arXiv subjects

Areg Karapetyan

Publications and source records attributed to Areg Karapetyan.

14 recordsLinked to original sources

arXiv2026

UniST-Pred: A Robust Unified Framework for Spatio-Temporal Traffic Forecasting in Transportation Networks Under Disruptions

Spatio-temporal traffic forecasting is a core component of intelligent transportation systems, supporting various downstream tasks such as signal control and network-level traffic management. In real-world deployments, forecasting models must operate under structural and observational uncertainties, conditions that are rarely considered in model design. Recent approaches achieve strong short-term predictive performance by tightly coupling spatial and temporal modeling, often at the cost of increased complexity and limited modularity. In contrast, efficient time-series models capture long-range temporal dependencies without relying on explicit network structure. We propose UniST-Pred, a unified spatio-temporal forecasting framework that first decouples temporal modeling from spatial representation learning, then integrates both through adaptive representation-level fusion. To assess robustness of the proposed approach, we construct a dataset based on an agent-based, microscopic traffic simulator (MATSim) and evaluate UniST-Pred under severe network disconnection scenarios. Additionally, we benchmark UniST-Pred on standard traffic prediction datasets, demonstrating its competitive performance against existing well-established models despite a lightweight design. The results illustrate that UniST-Pred maintains strong predictive performance across both real-world and simulated datasets, while also yielding interpretable spatio-temporal representations under infrastructure disruptions. The source code and the generated dataset are available at https://anonymous.4open.science/r/UniST-Pred-EF27

cs.LG↗

arXiv2025

Climate Adaptation-Aware Flood Prediction for Coastal Cities Using Deep Learning

Climate change and sea-level rise (SLR) pose escalating threats to coastal cities, intensifying the need for efficient and accurate methods to predict potential flood hazards. Traditional physics-based hydrodynamic simulators, although precise, are computationally expensive and impractical for city-scale coastal planning applications. Deep Learning (DL) techniques offer promising alternatives, however, they are often constrained by challenges such as data scarcity and high-dimensional output requirements. Leveraging a recently proposed vision-based, low-resource DL framework, we develop a novel, lightweight Convolutional Neural Network (CNN)-based model designed to predict coastal flooding under variable SLR projections and shoreline adaptation scenarios. Furthermore, we demonstrate the ability of the model to generalize across diverse geographical contexts by utilizing datasets from two distinct regions: Abu Dhabi and San Francisco. Our findings demonstrate that the proposed model significantly outperforms state-of-the-art methods, reducing the mean absolute error (MAE) in predicted flood depth maps on average by nearly 20%. These results highlight the potential of our approach to serve as a scalable and practical tool for coastal flood management, empowering decision-makers to develop effective mitigation strategies in response to the growing impacts of climate change. Project Page: https://caspiannet.github.io/

cs.CV↗

arXiv2024

Deep Vision-Based Framework for Coastal Flood Prediction Under Climate Change Impacts and Shoreline Adaptations

In light of growing threats posed by climate change in general and sea level rise (SLR) in particular, the necessity for computationally efficient means to estimate and analyze potential coastal flood hazards has become increasingly pressing. Data-driven supervised learning methods serve as promising candidates that can dramatically expedite the process, thereby eliminating the computational bottleneck associated with traditional physics-based hydrodynamic simulators. Yet, the development of accurate and reliable coastal flood prediction models, especially those based on Deep Learning (DL) techniques, has been plagued with two major issues: (1) the scarcity of training data and (2) the high-dimensional output required for detailed inundation mapping. To remove this barrier, we present a systematic framework for training high-fidelity Deep Vision-based coastal flood prediction models in low-data settings. We test the proposed workflow on different existing vision models, including a fully transformer-based architecture and a Convolutional Neural Network (CNN) with additive attention gates. Additionally, we introduce a deep CNN architecture tailored specifically to the coastal flood prediction problem at hand. The model was designed with a particular focus on its compactness so as to cater to resource-constrained scenarios and accessibility aspects. The performance of the developed DL models is validated against commonly adopted geostatistical regression methods and traditional Machine Learning (ML) approaches, demonstrating substantial improvement in prediction quality. Lastly, we round up the contributions by providing a meticulously curated dataset of synthetic flood inundation maps of Abu Dhabi's coast produced with a physics-based hydrodynamic simulator, which can serve as a benchmark for evaluating future coastal flood prediction models.

