arXiv subjects

Alberto Leon-Garcia

Publications and source records attributed to Alberto Leon-Garcia.

At least 19 recordsLinked to original sources

arXiv2026

ARBITER: Guarded Agentic Control for SLO-Oriented Kubernetes Remediation

Maintaining service-level objectives (SLOs) on Kubernetes microservices remains difficult because autoscalers observe coarse resource metrics, recent SLO controllers often depend on custom telemetry, and unconstrained agentic operators cannot safely mutate production clusters. We present ARBITER, a guarded control plane for SLO-oriented Kubernetes remediation. ARBITER builds an OpenTelemetry-native causal resource graph, assembles bounded DiagnosisContext objects, and exposes a finite typed-action interface that separates planning from execution. The same interface supports deterministic planners and an LLM-backed planning harness, with deterministic schema checks, policy gates, resource/disruption budgets, approval, and bounded execution forming the safety substrate. We evaluate ARBITER on a 4-node Kubernetes cluster using DeathStarBench Social Network and Online Boutique. The evaluation tests two forms of SLO-oriented control that resource autoscaling alone does not provide: selecting the right remediation action and selecting the right downstream target. For bad-image deployment regressions, ARBITER selects rollback_canary in all ten CPU-burn and pure-latency runs; HPA either scales the faulty image or never triggers. For a downstream critical-path fault, the user-visible breach appears at the frontend, but trace evidence identifies home-timeline-service as the remediable bottleneck. Deterministic ARBITER and a live approval-gated Sonnet harness target that downstream service in every replicate, whereas HPA/resource-only control never does. Additional experiments cover guarded placement repair, Online Boutique portability, adversarial safety rejection, offline multi-model replay, and KWOK-based control-plane scale evidence. We release the controller, replay corpus, harnesses, safety tests, and figure artifacts: https://github.com/pooyan/arbiter.

cs.DC↗

arXiv2026

FAME: Failure-Aware Mixture-of-Experts for Message-Level Log Anomaly Detection

Production systems generate millions of log lines daily, yet most anomaly detectors operate at the session or window-level, flagging groups of lines rather than identifying the specific message responsible. This coarse granularity forces operators to inspect many routine lines per alert. Message-level detection offers finer granularity, but remains challenging. A single event template may correspond to both normal and anomalous messages, failures arise from heterogeneous subsystems, and line-level labeling at scale is impractical. Although large language models (LLMs) can reason over log semantics, applying them to every line is too costly for continuous monitoring. We present FAME (Failure-Aware Mixture-of-Experts), a label-efficient message-level mixture-of-experts framework that uses an LLM only once offline. We annotate at most K labeled lines per template to derive binary normal/anomaly indicators and representative examples. The LLM proposes a partition of templates into failure domains, and a certification step validates the proposal before training. FAME trains a lightweight router and domain experts that run on-premise and output anomaly predictions and failure-domain labels. On BGL, FAME achieves F1 = 98.16 at K = 100 reducing annotation effort by 76x and detects 97.7% of anomalies from unseen EventIDs. On Thunderbird, FAME reaches F1 = 99.95 with perfect recall.

cs.SE↗

arXiv2024

Yodel: A Layer 3.5 Name-Based Multicast Network Architecture For The Future Internet

Multicasting refers to the ability of transmitting data to multiple recipients without data sources needing to provide more than one copy of the data to the network. The network takes responsibility to route and deliver a copy of each data to every intended recipient. Multicasting has the potential to improve the network efficiency and performance (e.g., throughput and latency) through transferring fewer bits in communicating the same data to multiple recipients compared with unicast transmissions, reduce the amount of networking resources needed for communication, lower the network energy footprint, and alleviate the occurrence of congestion in the network. Over the past few decades, providing multicast services has been a real challenge for ISPs, especially to support home users and multi-domain network applications, leading to the emergence of complex application-level solutions. These solutions like Content Delivery and Peer-to-Peer networks take advantage of complex caching, routing, transport, and topology management systems which put heavy strains on the underlying Internet infrastructures to offer multicasting services. In reality, the main motivation behind the design of these systems is rather sharing content than offering efficient multicast services. In this paper, we propound Yodel, a name-based multicast network architecture that can provide multi-domain multicast services for current and future Internet applications. Compared to the wider array of other name-based network architectures with clean-slate infrastructure requirements, Yodel is designed to provide multicast services over the current Internet infrastructure. Hence, Yodel puts forward several design goals that distinguish it from other name-based network architectures with inherent multicast capabilities. This paper is prepared to discuss the Yodel architecture, its design goals, and architectural functions.

