Dhruv Suri

Dhruv Suri, Helgi Hilmarsson, Shourya Bose

Solving AC Optimal Power Flow (AC-OPF) is of central importance in electricity market operations, where interior-point methods (IPMs) such as IPOPT are the standard solvers. A growing body of work uses machine learning to predict primal warm-start iterates, reporting iteration reductions of 30-46\%. We show that these reported gains rest on an inappropriate evaluation baseline: prior methods benchmark against the flat start $V_m = 1, V_a = 0$, whereas the solver's actual default - the variable-bound midpoint $(l+u)/2$ - is near-optimal for log-barrier centrality. Against this corrected baseline, no primal-only warm-start method reduces solver iterations. We trace the failure to a geometric property of interior-point methods: primal prediction accuracy is anticorrelated with convergence speed, and providing the ground-truth optimal solution $x^*$ without dual variables causes the solver to diverge. Oracle experiments establish that the complete primal-dual-barrier state $(x^*, λ^*, z^*, μ^*)$ reduces IPOPT iterations from 23 to 3 - an 85\% reduction that is structurally inaccessible to primal-only methods. To enable rigorous evaluation of warm-start methods on this task, we release a benchmark suite comprising dual-labeled AC-OPF datasets with IPOPT-extracted solutions, a corrected evaluation protocol, and WARP - a topology-conditioned encode-process-decode interaction network that predicts the full interior-point state $(\hat{x}, \hatλ, \hat{z}, \hatμ)$ on the heterogeneous constraint graph. WARP achieves a 76\% reduction in IPOPT iterations while natively accommodating N-1 contingency topology variations without retraining.

Shourya Bose, Helgi Hilmarsson, Dhruv Suri

Neural warm starts can sharply reduce the number of Newton-Raphson iterations required to solve the AC power flow problem, but existing supervised approaches generalize poorly on heavily loaded instances near voltage collapse. We prove a lower bound on the Newton-Raphson iteration count that depends on the direction of the warm start error rather than on its magnitude, and show as a corollary that the bound becomes vacuous as the smallest singular value of the power-flow Jacobian shrinks, identifying the failure mode of supervised regression near the saddle-node bifurcation. Motivated by this analysis, we introduce Newton's Lantern, a finetuning pipeline that combines group relative policy optimization with a learned reward model trained on perturbations of the base model's predictions, using the iteration count itself as the supervisory signal. Across IEEE 118-bus, GOC 500-bus, and GOC 2000-bus benchmarks, Newton's Lantern is the only method that converges on every test snapshot while attaining the smallest mean iteration count.

Dhruv Suri, Praneet Dutta, Flora Xue et al.

As Chile's electric power sector advances toward a future powered by renewable energy, accurate forecasting of renewable generation is essential for managing grid operations. The integration of renewable energy sources is particularly challenging due to the operational difficulties of managing their power generation, which is highly variable compared to fossil fuel sources, delaying the availability of clean energy. To mitigate this, we quantify the impact of increasing intermittent generation from wind and solar on thermal power plants in Chile and introduce a hybrid wind speed forecasting methodology which combines two custom ML models for Chile. The first model is based on TiDE, an MLP-based ML model for short-term forecasts, and the second is based on a graph neural network, GraphCast, for medium-term forecasts up to 10 days. Our hybrid approach outperforms the most accurate operational deterministic systems by 4-21% for short-term forecasts and 5-23% for medium-term forecasts and can directly lower the impact of wind generation on thermal ramping, curtailment, and system-level emissions in Chile.

Dhruv Suri, Anela Arifi, Ines Azevedo

Nowcasting day-ahead marginal emissions factors is increasingly important for power systems with high flexibility and penetration of distributed energy resources. With a significant share of firm generation from natural gas and coal power plants, forecasting day-ahead emissions in the current energy system has been widely studied. In contrast, as we shift to an energy system characterized by flexible power markets, dispatchable sources, and competing low-cost generation such as large-scale battery or hydrogen storage, system operators will be able to choose from a mix of different generation as well as emission pathways. To fully develop the emissions implications of a given dispatch schedule, we need a near real-time workflow with two layers. The first layer is a market model that continuously solves a security-constrained economic dispatch model. The second layer determines the marginal emissions based on the output of the market model, which is the subject of this paper. We propose using multi-headed convolutional neural networks to generate day-ahead forecasts of marginal and average emissions for a given independent system operator.

Dhruv Suri, Mohak Mangal

The increasing penetration of renewable energy sources introduces significant variability and uncertainty in modern power systems, making accurate state prediction critical for reliable grid operation. Conventional forecasting methods often neglect the power grid's inherent topology, limiting their ability to capture complex spatio temporal dependencies. This paper proposes a topology aware Graph Neural Network (GNN) framework for predicting power system states under high renewable integration. We construct a graph based representation of the power network, modeling buses and transmission lines as nodes and edges, and introduce a specialized GNN architecture that integrates GraphSAGE convolutions with Gated Recurrent Units (GRUs) to model both spatial and temporal correlations in system dynamics. The model is trained and evaluated on the NREL 118 test system using realistic, time synchronous renewable generation profiles. Our results show that the proposed GNN outperforms baseline approaches including fully connected neural networks, linear regression, and rolling mean models, achieving substantial improvements in predictive accuracy. The GNN achieves average RMSEs of 0.13 to 0.17 across all predicted variables and demonstrates consistent performance across spatial locations and operational conditions. These results highlight the potential of topology aware learning for scalable and robust power system forecasting in future grids with high renewable penetration.

Aman Gupta, Aditi Sheshadri, Dhruv Suri

Accurate weather forecasts are critical for societal planning and disaster preparedness. Yet these forecasts remain challenging to produce and evaluate, especially in regions with sparse observational coverage. Current evaluation of artificial intelligence (AI) weather prediction relies primarily on reanalyses, which can obscure important deficiencies. Here we present MAUSAM (Measuring AI Uncertainty during South Asian Monsoon), an evaluation of seven leading AI-based forecasting systems - FourCastNet, FourCastNet-SFNO, Pangu-Weather, GraphCast, Aurora, AIFS, and GenCast - during the South Asian Monsoon, using ground-based weather stations, rain gauge networks, and geostationary satellite imagery. The AI models demonstrate impressive forecast skill during monsoon across a broad range of variables, ranging from large-scale surface temperature and winds to precipitation, cloud cover, and subseasonal to seasonal eddy statistics, highlighting the strength of data-driven weather prediction. However, the models still exhibit systematic errors at finer scales like the underprediction of extreme precipitation, divergent cyclone tracks, and the mesoscale kinetic energy spectra, highlighting avenues for future improvement. A comparison against observations reveals forecast errors up to 15-45% larger than those relative to reanalysis and traditional forecasts, indicating that reanalysis-centric benchmarks can overstate forecast skill. Of the models assessed, AIFS achieves the most consistent representation of atmospheric variables, with GraphCast and GenCast also showing strong skill. The analysis presents a framework for evaluating AI weather models on regional prediction and highlights both the promise and current limitations of AI weather prediction in data-sparse regions, underscoring the importance of observational evaluation for future operational adoption.