cs.CV↗

arXiv2023

Improved Approximation Guarantees for Power Scheduling Problems With Sum-of-Squares Constraints

We study a class of combinatorial scheduling problems characterized by a particular type of constraint often associated with electrical power or gas energy. This constraint appears in several practical applications and is expressed as a sum of squares of linear functions. Its nonlinear nature adds complexity to the scheduling problem, rendering it notably challenging, even in the case of a linear objective. In fact, exact polynomial time algorithms are unlikely to exist, and thus, prior works have focused on designing approximation algorithms with polynomial running time and provable guarantees on the solution quality. In an effort to advance this line of research, we present novel approximation algorithms yielding significant improvements over the existing state-of-the-art results for these problems.

cs.DS↗

arXiv2023

DClEVerNet: Deep Combinatorial Learning for Efficient EV Charging Scheduling in Large-scale Networked Facilities

With the electrification of transportation, the rising uptake of electric vehicles (EVs) might stress distribution networks significantly, leaving their performance degraded and stability jeopardized. To accommodate these new loads cost-effectively, modern power grids require coordinated or ``smart'' charging strategies capable of optimizing EV charging scheduling in a scalable and efficient fashion. With this in view, the present work focuses on reservation management programs for large-scale, networked EV charging stations. We formulate a time-coupled binary optimization problem that maximizes EV users' total welfare gain while accounting for the network's available power capacity and stations' occupancy limits. To tackle the problem at scale while retaining high solution quality, a data-driven optimization framework combining techniques from the fields of Deep Learning and Approximation Algorithms is introduced. The framework's key ingredient is a novel input-output processing scheme for neural networks that allows direct extrapolation to problem sizes substantially larger than those included in the training set. Extensive numerical simulations based on synthetic and real-world data traces verify the effectiveness and superiority of the presented approach over two representative scheduling algorithms. Lastly, we round up the contributions by listing several immediate extensions to the proposed framework and outlining the prospects for further exploration.

cs.LG↗

arXiv2023

Towards Autonomous and Safe Last-mile Deliveries with AI-augmented Self-driving Delivery Robots

In addition to its crucial impact on customer satisfaction, last-mile delivery (LMD) is notorious for being the most time-consuming and costly stage of the shipping process. Pressing environmental concerns combined with the recent surge of e-commerce sales have sparked renewed interest in automation and electrification of last-mile logistics. To address the hurdles faced by existing robotic couriers, this paper introduces a customer-centric and safety-conscious LMD system for small urban communities based on AI-assisted autonomous delivery robots. The presented framework enables end-to-end automation and optimization of the logistic process while catering for real-world imposed operational uncertainties, clients' preferred time schedules, and safety of pedestrians. To this end, the integrated optimization component is modeled as a robust variant of the Cumulative Capacitated Vehicle Routing Problem with Time Windows, where routes are constructed under uncertain travel times with an objective to minimize the total latency of deliveries (i.e., the overall waiting time of customers, which can negatively affect their satisfaction). We demonstrate the proposed LMD system's utility through real-world trials in a university campus with a single robotic courier. Implementation aspects as well as the findings and practical insights gained from the deployment are discussed in detail. Lastly, we round up the contributions with numerical simulations to investigate the scalability of the developed mathematical formulation with respect to the number of robotic vehicles and customers.

cs.RO↗

arXiv2022

Approximations for Generalized Unsplittable Flow on Paths with Application to Power Systems Optimization

The Unsplittable Flow on a Path (UFP) problem has garnered considerable attention as a challenging combinatorial optimization problem with notable practical implications. Steered by its pivotal applications in power engineering, the present work formulates a novel generalization of UFP, wherein demands and capacities in the input instance are monotone step functions over the set of edges. As an initial step towards tackling this generalization, we draw on and extend ideas from prior research to devise a quasi-polynomial time approximation scheme (QPTAS) under the premise that the demands and capacities lie in a quasi-polynomial range. Second, retaining the same assumption, an efficient logarithmic approximation is introduced for the single-source variant of the problem. Finally, we round up the contributions by designing a (kind of) black-box reduction that, under some mild conditions, allows to translate LP-based approximation algorithms for the studied problem into their counterparts for the Alternating Current Optimal Power Flow (AC OPF) problem -- a fundamental workflow in operation and control of power systems.

cs.DS↗

arXiv2022

Multi-Agent Chance-Constrained Stochastic Shortest Path with Application to Risk-Aware Intelligent Intersection

