arXiv subjects

Eliseo Curcio

Publications and source records attributed to Eliseo Curcio.

8 recordsLinked to original sources

arXiv2026

Beyond the Grid: Cost, Carbon, and Capital Requirements of On-Site Power Technologies for AI Data Centers

Interconnection queues, not electricity prices, now govern where data centers can be built, and the standard levelized-cost comparison answers a question no developer faces: it assumes a load profile, freezes the grid price while modeling the demand that moves it, and quotes busbar costs a facility cannot buy. This paper evaluates nine on-site supply technologies against a delivered grid whose price is endogenous to projected data-center demand, on a complete-site basis that retains standby charges, with measured GPU training load, delivered fuel prices, production-pathway carbon, and statutory 45V and 48E incentive mechanics. Nothing beats the wire: gas combined cycle produces at 47 USD/MWh but costs about 114 USD per megawatt-hour of complete site energy against a 92 USD grid; four-hour storage is physically capped near 18 percent of annual energy and, charged at the margin, dirtier than the grid; hydrogen from grid-priced power fails on cost and carbon together. An investment inversion converts these findings into capital terms: conversion-hardware learning buys nothing, because free hardware still exceeds the grid for every low-carbon arm, while global electrolyser deployment on sited sub-20 USD/MWh power brings PEM hydrogen power to about 2.2 times the grid at 300 billion USD and 1.9 times at 1 trillion USD (2.7 and 2.3 for the hydrogen engine), with a carbon reduction of roughly 85 percent (6.8-fold) against grid-power production. Grid parity is not purchasable at any budget. On-site supply is an access and depth product; most current investment targets the wrong term.

econ.EM↗

arXiv2026

Cutting AI Datacenter Energy with Reinforcement Learning: Measured Power Control of LLM Training from One GPU to the Fleet

Reinforcement-learning post-training dominates modern language-model development, yet its power behavior on GPU hardware has not been characterized, and datacenters manage GPU power with workload-blind mechanisms, static caps and reactive throttling, that slow hardware indiscriminately. We instrument GRPO training with half-second power telemetry at 7B, 14B, and 72B scales on one to four A100s (380,000+ samples), and train a PPO meta-controller that adapts the workload's own generation parameters to measured power. Against the full 500-step 7B trace, the controller cuts power-limit violations by 89.8% while increasing token output by 18.1% and energy efficiency by 26.2% (tokens per MWh). Deployed live at 72B, the same controller family yields replicated null results, diagnosed as the group-size actuator losing authority under model sharding. An actuator-authority sweep shows the same parameters applied as generation concurrency retain 17-22% power authority, isolating an occupancy-versus-volume principle; a controller rebuilt on that actuator controls a live 72B rollout-generation workload across three replications: 35.7% more output than a static safe baseline at 2.27 +/- 1.08% budget violations, 87.2% fewer violations than uncontrolled operation, and the best mean throughput and energy per token among constrained controllers, with an adaptive threshold rule matching it in one of three operating conditions. Under realistic measurement windows the original 72B transients fall from 23.6% at half-second resolution to 1.6% at 30 s and zero at 5 min; a composed 16-GPU fleet shows zero violations at 30 s and longer, with peak demand at 50-56% of nameplate. For this fleet mix, roughly twofold oversubscription of nameplate appears feasible, subject to operator validation. We quantify the economic and carbon consequences and specify a low-cost operator pilot.

cs.AI↗

arXiv2026

Retrieval over Reasoning: A Cost-Controlled Benchmark of Language Models for Energy-Retrofit Recommendation

Recommending the correct set of energy conservation measures (ECMs) for a building is a structured, multi-label prediction problem in which a task-specific supervised model has weak training signal and a general language model has no grounding in the local building stock. We study this problem on 10,422 real New York City Local Law 87 (LL87) energy-audit records, taking as ground truth the set of ECM categories that certified auditors actually recommended. We make four contributions. First, we establish that energy-use-intensity (EUI) prediction - the upstream task - is effectively solved by tree ensembles: across fifteen trained models, a stacking ensemble reaches a coefficient of determination R^2 = 0.757, and every one of six neural architectures is outperformed by gradient-boosted trees. Second, we show that the framing of the recommendation task dominates model choice: recasting ECM recommendation as 19-way multi-label classification rather than single-label categorization lifts a gradient-boosted-tree baseline from a previously reported 25.9% accuracy to a micro-F1 of 0.571. Third, we benchmark eight large language models (LLMs) from four providers in a 2x2 design that independently toggles retrieval grounding and explicit reasoning, scoring each arm on per-label F1, U.S.-dollar cost per building, and latency; retrieval-augmented generation (RAG) improves micro-F1 by +0.11 to +0.20 on every model, while explicit reasoning yields no measurable accuracy change (-0.018 to +0.010) at up to 8.4x the cost. Fourth, we show LLMs systematically over-recommend - high recall, low precision - and that retrieval closes the gap chiefly by improving precision. A 70-billion-parameter open-weight model with a fifteen-line nearest-neighbor retrieval step reaches 0.511 micro-F1 at $0.00032 per building, comparable to a frontier model at roughly 10.1x lower cost.

