About

Shan Lin is an Associate Professor at the Department of Electrical and Computer Engineering at Stony Brook University. His research focuses on cyber physical systems, wireless networks, networked information systems, and sensing systems. His work involves developing and analyzing systems that integrate physical processes with computational and communication components, aiming to improve the efficiency, reliability, and security of such systems.

Research topics

• Artificial Intelligence
• Computer Science
• Mathematics
• Mathematical optimization
• Distributed computing
• Electrical engineering
• Computer vision
• Real-time computing
• Computer network
• Engineering

Selected publications

• MARLIN: LLM-Guided Multi-Agent Reinforcement Learning with Murmuration Intelligence for Reservoir Management

  2026-05-24

  article

  Intensifying climate change and cascading uncertainties across interconnected reservoir networks pose escalating threats to global water security, demanding management systems that are both adaptive and scalable. Traditional centralized optimization becomes computationally intractable and brittle under real-world uncertainty, while existing reinforcement learning (RL) approaches are not designed for complex, multi-node hydrological systems. To address these challenges, we introduce MARLIN, a decentralized reservoir management framework that explicitly handles dual-layer uncertainty: (1) stochastic variability in physical water transfer and (2) dynamic human–environmental perturbations. MARLIN embeds bio-inspired alignment, separation, and cohesion rules into a multi-agent reinforcement learning (MARL) architecture to stabilize coordination under physical uncertainty. Additionally, external conditions such as weather forecasts, regulatory updates, and stakeholder preferences introduce unstructured textual information that traditional models cannot process directly. To bridge this gap, we integrate a large language model (LLM) that interprets contextual information and dynamically adjusts the coordination parameters of the three murmuration rules, enabling rapid adaptation to evolving environmental and human requirements. Experiments on USGS data show that MARLIN improves uncertainty handling by 23%, reduces computational cost by 35%, and accelerates flood response by 68%. The framework demonstrates strong scalability, with emergent coordination patterns increasing super-linearly as the network expands while maintaining linear computational complexity. These results highlight MARLIN's potential as a scalable and intelligent solution for adaptive water resource management and disaster prevention.

  PublisherDOI

• eFlx: Energy Flexibility Provisioning for E-taxi Fleets

  2025-05-06

  articleOpen accessSenior author

  An e-taxi fleet consumes a significant amount of energy daily, making it a substantial electricity consumer. Unlike traditional consumers, such as factories and buildings, a fleet coordinates charging activities across both times and locations, offering considerable flexibility in its energy demand. This allows a fleet to achieve substantial reductions in energy consumption in response to demand response requests while maintaining transportation service quality. To better understand and control this intrinsic energy flexibility, we propose the eFlx framework for managing e-taxi fleets for demand response. In the eFlx framework, we establish a model to characterize the energy flexibility upon receiving a real-time demand response request. We then investigate the energy flexibility provisioning problem, formulated as a bi-level optimal control problem, which aims to optimize and maintain the energy flexibility of the fleet for potential demand response requests that could arise at any time. To achieve real-time flexibility provisioning, we develop an efficient iterative algorithm to solve this problem. Data-driven evaluations with NYC datasets demonstrate that eFlx achieves a 19. 98% greater reduction in energy demand compared to existing solutions, without requiring extra charging or compromising the quality of taxi service.

  PublisherOA PDFDOI

• Multi-Agent Reinforcement Learning for Decentralized Reservoir Management via Murmuration Intelligence

  ArXiv.org · 2025-04-15

  preprintOpen accessSenior author

  Conventional centralized water management systems face critical limitations from computational complexity and uncertainty propagation. We present MurmuRL, a novel decentralized framework inspired by starling murmurations intelligence, integrating bio-inspired alignment, separation, and cohesion rules with multi-agent reinforcement learning. MurmuRL enables individual reservoirs to make autonomous local decisions while achieving emergent global coordination. Experiments on grid networks demonstrate that MurmuRL achieves 8.8% higher final performance while using 27% less computing overhead compared to centralized approaches. Notably, strategic diversity scales super-linearly with system size, exhibiting sophisticated coordination patterns and enhanced resilience during extreme events. MurmuRL offers a scalable solution for managing complex water systems by leveraging principles of natural collective behavior.