In transportation networks, where traffic lights have traditionally been used for vehicle coordination, intersections act as natural bottlenecks. A formidable challenge for existing automated intersections lies in detecting and reasoning about uncertainty from the operating environment and human-driven vehicles. In this paper, we propose a risk-aware intelligent intersection system for autonomous vehicles (AVs) as well as human-driven vehicles (HVs). We cast the problem as a novel class of Multi-agent Chance-Constrained Stochastic Shortest Path (MCC-SSP) problems and devise an exact Integer Linear Programming (ILP) formulation that is scalable in the number of agents' interaction points (e.g., potential collision points at the intersection). In particular, when the number of agents within an interaction point is small, which is often the case in intersections, the ILP has a polynomial number of variables and constraints. To further improve the running time performance, we show that the collision risk computation can be performed offline. Additionally, a trajectory optimization workflow is provided to generate risk-aware trajectories for any given intersection. The proposed framework is implemented in CARLA simulator and evaluated under a fully autonomous intersection with AVs only as well as in a hybrid setup with a signalized intersection for HVs and an intelligent scheme for AVs. As verified via simulations, the featured approach improves intersection's efficiency by up to $200\%$ while also conforming to the specified tunable risk threshold.

cs.AI↗

arXiv2022

Autonomous Recharging and Flight Mission Planning for Battery-operated Autonomous Drones

Unmanned aerial vehicles (UAVs), commonly known as drones, are being increasingly deployed throughout the globe as a means to streamline monitoring, inspection, mapping, and logistic routines. When dispatched on autonomous missions, drones require an intelligent decision-making system for trajectory planning and tour optimization. Given the limited capacity of their onboard batteries, a key design challenge is to ensure the underlying algorithms can efficiently optimize the mission objectives along with recharging operations during long-haul flights. With this in view, the present work undertakes a comprehensive study on automated tour management systems for an energy-constrained drone: (1) We construct a machine learning model that estimates the energy expenditure of typical multi-rotor drones while accounting for real-world aspects and extrinsic meteorological factors. (2) Leveraging this model, the joint program of flight mission planning and recharging optimization is formulated as a multi-criteria Asymmetric Traveling Salesman Problem (ATSP), wherein a drone seeks for the time-optimal energy-feasible tour that visits all the target sites and refuels whenever necessary. (3) We devise an efficient approximation algorithm with provable worst-case performance guarantees and implement it in a drone management system, which supports real-time flight path tracking and re-computation in dynamic environments. (4) The effectiveness and practicality of the proposed approach are validated through extensive numerical simulations as well as real-world experiments.

cs.RO↗

arXiv2021

Online Algorithm for Demand Response with Inelastic Demands and Apparent Power Constraint

A classical problem in power systems is to allocate in-coming (elastic or inelastic) demands without violating the operating constraints of electric networks in an online fashion. Although online decision problems have been well-studied in the literature, a unique challenge arising in power systems is the presence of non-linear constraints, a departure from the traditional settings. A particular example is the capacity constraint of apparent power, which gives rise to a quadratic constraint, rather than typical linear constraints. In this paper, we present a competitive randomized online algorithm for deciding whether a sequence of inelastic demands can be allocated for the requested intervals, subject to the total satisfiable apparent power within a time-varying capacity constraint. We also consider an alternative setting with nodal voltage constraint, using a variant of the online algorithm. Finally, simulation studies are provided to evaluate the algorithms empirically.

cs.DS↗

arXiv2020

Explainable AI as a Social Microscope: A Case Study on Academic Performance

Academic performance is perceived as a product of complex interactions between students' overall experience, personal characteristics and upbringing. Data science techniques, most commonly involving regression analysis and related approaches, serve as a viable means to explore this interplay. However, these tend to extract factors with wide-ranging impact, while overlooking variations specific to individual students. Focusing on each student's peculiarities is generally impossible with thousands or even hundreds of subjects, yet data mining methods might prove effective in devising more targeted approaches. For instance, subjects with shared characteristics can be assigned to clusters, which can then be examined separately with machine learning algorithms, thereby providing a more nuanced view of the factors affecting individuals in a particular group. In this context, we introduce a data science workflow allowing for fine-grained analysis of academic performance correlates that captures the subtle differences in students' sensitivities to these factors. Leveraging the Local Interpretable Model-Agnostic Explanations (LIME) algorithm from the toolbox of Explainable Artificial Intelligence (XAI) techniques, the proposed pipeline yields groups of students having similar academic attainment indicators, rather than similar features (e.g. familial background) as typically practiced in prior studies. As a proof-of-concept case study, a rich longitudinal dataset is selected to evaluate the effectiveness of the proposed approach versus a standard regression model.

