arXiv subjects

Mohammad A. Islam

Publications and source records attributed to Mohammad A. Islam.

10 recordsLinked to original sources

arXiv2026

Balancing Bits and Drops: Stress-Adjusted Water Management for Data Centers

Data centers are critical to today's digital economy, but are also among the largest industrial consumers of freshwater. Beyond the sheer volume of water use, the environmental impact of data center water consumption varies significantly across locations and seasons, depending on local and regional water stress. However, prior research has largely focused on reducing total water use, overlooking that the same unit of water can have drastically different environmental consequences depending on when and where it is consumed. In this paper, we introduce a stress-adjusted water framework that quantifies the true sustainability impact of data center water consumption by incorporating both spatial and temporal water stress. Using the AWARE-US model, we capture county-level monthly variations in water availability and extend this framework to account for the off-site water footprint of electricity generation. Based on this stress-aware accounting, we analyze stress-adjusted water-computing strategies spanning both the software and infrastructure layers. Specifically, we study workload scheduling policies that jointly optimize water and carbon efficiency, evaluate the potential of rainwater harvesting as a supplemental water source, and investigate the feasibility of dry cooling as a water-free alternative to evaporative cooling.

cs.CY↗

arXiv2026

Maximizing Compute Capacity in AI Data Centers through Cooling, Energy Storage, and Computing Adaptation

The deployment of artificial intelligence is increasingly constrained by limited site-level power capacity, which must support both compute systems and non-compute systems (primarily cooling) at all times. Cooling power demand, especially in non-evaporative cooling systems, can increase substantially with ambient temperature in the summer, producing recurring periods of elevated cooling power that often lasts for multiple hours per day. Therefore, maximizing compute capacity under a limited site-level power budget is an important planning and operational challenge. Sizing the compute system conservatively based on peak cooling power can leave part of the site-level power capacity underutilized when the cooling power is below its peak, particularly in cooler months. On the other hand, sizing the compute system aggressively based on low cooling power can cause the total site-level power demand to exceed the site-level power capacity during hot days in the summer. This paper proposes ComputeAmp (Compute Amplifier), a framework that maximizes the compute capacity by jointly and dynamically leveraging cooling, battery energy storage, and computing-based adaptation. We discuss the opportunities and limitations of ComputeAmp and illustrate its potential to significantly expand usable compute capacity within local power and water resource limits. We also present a problem formulation for ComputeAmp and highlight a few algorithmic and operational challenges.

cs.PF↗

arXiv2026

DeEscalWild: A Real-World Benchmark for Automated De-Escalation Training with SLMs

Effective de-escalation is critical for law enforcement safety and community trust, yet traditional training methods lack scalability and realism. While Large Language Models (LLMs) enable dynamic, open-ended simulations, their substantial computational footprint renders them impractical for deployment on the lightweight, portable hardware required for immersive field training. Small Language Models (SLMs) offer a viable real-time alternative but suffer from a critical scarcity of high-quality, domain-specific training data. To bridge this gap, we present DeEscalWild, a novel benchmark dataset curated from a multi-stage pipeline of in-the-wild police-civilian interactions extracted from publicly available video repositories. Starting with 5,000 raw inputs, we employed a rigorous hybrid filtering process combining human-in-the-loop verification with LLM-as-a-Judge evaluation to distill 1,500 high-fidelity scenarios. The resulting corpus comprises 285,887 dialogue turns, totaling approximately 4.7 million tokens. Extensive experiments demonstrate that SLMs fine-tuned on this data significantly outperform their base counterparts across ROUGE-L, BLEU-4, METEOR, BERTScore, Realism Score, and human evaluation metrics. Notably, our fine-tuned Qwen 2.5 (3B-Instruct) surpasses the general-purpose Gemini 2.5 Flash model when evaluated under equivalent conditions, demonstrating that domain-optimized SLMs can achieve superior performance with a fraction of the computational cost. This work establishes the foundational infrastructure for accessible, low-latency, and privacy-preserving officer training systems at the edge. We publicly release our code(https://github.com/Hasebul/DeEscalWild-Benchmark-Framework) and dataset(https://doi.org/10.7910/DVN/CWMCZI).

