arXiv subjects

Hooman Torkaman

Publications and source records attributed to Hooman Torkaman.

2 recordsLinked to original sources

arXiv2026

Quantum Inspired QUBO Assisted ALNS for Reliability Driven Hurricane Restoration of Distribution Networks

Post hurricane distribution system restoration requires rapid repair scheduling subject to feeder topology, field logistics, and electrical feasibility. This paper presents a quantum inspired quadratic unconstrained binary optimization (QUBO) assisted adaptive large neighborhood search (ALNS) framework. At each restoration stage, a local CPU simulated annealing sampler ranks individual repairs and multi job combinations near the energized frontier. A deterministic decoder preserves crew truck logistics, enforces full useful crew utilization, and rejects infeasible batches. Final schedules are validated through OpenDSS replay. The framework is evaluated on the IEEE 123 node test feeder without distributed generation under 80, 90, and 100 m/s wind scenarios. In the 100 m/s stress test, the proposed method reduces mean system average interruption duration index and energy not supplied by 2.24% and restoration makespan by 50.71% relative to classical energized ALNS. Results show that QUBO assistance is most valuable when severe damage creates a larger combinatorial repair space.

eess.SY↗

arXiv2026

An Integrated Two-Stage Deep-Learning Tool for Rapid Post-Hurricane Damage Identification and Repair Scheduling

Post-hurricane damage assessment and repair scheduling can require computationally intensive simulation and optimization. This paper presents an integrated two-stage deep-learning tool for rapid damaged-line identification and repair-schedule computation. An available offline synthetic dataset for the IEEE 9500-node test feeder contains 1,700 hurricane scenarios with exposure features, grid metadata, fragility parameters, OpenDSS outputs, damaged-line labels, and Adaptive Large Neighborhood Search reference schedules. Stage 1 benchmarks MLP, ResMLP, and GraphSAGE, while Stage 2 compares MLP, DeepSets, and Set Transformer. The selected ResMLP-Set Transformer pipeline propagates Stage 1 errors into Stage 2 and achieves a damaged-job F1-score of 0.920, pairwise order agreement of 0.854, and start- and end-time mean absolute errors of 4.349 min and 4.486 min, respectively. The tool provides rapid initial repair-log decision support for new hurricane cases.

eess.SY↗