy frequency measurement under event-driven parameter jumps and locational transient responses. This paper presents a systematic comparative analysis on inertia estimation algorithms (IEAs) for frequency response applications. Classical methods such as filtering and fitting under measurement-based methods are benchmarked against data-based parameter estimation techniques such as recursive least squares (RLS) and model-based methods such as Kalman filtering (KF). The main contributions are: (i) a holistic review of model- and data-based inertia estimation methods, (ii) exploration on the effect of IEA to wind-based inertia emulation strategies. The findings underscore the need for robust, adaptive, and data-driven estimation frameworks to ensure secure operation of future low-inertia grids.

eess.SY↗

arXiv2026

RRAM-DP: Device-Calibrated Differential Privacy for In-Memory Edge Learning

Edge Artificial Intelligence of Things (AIoT) systems often collect sensitive data in situ, raising serious privacy concerns. Resistive-switching random-access memory (RRAM) is an attractive substrate for efficient AIoT thanks to its multi-bit storage and compute-in-memory (CiM) capabilities, while its inherently stochastic write behavior provides a natural source of randomness that can be leveraged for differential privacy (DP) protection. Yet how to transform this device-level randomness-typically viewed as detrimental to accuracy-into a principled randomized mechanism while preserving model utility remains underexplored. We propose RRAM-DP, a hardware-algorithm co-design that relaxes RRAM write-verify operations to inject calibrated noise for inherently (epsilon, delta)-DP with formal DP analysis; together with pretraining techniques, it renders a novel private, high-utility CiM training paradigm. On CIFAR-10/100, STS-B, and SST-2, RRAM-DP-SGD incurs at best only a 3.8% accuracy drop at (epsilon=2, delta=O(1/n))-DP relative to non-private SGD. At the same privacy level, RRAM-DP-SGD delivers up to 57x and 3.2x energy savings and 2.7x and 1.8x speedups over A100 and DiVa-GEMM, respectively. These results point toward efficient, privacy-preserving in-memory training on RRAM at the edge.

cs.CR↗

arXiv2024

SNNGX: Securing Spiking Neural Networks with Genetic XOR Encryption on RRAM-based Neuromorphic Accelerator

Biologically plausible Spiking Neural Networks (SNNs), characterized by spike sparsity, are growing tremendous attention over intellectual edge devices and critical bio-medical applications as compared to artificial neural networks (ANNs). However, there is a considerable risk from malicious attempts to extract white-box information (i.e., weights) from SNNs, as attackers could exploit well-trained SNNs for profit and white-box adversarial concerns. There is a dire need for intellectual property (IP) protective measures. In this paper, we present a novel secure software-hardware co-designed RRAM-based neuromorphic accelerator for protecting the IP of SNNs. Software-wise, we design a tailored genetic algorithm with classic XOR encryption to target the least number of weights that need encryption. From a hardware perspective, we develop a low-energy decryption module, meticulously designed to provide zero decryption latency. Extensive results from various datasets, including NMNIST, DVSGesture, EEGMMIDB, Braille Letter, and SHD, demonstrate that our proposed method effectively secures SNNs by encrypting a minimal fraction of stealthy weights, only 0.00005% to 0.016% weight bits. Additionally, it achieves a substantial reduction in energy consumption, ranging from x59 to x6780, and significantly lowers decryption latency, ranging from x175 to x4250. Moreover, our method requires as little as one sample per class in dataset for encryption and addresses hessian/gradient-based search insensitive problems. This strategy offers a highly efficient and flexible solution for securing SNNs in diverse applications.

cs.CR↗