cs.NI↗

arXiv2024

Statistical and Machine Learning Models for Predicting Fire and Other Emergency Events

Emergency events in a city cause considerable economic loss to individuals, their families, and the community. Accurate and timely prediction of events can help the emergency fire and rescue services in preparing for and mitigating the consequences of emergency events. In this paper, we present a systematic development of predictive models for various types of emergency events in the City of Edmonton, Canada. We present methods for (i) data collection and dataset development; (ii) descriptive analysis of each event type and its characteristics at different spatiotemporal levels; (iii) feature analysis and selection based on correlation coefficient analysis and feature importance analysis; and (iv) development of prediction models for the likelihood of occurrence of each event type at different temporal and spatial resolutions. We analyze the association of event types with socioeconomic and demographic data at the neighborhood level, identify a set of predictors for each event type, and develop predictive models with negative binomial regression. We conduct evaluations at neighborhood and fire station service area levels. Our results show that the models perform well for most of the event types with acceptable prediction errors for weekly and monthly periods. The evaluation shows that the prediction accuracy is consistent at the level of the fire station, so the predictions can be used in management by fire rescue service departments for planning resource allocation for these time periods. We also examine the impact of the COVID-19 pandemic on the occurrence of events and on the accuracy of event predictor models. Our findings show that COVID-19 had a significant impact on the performance of the event prediction models.

cs.AI↗

arXiv2024

Intent Assurance using LLMs guided by Intent Drift

Intent-Based Networking (IBN) presents a paradigm shift for network management, by promising to align intents and business objectives with network operations--in an automated manner. However, its practical realization is challenging: 1) processing intents, i.e., translate, decompose and identify the logic to fulfill the intent, and 2) intent conformance, that is, considering dynamic networks, the logic should be adequately adapted to assure intents. To address the latter, intent assurance is tasked with continuous verification and validation, including taking the necessary actions to align the operational and target states. In this paper, we define an assurance framework that allows us to detect and act when intent drift occurs. To do so, we leverage AI-driven policies, generated by Large Language Models (LLMs) which can quickly learn the necessary in-context requirements, and assist with the fulfillment and assurance of intents.

cs.AI↗

arXiv2024

Threshold Policies with Tight Guarantees for Online Selection with Convex Costs

This paper provides threshold policies with tight guarantees for online selection with convex cost (OSCC). In OSCC, a seller wants to sell some asset to a sequence of buyers with the goal of maximizing her profit. The seller can produce additional units of the asset, but at non-decreasing marginal costs. At each time, a buyer arrives and offers a price. The seller must make an immediate and irrevocable decision in terms of whether to accept the offer and produce/sell one unit of the asset to this buyer. The goal is to develop an online algorithm that selects a subset of buyers to maximize the seller's profit, namely, the total selling revenue minus the total production cost. Our main result is the development of a class of simple threshold policies that are logistically simple and easy to implement, but have provable optimality guarantees among all deterministic algorithms. We also derive a lower bound on competitive ratios of randomized algorithms and prove that the competitive ratio of our threshold policy asymptotically converges to this lower bound when the total production output is sufficiently large. Our results generalize and unify various online search, pricing, and auction problems, and provide a new perspective on the impact of non-decreasing marginal costs on real-world online resource allocation problems.