cs.CL↗

arXiv2025

Making AI Less "Thirsty": Uncovering and Addressing the Secret Water Footprint of AI Models

The growing carbon footprint of artificial intelligence (AI) has been undergoing public scrutiny. Nonetheless, the equally important water (withdrawal and consumption) footprint of AI has largely remained under the radar. For example, training the GPT-3 language model in Microsoft's state-of-the-art U.S. data centers can directly evaporate 700,000 liters of clean freshwater, but such information has been kept a secret. More critically, the global AI demand is projected to account for 4.2-6.6 billion cubic meters of water withdrawal in 2027, which is more than the total annual water withdrawal of 4-6 Denmark or half of the United Kingdom. This is concerning, as freshwater scarcity has become one of the most pressing challenges. To respond to the global water challenges, AI can, and also must, take social responsibility and lead by example by addressing its own water footprint. In this paper, we provide a principled methodology to estimate the water footprint of AI, and also discuss the unique spatial-temporal diversities of AI's runtime water efficiency. Finally, we highlight the necessity of holistically addressing water footprint along with carbon footprint to enable truly sustainable AI.

cs.LG↗

arXiv2025

Power-Aware Scheduling for Multi-Center HPC Electricity Cost Optimization

This paper introduces TARDIS (Temporal Allocation for Resource Distribution using Intelligent Scheduling), a novel power-aware job scheduler for High-Performance Computing (HPC) systems that minimizes electricity costs through both temporal and spatial optimization. Our approach addresses the growing concerns of energy consumption in HPC centers, where electricity expenses constitute a substantial portion of operational costs and have a significant financial impact. TARDIS employs a Graph Neural Network (GNN) to accurately predict individual job power consumption, then uses these predictions to strategically schedule jobs across multiple HPC facilities based on time-varying electricity prices. The system integrates both temporal scheduling, shifting power-intensive workloads to off-peak hours, and spatial scheduling, distributing jobs across geographically dispersed centers with different pricing schemes. We evaluate TARDIS using trace-based simulations from real HPC workloads, demonstrating cost reductions of up to 18% in temporal optimization scenarios and 10 to 20% in multi-site environments compared to state-of-the-art scheduling approaches, while maintaining comparable system performance and job throughput. Our comprehensive evaluation shows that TARDIS effectively addresses limitations in existing power-aware scheduling approaches by combining accurate power prediction with holistic spatial-temporal optimization, providing a scalable solution for sustainable and cost-efficient HPC operations.

cs.DC↗

arXiv2025

HPC Application Parameter Autotuning on Edge Devices: A Bandit Learning Approach

The growing necessity for enhanced processing capabilities in edge devices with limited resources has led us to develop effective methods for improving high-performance computing (HPC) applications. In this paper, we introduce LASP (Lightweight Autotuning of Scientific Application Parameters), a novel strategy designed to address the parameter search space challenge in edge devices. Our strategy employs a multi-armed bandit (MAB) technique focused on online exploration and exploitation. Notably, LASP takes a dynamic approach, adapting seamlessly to changing environments. We tested LASP with four HPC applications: Lulesh, Kripke, Clomp, and Hypre. Its lightweight nature makes it particularly well-suited for resource-constrained edge devices. By employing the MAB framework to efficiently navigate the search space, we achieved significant performance improvements while adhering to the stringent computational limits of edge devices. Our experimental results demonstrate the effectiveness of LASP in optimizing parameter search on edge devices.