  PublisherOA PDFDOI

• Energy-aware E-taxi Fleet Coordination under Power Rationing via Dynamic Charging Rate

  2025-07-08

  articleSenior author

  Existing electric taxi (e-taxi) services rely on charging infrastructure to maintain their daily operations. Unfortunately, severe power system disruptions, such as power rationing, can impose harsh constraints on e-taxi charging activities and significantly affect the service quality of e-taxis fleets. To address this issue, we design a framework for Energy-Aware e-taxi fleet coordination via dynamic charging Rate (EAR), to provide a satisfactory service quality while meeting energy conservation requirements. In this framework, an e-taxi fleet coordination algorithm is designed to provide sustainable service quality during pre-rationing, rationing and post-rationing phases. The coordination problem across the three phases is modeled as separate multi-objective mixed-integer linear problems due to the distinct objectives of each phase. The proposed solution is evaluated with a comprehensive dataset for an existing e-taxi system and charging infrastructures including nearly 800 e-taxis. Our data-driven evaluation shows that EAR improves the ratio of served passengers by 37.0% during the power rationing phase compared with the state-of-the-art method, which does not consider disruptions in charging infrastructure when coordinating e-taxis.

  PublisherDOI

• Cumulative-Time Signal Temporal Logic

  ArXiv.org · 2025-04-14

  preprintOpen accessSenior author

  Signal Temporal Logic (STL) is a widely adopted specification language in cyber-physical systems for expressing critical temporal requirements, such as safety conditions and response time. However, STL's expressivity is not sufficient to capture the cumulative duration during which a property holds within an interval of time. To overcome this limitation, we introduce Cumulative-Time Signal Temporal Logic (CT-STL) that operates over discrete-time signals and extends STL with a new cumulative-time operator. This operator compares the sum of all time steps for which its nested formula is true with a threshold. We present both a qualitative and a quantitative (robustness) semantics for CT-STL and prove both their soundness and completeness properties. We provide an efficient online monitoring algorithm for both semantics. Finally, we show the applicability of CT-STL in two case studies: specifying and monitoring cumulative temporal requirements for a microgrid and an artificial pancreas.

  PublisherOA PDFDOI

• A novel and robust Fourier-based Kolmogorov-Arnold Network in early warning of rockbursts from microseismic data

  Stochastic Environmental Research and Risk Assessment · 2025-10-17

  article
  PublisherDOI

• Energy consumption monitoring of traction transformer end in rail transit under dual carbon targets

  2025-01-20

  article

  Carbon emissions are a global issue that restricts social development, and the carbon emissions level of the power industry directly affects the achievement of international commitments to carbon reduction. Reducing the energy consumption of rail transit can help optimize the energy structure, reduce greenhouse gas emissions, and contribute to achieving China's dual carbon goals. Therefore, this article proposes a method for monitoring the energy consumption of traction transformers in rail transit under the dual carbon target. A monitoring and control scheme based on microcontroller was studied by analyzing the losses of traction transformers in rail transit. This scheme calculates the load of the transformer through a multifunctional meter, and sets corresponding gear shifting thresholds to adjust the transformer capacity, in order to reduce losses and save energy. After experimental verification, this method has improved the energy-saving effect of traction transformers to a certain extent, while ensuring the stability and reliability of operation, providing useful reference for achieving carbon reduction goals in the field of rail transit.

  PublisherDOI

• SHADE-AD: An LLM-Based Framework for Synthesizing Activity Data of Alzheimer’s Patients

  2025-05-04 · 6 citations

  articleOpen access

  Alzheimer's Disease (AD) has become an increasingly critical global health concern, which necessitates effective monitoring solutions in smart health applications. However, the development of such solutions is significantly hindered by the scarcity of AD-specific activity datasets. To address this challenge, we propose SHADE-AD, a Large Language Model (LLM) framework for Synthesizing Human Activity Datasets Embedded with AD features. Leveraging both public datasets and our own collected data from 99 AD patients, SHADE-AD synthesizes human activity videos that specifically represent AD-related behaviors. By employing a three-stage training mechanism, it broadens the range of activities beyond those collected from limited deployment settings. We conducted comprehensive evaluations of the generated dataset, demonstrating significant improvements in downstream tasks such as Human Activity Recognition (HAR) detection, with enhancements of up to 79.69%. Detailed motion metrics between real and synthetic data show strong alignment, validating the realism and utility of the synthesized dataset. These results underscore SHADE-AD's potential to advance smart health applications by providing a cost-effective, privacy-preserving solution for AD monitoring.