cs.GT↗

arXiv2024

LLM-based policy generation for intent-based management of applications

Automated management requires decomposing high-level user requests, such as intents, to an abstraction that the system can understand and execute. This is challenging because even a simple intent requires performing a number of ordered steps. And the task of identifying and adapting these steps (as conditions change) requires a decomposition approach that cannot be exactly pre-defined beforehand. To tackle these challenges and support automated intent decomposition and execution, we explore the few-shot capability of Large Language Models (LLMs). We propose a pipeline that progressively decomposes intents by generating the required actions using a policy-based abstraction. This allows us to automate the policy execution by creating a closed control loop for the intent deployment. To do so, we generate and map the policies to APIs and form application management loops that perform the necessary monitoring, analysis, planning and execution. We evaluate our proposal with a use-case to fulfill and assure an application service chain of virtual network functions. Using our approach, we can generalize and generate the necessary steps to realize intents, thereby enabling intent automation for application management.

cs.DC↗

arXiv2023

Mechanism Design for Online Resource Allocation: A Unified Approach

This paper concerns the mechanism design for online resource allocation in a strategic setting. In this setting, a single supplier allocates capacity-limited resources to requests that arrive in a sequential and arbitrary manner. Each request is associated with an agent who may act selfishly to misreport the requirement and valuation of her request. The supplier charges payment from agents whose requests are satisfied, but incurs a load-dependent supply cost. The goal is to design an incentive compatible online mechanism, which determines not only the resource allocation of each request, but also the payment of each agent, so as to (approximately) maximize the social welfare (i.e., aggregate valuations minus supply cost). We study this problem under the framework of competitive analysis. The major contribution of this paper is the development of a unified approach that achieves the best-possible competitive ratios for setups with different supply costs. Specifically, we show that when there is no supply cost or the supply cost function is linear, our model is essentially a standard 0-1 knapsack problem, for which our approach achieves logarithmic competitive ratios that match the state-of-the-art (which is optimal). For the more challenging setup when the supply cost is strictly-convex, we provide online mechanisms, for the first time, that lead to the optimal competitive ratios as well. To the best of our knowledge, this is the first approach that unifies the characterization of optimal competitive ratios in online resource allocation for different setups including zero, linear and strictly-convex supply costs.

cs.GT↗

arXiv2023

Online Combinatorial Auctions for Resource Allocation with Supply Costs and Capacity Limits

We study a general online combinatorial auction problem in algorithmic mechanism design. A provider allocates multiple types of capacity-limited resources to customers that arrive in a sequential and arbitrary manner. Each customer has a private valuation function on bundles of resources that she can purchase (e.g., a combination of different resources such as CPU and RAM in cloud computing). The provider charges payment from customers who purchase a bundle of resources and incurs an increasing supply cost with respect to the totality of resources allocated. The goal is to maximize the social welfare, namely, the total valuation of customers for their purchased bundles, minus the total supply cost of the provider for all the resources that have been allocated. We adopt the competitive analysis framework and provide posted-price mechanisms with optimal competitive ratios. Our pricing mechanism is optimal in the sense that no other online algorithms can achieve a better competitive ratio. We validate the theoretic results via empirical studies of online resource allocation in cloud computing. Our numerical results demonstrate that the proposed pricing mechanism is competitive and robust against system uncertainties and outperforms existing benchmarks.

cs.GT↗

arXiv2022

Missing Data Estimation in Temporal Multilayer Position-aware Graph Neural Network (TMP-GNN)

GNNs have been proven to perform highly effective in various node-level, edge-level, and graph-level prediction tasks in several domains. Existing approaches mainly focus on static graphs. However, many graphs change over time with their edge may disappear, or node/edge attribute may alter from one time to the other. It is essential to consider such evolution in representation learning of nodes in time varying graphs. In this paper, we propose a Temporal Multi-layered Position-aware Graph Neural Network (TMP-GNN), a node embedding approach for dynamic graph that incorporates the interdependence of temporal relations into embedding computation. We evaluate the performance of TMP-GNN on two different representations of temporal multilayered graphs. The performance is assessed against the most popular GNNs on node-level prediction tasks. Then, we incorporate TMP-GNN into a deep learning framework to estimate missing data and compare the performance with their corresponding competent GNNs from our former experiment, and a baseline method. Experimental results on four real-world datasets yield up to 58% of lower ROC AUC for pairwise node classification task, and 96% of lower MAE in missing feature estimation, particularly for graphs with a relatively high number of nodes and lower mean degree of connectivity.

