Rapid electrification and decarbonization are increasing the complexity of distribution grid (DG) operation and planning, necessitating advanced computational analyses to ensure reliability and resilience. These analyses depend on disparate workflows comprising complex models, function calls, and data pipelines that require substantial expert knowledge and remain difficult to automate. Workforce and budget constraints further limit utilities' ability to apply such analyses at scale. To address this gap, we built an agentic system, PowerChain, which is capable of autonomously performing complex grid analyses. Existing agentic AI systems are typically developed in a bottom-up manner with a customized context for predefined analysis tasks; therefore, they do not generalize to tasks that the agent has never seen. In comparison, to generalize to unseen DG analysis tasks, PowerChain dynamically generates structured context by leveraging supervisory signals from self-contained power systems tools (e.g., GridLAB-D) and an optimized set of expert-annotated and verified reasoning trajectories. For complex DG tasks defined in natural language, empirical results on real utility data demonstrate that PowerChain achieves up to a similar to 144% improvement in performance over baselines.
This paper presents a novel structure-preserving, Kron-based reduction framework for unbalanced distribution feeders. The method aggregates electrically similar nodes within a mixed-integer optimization (MIP) problem to engender reduced networks that optimally reproduce the voltage profiles of the original full network. To overcome computational bottlenecks of MIP formulations, we motivate an exhaustive-search formulation to identify optimal aggregation decisions, while enforcing voltage margin limits. The proposed exhaustive network reduction algorithm is parallelizable on GPUs, which enables scalable network reduction. The resulting reduced networks approximate the full system’s voltage profiles with low errors, and are suitable for steady-state analysis and optimal power flow studies. The framework is validated on two real utility distribution feeders with 5, 991 and 8, 381 nodes. The reduced models achieve up to 90% and 80% network reduction, respectively, while the maximum voltage-magnitude error remains below 0.003 p.u. Furthermore, on a 1000-node version of the network, the GPU-accelerated reduction algorithm runs up to 15x faster than its CPU-based counterpart.
Solving for globally optimal line switching decisions in AC transmission grids can be intractably slow. Machine learning (ML) models, meanwhile, can be trained to predict near-optimal decisions at a fraction of the speed. Verifying the performance and impact of these ML models on network operation, however, is a critically important step prior to their actual deployment. In this paper, we train a Neural Network (NN) to solve the optimal power shutoff line switching problem. To assess the worst-case load shedding induced by this model, we propose a bilevel attacker-defender verification approach that finds the NN line switching decisions that cause the highest quantity of network load shedding. Solving this problem to global optimality is challenging (due to AC power flow and NN nonconvexities), so our approach exploits a convex relaxation of the AC physics, combined with a local NN search, to find a guaranteed lower bound on worst-case load shedding. These under-approximation bounds are solved via MathOptAI.jl. We benchmark against a random sampling approach, and we find that our optimization-based approach always finds larger load shedding, by an average margin of 33% in the largest test case. Test results are collected on multiple PGLib test cases and on trained NN models which contain more than 10 million model parameters.
The high penetration of distributed energy resources, resulting in backfeed of power at the transmission and distribution interface, is causing conventional underfrequency load shedding (UFLS) schemes to become nonconforming. Adaptive schemes that update UFLS relay settings recursively in time offer a solution, but existing adaptive techniques that obtain UFLS relay settings with linearized or reduced-order model formulations fail to capture AC nonlinear network behavior. In practice, this will result in relays unable to restore system frequency during adverse disturbances. We formulate an adaptive UFLS problem as a trajectory optimization and include the full AC nonlinear network dynamics to ensure AC feasibility and time-coordinated control actions. We include binary decisions to model relay switching action and time-delayed multi-stage load-shedding. However, this formulation results in an intractable MINLP problem. To enforce model tractability, we relax these binary variables into continuous surrogates and reformulate the MINLP as a sequence of NLPs. We solve the NLPs with a homotopy-driven method that enforces near-integer-feasible solutions. We evaluate the framework on multiple synthetic transmission systems and demonstrate that it scales efficiently to networks exceeding 1500+ nodes with over 170k+ continuous and 73k+ binary decision variables, while successfully recovering binary-feasible solutions that arrest the frequency decline during worst-case disturbance.
Stroke remains a rare but life-threatening complication of pregnancy, with significant implications for both maternal and fetal health. Current stroke prevention and treatment guidelines offer limited guidance for managing stroke in pregnant and postpartum patients. Despite advances in obstetric and neurological care, the diagnosis and management of pregnancy-associated stroke continue to be challenged by delayed recognition, a lack of tailored clinical guidelines, and persistent disparities in outcomes. This scientific statement represents a multidisciplinary effort to synthesize current knowledge of the risk factors and diverse causes of stroke in pregnancy and to offer consensus-driven suggestions for prevention, acute management, and postpartum recovery. Nearly half of all US pregnancy-associated stroke hospitalizations occur in the setting of hypertensive disorders. Primary stroke prevention strategies include risk factor modification, aggressive hypertension management and prompt treatment of severe hypertension in pregnancy and postpartum, and antithrombotic therapy in some high-risk groups. Secondary stroke prevention strategies in pregnancy depend on the mechanism of the prior stroke. Pregnancy should not delay evidence-based treatments for acute stroke. The use of telemedicine can facilitate early consultation with a vascular neurologist and a maternal-fetal medicine specialist in cases of acute pregnancy-related stroke, helping to guide initial decision-making. Computed tomography, computed tomography angiography, and magnetic resonance imaging without contrast are all safe neuroimaging modalities for rapid evaluation of pregnant patients with acute stroke symptoms. Acute stroke alone is not an indication for immediate delivery, and stabilization of the mother should come first. Vaginal delivery after stroke is preferred when feasible because it avoids the surgical risks and hemodynamic stress associated with cesarean delivery. Survivors of pregnancy-associated stroke face unique challenges such as caring for an infant and breastfeeding and require support from a multidisciplinary rehabilitation team. Continued research, including inclusive clinical trials, is urgently needed to refine stroke risk assessment, to expand treatment options, and to improve maternal outcomes.