cs.CY↗

arXiv2018

Complex-demand Scheduling Problem with Application in Smart Grid

We consider the problem of scheduling complex-valued demands over a discretized time horizon. Given a set of users, each user is associated with a set of demands representing different power consumption preferences. A demand is represented by a complex number, a time interval, and a utility value obtained if it is satisfied. At each time slot, the magnitude of the total selected demands should not exceed a given generation capacity. This naturally captures the supply constraints in alternating current (AC) electric systems. In this paper, we consider maximizing the aggregate user utility subject to power supply limits over a time horizon. We present approximation algorithms characterized by the maximum angle $ϕ$ between any two complex-valued demands. More precisely, a PTAS is presented for the case $ϕ\in [0,\tfracπ{2}]$, a bi-criteria FPTAS for $ϕ\in [0,π \mbox{-} \varepsilon]$ for any polynomially small $\varepsilon$, assuming the number of time slots in the discretized time horizon is a constant. Furthermore, if the number of time slots is part of the input, we present a reduction to the real-valued unsplittable flow problem on a path with only a constant approximation ratio. Finally, we present a practical greedy algorithm for the single time slot case with an approximation ratio of $\tfrac{1}{2}\cos \fracϕ{2}$ and a running time complexity of only ${O}(N\log N)$, $N$ standing for the aggregate number of user demands, which can be implemented efficiently in practice.

cs.DS↗

arXiv2018

Assessing the Privacy Cost in Centralized Event-Based Demand Response for Microgrids

Demand response (DR) programs have emerged as a potential key enabling ingredient in the context of smart grid (SG). Nevertheless, the rising concerns over privacy issues raised by customers subscribed to these programs constitute a major threat towards their effective deployment and utilization. This has driven extensive research to resolve the hindrance confronted, resulting in a number of methods being proposed for preserving customers' privacy. While these methods provide stringent privacy guarantees, only limited attention has been paid to their computational efficiency and performance quality. Under the paradigm of differential privacy, this paper initiates a systematic empirical study on quantifying the trade-off between privacy and optimality in centralized DR systems for maximizing cumulative customer utility. Aiming to elucidate the factors governing this trade-off, we analyze the cost of privacy in terms of the effect incurred on the objective value of the DR optimization problem when applying the employed privacy-preserving strategy based on Laplace mechanism. The theoretical results derived from the analysis are complemented with empirical findings, corroborated extensively by simulations on a 4-bus MG system with up to thousands of customers. By evaluating the impact of privacy, this pilot study serves DR practitioners when considering the social and economic implications of deploying privacy-preserving DR programs in practice. Moreover, it stimulates further research on exploring more efficient approaches with bounded performance guarantees for optimizing energy procurement of MGs without infringing the privacy of customers on demand side.

eess.SY↗

arXiv2016

Efficient Algorithm for Scalable Event-based Demand Response Management in Microgrids

Demand response management has become one of the key enabling technologies for smart grids. Motivated by the increasing demand response incentives offered by service operators, more customers are subscribing to various demand response programs. However, with growing customer participation, the problem of determining the optimal loads to be curtailed in a microgrid during contingencies within a feasible time frame becomes computationally hard. This paper proposes an efficient approximation algorithm for event-based demand response management in microgrids. In event-based management, it is important to curtail loads as fast as possible to maintain the stability of a microgrid during the islanded mode in a scalable manner. A simple greedy approach is presented that can rapidly determine a close-to-optimal load curtailment scheme to maximize the aggregate customer utility in milliseconds for a large number of customers. This paper further derives a novel theoretical guarantee of the gap between the proposed efficient algorithm and the optimal solution (that may be computationally hard to obtain). The performance of algorithm is corroborated extensively by simulations with up to thousands of customers. For the sake of practicality, the proposed event-based demand response management algorithm is applied to a feeder from the Canadian benchmark distribution system. The simulation results demonstrate that the proposed approach efficiently optimizes microgrid operation during islanded mode while maintaining appropriate voltage levels and network constrains.

math.OC↗