cs.LG↗

arXiv2021

A Deep Reinforcement Learning Approach for Fair Traffic Signal Control

Traffic signal control is one of the most effective methods of traffic management in urban areas. In recent years, traffic control methods based on deep reinforcement learning (DRL) have gained attention due to their ability to exploit real-time traffic data, which is often poorly used by the traditional hand-crafted methods. While most recent DRL-based methods have focused on maximizing the throughput or minimizing the average travel time of the vehicles, the fairness of the traffic signal controllers has often been neglected. This is particularly important as neglecting fairness can lead to situations where some vehicles experience extreme waiting times, or where the throughput of a particular traffic flow is highly impacted by the fluctuations of another conflicting flow at the intersection. In order to address these issues, we introduce two notions of fairness: delay-based and throughput-based fairness, which correspond to the two issues mentioned above. Furthermore, we propose two DRL-based traffic signal control methods for implementing these fairness notions, that can achieve a high throughput as well. We evaluate the performance of our proposed methods using three traffic arrival distributions, and find that our methods outperform the baselines in the tested scenarios.

cs.LG↗

arXiv2021

Toward Efficient Transfer Learning in 6G

6G networks will greatly expand the support for data-oriented, autonomous applications for over the top (OTT) and networking use cases. The success of these use cases will depend on the availability of big data sets which is not practical in many real scenarios due to the highly dynamic behavior of systems and the cost of data collection procedures. Transfer learning (TL) is a promising approach to deal with these challenges through the sharing of knowledge among diverse learning algorithms. with TL, the learning rate and learning accuracy can be considerably improved. However, there are implementation challenges to efficiently deploy and utilize TL in 6G. In this paper, we initiate this discussion by providing some performance metrics to measure the TL success. Then, we show how infrastructure, application, management, and training planes of 6G can be adapted to handle TL. We provide examples of TL in 6G and highlight the spatio-temporal features of data in 6G that can lead to efficient TL. By simulation results, we demonstrate how transferring the quantized neural network weights between two use cases can make a trade-off between overheads and performance and attain more efficient TL in 6G. We also provide a list of future research directions in TL for 6G.

cs.NI↗

arXiv2021

Queue-Learning: A Reinforcement Learning Approach for Providing Quality of Service

End-to-end delay is a critical attribute of quality of service (QoS) in application domains such as cloud computing and computer networks. This metric is particularly important in tandem service systems, where the end-to-end service is provided through a chain of services. Service-rate control is a common mechanism for providing QoS guarantees in service systems. In this paper, we introduce a reinforcement learning-based (RL-based) service-rate controller that provides probabilistic upper-bounds on the end-to-end delay of the system, while preventing the overuse of service resources. In order to have a general framework, we use queueing theory to model the service systems. However, we adopt an RL-based approach to avoid the limitations of queueing-theoretic methods. In particular, we use Deep Deterministic Policy Gradient (DDPG) to learn the service rates (action) as a function of the queue lengths (state) in tandem service systems. In contrast to existing RL-based methods that quantify their performance by the achieved overall reward, which could be hard to interpret or even misleading, our proposed controller provides explicit probabilistic guarantees on the end-to-end delay of the system. The evaluations are presented for a tandem queueing system with non-exponential inter-arrival and service times, the results of which validate our controller's capability in meeting QoS constraints.

cs.LG↗

arXiv2021

Estimation of Missing Data in Intelligent Transportation System

Missing data is a challenge in many applications, including intelligent transportation systems (ITS). In this paper, we study traffic speed and travel time estimations in ITS, where portions of the collected data are missing due to sensor instability and communication errors at collection points. These practical issues can be remediated by missing data analysis, which are mainly categorized as either statistical or machine learning(ML)-based approaches. Statistical methods require the prior probability distribution of the data which is unknown in our application. Therefore, we focus on an ML-based approach, Multi-Directional Recurrent Neural Network (M-RNN). M-RNN utilizes both temporal and spatial characteristics of the data. We evaluate the effectiveness of this approach on a TomTom dataset containing spatio-temporal measurements of average vehicle speed and travel time in the Greater Toronto Area (GTA). We evaluate the method under various conditions, where the results demonstrate that M-RNN outperforms existing solutions,e.g., spline interpolation and matrix completion, by up to 58% decreases in Root Mean Square Error (RMSE).

