arXiv subjects

Novella Bartolini

Publications and source records attributed to Novella Bartolini.

10 recordsLinked to original sources

arXiv2026

Spatio-Temporal Shifting to Reduce Carbon, Water, and Land-Use Footprints of Cloud Workloads

In this paper, we investigate the potential of spatial and temporal cloud workload shifting to reduce carbon, water, and land use footprints. Specifically, we perform a simulation study leveraging publicly available data on the cloud infrastructure of major providers (AWS and Azure) as well as real-world workload traces (big data analytics and FaaS) and grid mix data to consider two different scenarios. Our simulation results indicate that spatial shifting can substantially lower carbon, water, and land use footprints. In the FaaS applications, shifting the spatiotemporal workload achieves carbon savings of up to 85%, water savings of around 50%, and reductions in land use of up to 45%, all while optimizing for the respective factors. Mixed optimization yields results comparable to those of land use alone. For big data workloads, spatiotemporal shifting delivers reductions of up to 45% in carbon emissions, 40% in water consumption, and nearly 40% in land use when optimized for the respective factors. Temporal shifting also decreases the footprint, though to a lesser extent. When applied together, the two strategies yield the greatest overall reduction, driven mainly by spatial shifting with temporal adjustments providing an additional, incremental benefit. Sensitivity analysis demonstrates that such shifting is robust to prediction errors in grid mix data and to variations across different seasons.

cs.DC↗

arXiv2026

Robust Causal Discovery in Real-World Time Series with Power-Laws

Exploring causal relationships in stochastic time series is a challenging yet crucial task with a vast range of applications, including finance, economics, neuroscience, and climate science. Many algorithms for Causal Discovery (CD) have been proposed; however, they often exhibit a high sensitivity to noise, resulting in spurious causal inferences in real data. In this paper, we observe that the frequency spectra of many real-world time series follow a power-law distribution, notably due to an inherent self-organizing behavior. Leveraging this insight, we build a robust CD method based on the extraction of power-law spectral features that amplify genuine causal signals. Our method consistently outperforms state-of-the-art alternatives on both synthetic benchmarks and real-world datasets with known causal structures, demonstrating its robustness and practical relevance.

cs.LG↗

arXiv2026

High-Quality Synthetic Financial Time-Series using a GAN-Diffusion Framework

In recent years, financial institutions and firms have increasingly adopted synthetic data to address data scarcity and to generate counterfactual market scenarios. However, reproducing all the statistical properties of financial time series, commonly known as stylized facts, remains an open challenge for many existing general-purpose architectures. In this paper, we present a quality-aware generative framework that combines two classes of generative methods, demonstrating how their integration addresses existing limitations while enhancing the realism of synthetic data. Specifically, we first introduce CoMeTS-GAN (Correlated Multivariate Time Series GAN), a Conditional Generative Adversarial Network (C-GAN) designed to jointly generate mid-price and volume time-series for correlated stocks. We then show how our GAN architecture can be incorporated into state-of-the-art diffusion models to enhance the quality of generated correlation structures. Specifically, the GAN's Critic serves as a quality evaluation module that guides the diffusion process, enforcing learned correlation structures in the generated time-series. Our framework offers a lightweight and responsive solution for realistic stock market simulation, explicitly modeling inter-asset correlation structures. We experimentally validate our framework against leading generative architectures, showing that it more effectively captures the stylized facts of stock markets and models inter-asset correlations.

cs.LG↗

arXiv2025

Environmentally-Conscious Cloud Orchestration Considering Geo-Distributed Data Centers

This paper presents a theoretical discussion for environmentally-conscious job deployment and migration in cloud environments, aiming to minimize the environmental impact of resource provisioning while incorporating sustainability requirements. As the demand for sustainable cloud services grows, it is crucial for cloud customers to select data center operators based on sustainability metrics and to accurately report the ecological footprint of their services. To this end, we analyze sustainability reports and define comprehensive environmental impact profiles for data centers, incorporating key sustainability indicators. We formalize the problem as an optimization model, balancing multiple environmental factors while respecting user preferences. A simulative case study demonstrates the {potential} of our approach compared to baseline strategies that optimize for single sustainability factors.

cs.DC↗

arXiv2023

LOB-Based Deep Learning Models for Stock Price Trend Prediction: A Benchmark Study

The recent advancements in Deep Learning (DL) research have notably influenced the finance sector. We examine the robustness and generalizability of fifteen state-of-the-art DL models focusing on Stock Price Trend Prediction (SPTP) based on Limit Order Book (LOB) data. To carry out this study, we developed LOBCAST, an open-source framework that incorporates data preprocessing, DL model training, evaluation and profit analysis. Our extensive experiments reveal that all models exhibit a significant performance drop when exposed to new data, thereby raising questions about their real-world market applicability. Our work serves as a benchmark, illuminating the potential and the limitations of current approaches and providing insight for innovative solutions.