econ.EM↗

arXiv2026

EnergyAgentBench: Benchmarking LLM Agents on Live Energy Infrastructure Data

Selecting the right electricity market region for a hyperscale AI datacenter requires reasoning across live electricity prices, grid carbon intensity, technology cost trajectories, and causal grid dynamics -- a multi-step, multi-source analytical task that static knowledge benchmarks cannot evaluate. We introduce EnergyAgentBench, the first agentic benchmark grounded in live electricity market data for this problem class. The benchmark comprises 70 task variants across five families: datacenter siting under cost-carbon trade-offs (F1), long-horizon portfolio siting (F1-LH), lifetime LCOE ranking over multi-decade cost trajectories (F2), 30-year portfolio optimization (F2-LH), and causal grid diagnosis (F3). Tasks require 3 to 48 sequential tool calls against live endpoints from the QuarluxAI infrastructure platform, the U.S. Energy Information Administration (EIA), and the National Renewable Energy Laboratory (NREL) with ground truth derived from trained XGBoost cost-surface models (R^2 0.967--0.995) and the NREL Annual Technology Baseline 2024. We evaluate nine models across Anthropic, OpenAI, and HuggingFace over 1,414 runs at three random seeds. Claude Sonnet 4.6 achieves the highest overall score (0.900) at one-quarter the cost of Claude Opus 4.7 (0.889). Claude Haiku 4.5 leads on long-horizon procedural siting (0.986), outperforming all frontier models including those costing 16x more per run. F3 Causal is the most discriminating family, with a 30.7-point spread between Sonnet (0.793) and Llama 3.3 70B (0.486), versus a 6.6-point spread on F1 Siting. A failure taxonomy of 135 coded failures identifies null-value integration in NREL ATB trajectories as the dominant failure mode (70%), followed by premature commitment on causal tasks (20%) and adversarial injection blindness (6%). Benchmark code, run trajectories, and the failure taxonomy dataset are publicly released.

econ.EM↗

arXiv2025

Benchmarking Reasoning Reliability in Artificial Intelligence Models for Energy-System Analysis

Artificial intelligence and machine learning are increasingly used for forecasting, optimization, and policy design in the energy sector, yet no standardized framework exists to evaluate whether these systems reason correctly. Current validation practices focus on predictive accuracy or computational efficiency, leaving the logical integrity of analytical conclusions untested. This study introduces the Analytical Reliability Benchmark (ARB), a reproducible framework that quantifies reasoning reliability in large language models applied to energy system analysis. The benchmark integrates five submetrics: accuracy, reasoning reliability, uncertainty discipline, policy consistency, and transparency, and evaluates model performance across deterministic, probabilistic, and epistemic scenarios using open technoeconomic datasets (NREL ATB 2024, DOE H2A/H2New, IEA WEO 2024). Four frontier models (GPT-4/5, Claude 4.5 Sonnet, Gemini 2.5 Pro, Llama 3 70B) were tested under identical factual and regulatory conditions. Results show that reasoning reliability can be objectively measured. GPT-4/5 and Claude 4.5 Sonnet achieved consistent and policy-compliant reasoning (Analytical Reliability Index greater than 90), Gemini 2.5 Pro demonstrated moderate stability, and Llama 3 70B remained below professional thresholds. Statistical validation confirmed that these differences are significant and reproducible. The ARB establishes the first quantitative method in the energy literature for verifying causal, probabilistic, and policy-driven reasoning in artificial intelligence systems, providing a reference framework for trustworthy and transparent analytical applications in the global energy transition.

cs.AI↗

arXiv2025

Introducing LCOAI: A Standardized Economic Metric for Evaluating AI Deployment Costs