  PublisherDOI

• MARLIN: Multi-Agent Reinforcement Learning with Murmuration Intelligence and LLM Guidance for Reservoir Management

  arXiv (Cornell University) · 2025-09-29

  preprintOpen access

  As climate change intensifies extreme weather events, water disasters pose growing threats to global communities, making adaptive reservoir management critical for protecting vulnerable populations and ensuring water security. Modern water resource management faces unprecedented challenges from cascading uncertainties propagating through interconnected reservoir networks. These uncertainties, rooted in physical water transfer losses and environmental variability, make precise control difficult. For example, sending 10 tons downstream may yield only 8-12 tons due to evaporation and seepage. Traditional centralized optimization approaches suffer from exponential computational complexity and cannot effectively handle such real-world uncertainties, while existing multi-agent reinforcement learning (MARL) methods fail to achieve effective coordination under uncertainty. To address these challenges, we present MARLIN, a decentralized reservoir management framework inspired by starling murmurations intelligence. Integrating bio-inspired alignment, separation, and cohesion rules with MARL, MARLIN enables individual reservoirs to make local decisions while achieving emergent global coordination. In addition, a LLM provides real-time reward shaping signals, guiding agents to adapt to environmental changes and human-defined preferences. Experiments on USGS data show that MARLIN improves uncertainty handling by 23\%, cuts computation by 35\%, and accelerates flood response by 68\%, exhibiting super-linear coordination, with complexity scaling 5.4x from 400 to 10,000 nodes. These results demonstrate MARLIN's potential for disaster prevention and protecting communities through intelligent, scalable water resource management.

  PublisherOA PDFDOI

• An STREL-based Formulation of Spatial Resilience in Cyber-Physical Systems

  ArXiv.org · 2025-12-14

  preprintOpen access

  Resiliency is the ability of a system to quickly recover from a violation (recoverability) and avoid future violations for as long as possible (durability). In the spatial setting, recoverability and durability (now known as persistency) are measured in units of distance. Like its temporal counterpart, spatial resiliency is of fundamental importance for Cyber-Physical Systems (CPS) and yet, to date, there is no widely agreed-upon formal treatment of spatial resiliency. We present a formal framework for reasoning about spatial resiliency in CPS. Our framework is based on the spatial fragment of STREL, which we refer to as SREL. In this framework, spatial resiliency is given a syntactic characterization in the form of a Spatial Resiliency Specification (SpaRS). An atomic predicate of SpaRS is called an S-atom. Given an arbitrary SREL formula $φ$, distance bounds $d_1, d_2$, the S-atom of $φ$, $S_{d_1, d_2} (φ)$, is the SREL formula $\negφR_{[0,d_1]} (φR_{[d_2, +\infty)}φ)$, specifying that recovery from a violation of $φ$ occurs within distance $d_1$ (recoverability), and subsequently that $φ$ be maintained along a route for a distance greater than $d_2$ (persistency). S-atoms can be combined using spatial STREL operators, allowing one to express composite resiliency specifications. We define a quantitative semantics for SpaRS in the form of a Spatial Resilience Value (SpaRV) function $σ$ and prove its soundness and completeness w.r.t. SREL's Boolean semantics. The $σ$-value for $S_{d_1,d_2}(φ)$ is a set of non-dominated (rec, per) pairs, quantifying recoverability and persistency, given that some routes may offer better recoverability while others better persistency. In addition, we design algorithms to evaluate SpaRV for SpaRS formulas. Finally, two case studies demonstrate the practical utility of our approach.

  PublisherOA PDFDOI

Recent grants

• CAREER: Safe and Secure Network Control for Smart and Connected Hospitals

  NSF · $450k · 2016–2023

• SHB: Type I (EXP): Collaborative Research: Heterogeneous Large-Scale Telemedicine for Cardiology Patients

  NSF · $300k · 2012–2014

• CPS: Synergy: Collaborative Research: Multiple-Level Predictive Control of Mobile Cyber Physical Systems with Correlated Context

  NSF · $88k · 2015–2017

• CPS: Synergy: Collaborative Research: Multiple-Level Predictive Control of Mobile Cyber Physical Systems with Correlated Context

  NSF · $200k · 2012–2015

• NeTS: Small: Collaborative Research: Non-Isotropic Networked Sensor Deployment for Smart Buildings

  NSF · $271k · 2012–2014

Frequent coauthors

• John A. Stankovic

  33 shared

• Tian He

  Jingdong (China)

  21 shared

• Hua Huang

  20 shared

• Kin Sum Liu

  Stony Brook University

  18 shared

• Scott A. Smolka

  16 shared

• Nicola Paoletti

  16 shared

• Desheng Zhang

  Yuntianhua Group (China)

  16 shared

• Fei Miao

  University of Connecticut

  14 shared

Labs

• Electrical and Computer EngineeringPI

Education

• Ph.D., Electrical Engineering

  University of California, Los Angeles

  2007

• M.S., Electrical Engineering

  University of California, Los Angeles

  2003

• B.S., Electrical Engineering

  University of California, Los Angeles

  2001