q-fin.TR↗

arXiv2021

Towards Realistic Market Simulations: a Generative Adversarial Networks Approach

Simulated environments are increasingly used by trading firms and investment banks to evaluate trading strategies before approaching real markets. Backtesting, a widely used approach, consists of simulating experimental strategies while replaying historical market scenarios. Unfortunately, this approach does not capture the market response to the experimental agents' actions. In contrast, multi-agent simulation presents a natural bottom-up approach to emulating agent interaction in financial markets. It allows to set up pools of traders with diverse strategies to mimic the financial market trader population, and test the performance of new experimental strategies. Since individual agent-level historical data is typically proprietary and not available for public use, it is difficult to calibrate multiple market agents to obtain the realism required for testing trading strategies. To addresses this challenge we propose a synthetic market generator based on Conditional Generative Adversarial Networks (CGANs) trained on real aggregate-level historical data. A CGAN-based "world" agent can generate meaningful orders in response to an experimental agent. We integrate our synthetic market generator into ABIDES, an open source simulator of financial markets. By means of extensive simulations we show that our proposal outperforms previous work in terms of stylized facts reflecting market responsiveness and realism.

cs.AI↗

arXiv2021

Static and Dynamic Failure Localization through Progressive Network Tomography

We aim at assessing the states of the nodes in a network by means of end-to-end monitoring paths. The contribution of this paper is twofold. First, we consider a static failure scenario. In this context, we aim at minimizing the number of probes to obtain failure identification. To face this problem, we propose a progressive approach to failure localization based on stochastic optimization, whose solution is the optimal sequence of monitoring paths to probe. We address the complexity of the problem by proposing a greedy strategy in two variants: one considers exact calculation of posterior probabilities of node failures, given the observation, whereas the other approximates these values by means of a novel failure centrality metric. Secondly, we adapt these two strategies to a dynamic failure scenario where nodes states can change throughout a monitoring period. By means of numerical experiments conducted on real network topologies, we demonstrate the practical applicability of our approach. Our performance evaluation evidences the superiority of our algorithms with respect to state of the art solutions based on classic Boolean Network Tomography as well as approaches based on sequential group testing.

cs.NI↗

arXiv2019

On Fundamental Bounds of Failure Identifiability by Boolean Network Tomography

Boolean network tomography is a powerful tool to infer the state (working/failed) of individual nodes from path-level measurements obtained by egde-nodes. We consider the problem of optimizing the capability of identifying network failures through the design of monitoring schemes. Finding an optimal solution is NP-hard and a large body of work has been devoted to heuristic approaches providing lower bounds. Unlike previous works, we provide upper bounds on the maximum number of identifiable nodes, given the number of monitoring paths and different constraints on the network topology, the routing scheme, and the maximum path length. These upper bounds represent a fundamental limit on identifiability of failures via Boolean network tomography. Our analysis provides insights on how to design topologies and related monitoring schemes to achieve the maximum identifiability under various network settings. Through analysis and experiments we demonstrate the tightness of the bounds and efficacy of the design insights for engineered as well as real networks.

cs.NI↗

arXiv2011

Sensor Activation and Radius Adaptation (SARA) in Heterogeneous Sensor Networks

In this paper we address the problem of prolonging the lifetime of wireless sensor networks (WSNs) deployed to monitor an area of interest. In this scenario, a helpful approach is to reduce coverage redundancy and therefore the energy expenditure due to coverage. We introduce the first algorithm which reduces coverage redundancy by means of Sensor Activation and sensing Radius Adaptation (SARA)in a general applicative scenario with two classes of devices: sensors that can adapt their sensing range (adjustable sensors) and sensors that cannot (fixed sensors). In particular, SARA activates only a subset of all the available sensors and reduces the sensing range of the adjustable sensors that have been activated. In doing so, SARA also takes possible heterogeneous coverage capabilities of sensors belonging to the same class into account. It specifically addresses device heterogeneity by modeling the coverage problem in the Laguerre geometry through Voronoi-Laguerre diagrams. SARA executes quickly and is guaranteed to terminate. It provides a configuration of the active set of sensors that lifetime and coverage requirements of demanding WSN applications, not met by current solutions. By means of extensive simulations we show that SARA achieves a network lifetime that is significantly superior to that obtained by previous algorithms in all the considered scenarios.

cs.NI↗

arXiv2009

Self-* overload control for distributed web systems

Unexpected increases in demand and most of all flash crowds are considered the bane of every web application as they may cause intolerable delays or even service unavailability. Proper quality of service policies must guarantee rapid reactivity and responsiveness even in such critical situations. Previous solutions fail to meet common performance requirements when the system has to face sudden and unpredictable surges of traffic. Indeed they often rely on a proper setting of key parameters which requires laborious manual tuning, preventing a fast adaptation of the control policies. We contribute an original Self-* Overload Control (SOC) policy. This allows the system to self-configure a dynamic constraint on the rate of admitted sessions in order to respect service level agreements and maximize the resource utilization at the same time. Our policy does not require any prior information on the incoming traffic or manual configuration of key parameters. We ran extensive simulations under a wide range of operating conditions, showing that SOC rapidly adapts to time varying traffic and self-optimizes the resource utilization. It admits as many new sessions as possible in observance of the agreements, even under intense workload variations. We compared our algorithm to previously proposed approaches highlighting a more stable behavior and a better performance.

cs.NI↗