cs.PF↗

arXiv2024

A Dataset for Research on Water Sustainability

Freshwater scarcity is a global problem that requires collective efforts across all industry sectors. Nevertheless, a lack of access to operational water footprint data bars many applications from exploring optimization opportunities hidden within the temporal and spatial variations. To break this barrier into research in water sustainability, we build a dataset for operation direct water usage in the cooling systems and indirect water embedded in electricity generation. Our dataset consists of the hourly water efficiency of major U.S. cities and states from 2019 to 2023. We also offer cooling system models that capture the impact of weather on water efficiency. We present a preliminary analysis of our dataset and discuss three potential applications that can benefit from it. Our dataset is publicly available at Open Science Framework (OSF)

cs.LG↗

arXiv2022

Practical Efficient Microservice Autoscaling with QoS Assurance

Cloud applications are increasingly moving away from monolithic services to agile microservices-based deployments. However, efficient resource management for microservices poses a significant hurdle due to the sheer number of loosely coupled and interacting components. The interdependencies between various microservices make existing cloud resource autoscaling techniques ineffective. Meanwhile, machine learning (ML) based approaches that try to capture the complex relationships in microservices require extensive training data and cause intentional SLO violations. Moreover, these ML-heavy approaches are slow in adapting to dynamically changing microservice operating environments. In this paper, we propose PEMA (Practical Efficient Microservice Autoscaling), a lightweight microservice resource manager that finds efficient resource allocation through opportunistic resource reduction. PEMA's lightweight design enables novel workload-aware and adaptive resource management. Using three prototype microservice implementations, we show that PEMA can find efficient resource allocation and save up to 33% resource compared to the commercial rule-based resource allocations.

cs.DC↗

arXiv2020

Your Noise, My Signal: Exploiting Switching Noise for Stealthy Data Exfiltration from Desktop Computers

Attacks based on power analysis have been long existing and studied, with some recent works focused on data exfiltration from victim systems without using conventional communications (e.g., WiFi). Nonetheless, prior works typically rely on intrusive direct power measurement, either by implanting meters in the power outlet or tapping into the power cable, thus jeopardizing the stealthiness of attacks. In this paper, we propose NoDE (Noise for Data Exfiltration), a new system for stealthy data exfiltration from enterprise desktop computers. Specifically, NoDE achieves data exfiltration over a building's power network by exploiting high-frequency voltage ripples (i.e., switching noises) generated by power factor correction circuits built into today's computers. Located at a distance and even from a different room, the receiver can non-intrusively measure the voltage of a power outlet to capture the high-frequency switching noises for online information decoding without supervised training/learning. To evaluate NoDE, we run experiments on seven different computers from top-vendors and using top brand power supply units. Our results show that for a single transmitter, NoDE achieves a rate of up to 28.48 bits/second with a distance of 90 feet (27.4 meters) without the line of sight, demonstrating a practically stealthy threat. Based on the orthogonality of switching noise frequencies of different computers, we also demonstrate simultaneous data exfiltration from four computers using only one receiver. Finally, we present a few possible defenses, such as installing noise filters, and discuss their limitations.

cs.CR↗

arXiv2013

Normal Mode Determination of Perovskite Crystal Structures with Octahedral Rotations: Theory and Applications

Nuclear site analysis methods are used to enumerate the normal modes of $ABX_{3}$ perovskite polymorphs with octahedral rotations. We provide the modes of the fourteen subgroups of the cubic aristotype describing the Glazer octahedral tilt patterns, which are obtained from rotations of the $BX_{6}$ octahedra with different sense and amplitude about high symmetry axes. We tabulate all normal modes of each tilt system and specify the contribution of each atomic species to the mode displacement pattern, elucidating the physical meaning of the symmetry unique modes. We have systematically generated 705 schematic atomic displacement patterns for the normal modes of all 15 (14 rotated + 1 unrotated) Glazer tilt systems. We show through some illustrative examples how to use these tables to identify the octahedral rotations, symmetric breathing, and first-order Jahn-Teller anti-symmetric breathing distortions of the $BX_{6}$ octahedra, and the associated Raman selection rules. We anticipate that these tables and schematics will be useful in understanding the lattice dynamics of bulk perovskites and would serve as reference point in elucidating the atomic origin of a wide range of physical properties in synthetic perovskite thin films and superlattices.

cond-mat.mtrl-sci↗