cs.LG↗

arXiv2020

Reinforcement Learning-based Admission Control in Delay-sensitive Service Systems

Ensuring quality of service (QoS) guarantees in service systems is a challenging task, particularly when the system is composed of more fine-grained services, such as service function chains. An important QoS metric in service systems is the end-to-end delay, which becomes even more important in delay-sensitive applications, where the jobs must be completed within a time deadline. Admission control is one way of providing end-to-end delay guarantee, where the controller accepts a job only if it has a high probability of meeting the deadline. In this paper, we propose a reinforcement learning-based admission controller that guarantees a probabilistic upper-bound on the end-to-end delay of the service system, while minimizes the probability of unnecessary rejections. Our controller only uses the queue length information of the network and requires no knowledge about the network topology or system parameters. Since long-term performance metrics are of great importance in service systems, we take an average-reward reinforcement learning approach, which is well suited to infinite horizon problems. Our evaluations verify that the proposed RL-based admission controller is capable of providing probabilistic bounds on the end-to-end delay of the network, without using system model information.

cs.PF↗

arXiv2020

Probabilistic Bounds on the End-to-End Delay of Service Function Chains using Deep MDN

Ensuring the conformance of a service system's end-to-end delay to service level agreement (SLA) constraints is a challenging task that requires statistical measures beyond the average delay. In this paper, we study the real-time prediction of the end-to-end delay distribution in systems with composite services such as service function chains. In order to have a general framework, we use queueing theory to model service systems, while also adopting a statistical learning approach to avoid the limitations of queueing-theoretic methods such as stationarity assumptions or other approximations that are often used to make the analysis mathematically tractable. Specifically, we use deep mixture density networks (MDN) to predict the end-to-end distribution of the delay given the network's state. As a result, our method is sufficiently general to be applied in different contexts and applications. Our evaluations show a good match between the learned distributions and the simulations, which suggest that the proposed method is a good candidate for providing probabilistic bounds on the end-to-end delay of more complex systems where simulations or theoretical methods are not applicable.

cs.PF↗

arXiv2020

On the Robustness of Cooperative Multi-Agent Reinforcement Learning

In cooperative multi-agent reinforcement learning (c-MARL), agents learn to cooperatively take actions as a team to maximize a total team reward. We analyze the robustness of c-MARL to adversaries capable of attacking one of the agents on a team. Through the ability to manipulate this agent's observations, the adversary seeks to decrease the total team reward. Attacking c-MARL is challenging for three reasons: first, it is difficult to estimate team rewards or how they are impacted by an agent mispredicting; second, models are non-differentiable; and third, the feature space is low-dimensional. Thus, we introduce a novel attack. The attacker first trains a policy network with reinforcement learning to find a wrong action it should encourage the victim agent to take. Then, the adversary uses targeted adversarial examples to force the victim to take this action. Our results on the StartCraft II multi-agent benchmark demonstrate that c-MARL teams are highly vulnerable to perturbations applied to one of their agent's observations. By attacking a single agent, our attack method has highly negative impact on the overall team reward, reducing it from 20 to 9.4. This results in the team's winning rate to go down from 98.9% to 0%.

cs.LG↗

arXiv2019

Real-Time Prediction of Delay Distribution in Service Systems using Mixture Density Networks

Motivated by interest in providing more efficient services in customer service systems, we use statistical learning methods and delay history information to predict the conditional distribution of the customers' waiting times in queueing systems. From the predicted distributions, descriptive statistics of the system such as the mean, variance and percentiles of the waiting times can be obtained, which can be used for delay announcements, SLA conformance and better system management. We model the conditional distributions by mixtures of Gaussians, parameters of which can be estimated using Mixture Density Networks. The evaluations show that exploiting more delay history information can result in much more accurate predictions under realistic time-varying arrival assumptions.

cs.PF↗