As artificial intelligence (AI) becomes foundational to enterprise infrastructure, organizations face growing challenges in accurately assessing the full economic implications of AI deployment. Existing metrics such as API token costs, GPU-hour billing, or Total Cost of Ownership (TCO) fail to capture the complete lifecycle costs of AI systems and provide limited comparability across deployment models. This paper introduces the Levelized Cost of Artificial Intelligence (LCOAI), a standardized economic metric designed to quantify the total capital (CAPEX) and operational (OPEX) expenditures per unit of productive AI output, normalized by valid inference volume. Analogous to established metrics like LCOE (levelized cost of electricity) and LCOH (levelized cost of hydrogen) in the energy sector, LCOAI offers a rigorous, transparent framework to evaluate and compare the cost-efficiency of vendor API deployments versus self-hosted, fine-tuned models. We define the LCOAI methodology in detail and apply it to three representative scenarios, OpenAI GPT-4.1 API, Anthropic Claude Haiku API, and a self-hosted LLaMA-2-13B deployment demonstrating how LCOAI captures critical trade-offs in scalability, investment planning, and cost optimization. Extensive sensitivity analyses further explore the impact of inference volume, CAPEX, and OPEX variability on lifecycle economics. The results illustrate the practical utility of LCOAI in procurement, infrastructure planning, and automation strategy, and establish it as a foundational benchmark for AI economic analysis. Policy implications and areas for future refinement, including environmental and performance-adjusted cost metrics, are also discussed.

econ.GN↗

arXiv2025

Accelerating Transportation Decarbonization: The Strategic Role of Ethanol Blends and Regulatory Incentives

This study evaluates ethanol blending as a practical near-term strategy for significant transportation decarbonization in the United States. Despite rapid growth in electric vehicle adoption, gasoline is projected to remain dominant, with annual demand around 135 billion gallons by 2035, necessitating immediate complementary solutions. Analysis indicates ethanol use will notably expand, driven by regulatory incentives such as RFS Renewable Identification Numbers (RINs) and IRA tax credits (45V), leading to potential market penetration of E15 at about 25% and E85 also expanding substantially. Ethanol derived from waste achieves notably lower carbon intensity at approximately 58.34 gCO2e/MJ, substantially better than conventional gasoline (~92 gCO2e/MJ), providing clear environmental advantages. Economic assessments show robust investor returns and local economic growth driven by policy incentives, including Renewable Identification Numbers (RINs) and IRA tax credits (45V). Infrastructure analysis confirms manageable costs and feasible adjustments for widespread adoption of higher ethanol blends.

q-fin.GN↗

arXiv2025

Techno-Economic Analysis of Hydrogen Production: Costs, Policies, and Scalability in the Transition to Net-Zero

This study presents a comprehensive techno-economic analysis of gray, blue, and green hydrogen production pathways, evaluating their cost structures, investment feasibility, infrastructure challenges, and policy-driven cost reductions. The findings confirm that gray hydrogen (1.50-2.50/kg) remains the most cost-effective today but is increasingly constrained by carbon pricing. Blue hydrogen (2.00-3.50/kg) offers a transitional pathway but depends on CCS costs, natural gas price volatility, and regulatory support. Green hydrogen (3.50-6.00/kg) is currently the most expensive but benefits from declining renewable electricity costs, electrolyzer efficiency improvements, and government incentives such as the Inflation Reduction Act (IRA), which provides tax credits of up to 3.00/kg. The analysis shows that renewable electricity costs below 20-30/MWh are essential for green hydrogen to achieve cost parity with fossil-based hydrogen. The DOE's Hydrogen Shot Initiative aims to lower green hydrogen costs to 1.00/kg by 2031, emphasizing the need for CAPEX reductions, economies of scale, and improved electrolyzer efficiency. Infrastructure remains a critical challenge, with pipeline retrofitting reducing transport costs by 50-70%, though liquefied hydrogen and chemical carriers remain costly due to energy losses and reconversion expenses. Investment trends indicate a shift toward green hydrogen, with over 250 billion projected by 2035, surpassing blue hydrogen's expected 100 billion. Carbon pricing above $100/ton CO2 will likely make gray hydrogen uncompetitive by 2030, accelerating the shift to low-carbon hydrogen. Hydrogen's long-term viability depends on continued cost reductions, policy incentives, and infrastructure expansion, with green hydrogen positioned as a cornerstone of the net-zero energy transition by 2035.

econ.GN↗