arXiv subjects

Adamantia Stamou

Publications and source records attributed to Adamantia Stamou.

5 recordsLinked to original sources

arXiv2026

A Game-Theoretic Framework for Incentive-Compatible AI training Under Renewable-Energy Constraints

As artificial intelligence systems increasingly rely on distributed and collaborative training, the energy footprint of these processes becomes a shared responsibility. Modern AI training often unfolds across heterogeneous compute nodes-ranging from cloud clusters to edge devices-whose energy availability is spatially and temporally variable. At the same time, renewable energy grids experience growing levels of excess generation, creating opportunities to align computational workloads with low-carbon energy supply. In this work, we develop a game-theoretic model of carbon-aware AI training in which autonomous agents strategically choose whether to participate and how intensively to train under limited renewable energy availability. Each agent balances diminishing learning returns, rewards for remaining within green-energy budgets, and penalties for grid consumption. While our framework applies broadly to distributed AI training, we examine Federated Learning as a representative case study due to its decentralized structure and flexible scheduling. We analyze equilibrium existence, efficiency, and adaptive dynamics, and provide simulation evidence that appropriately designed incentives can eliminate grid-based energy usage while preserving model performance. Our findings demonstrate how incentive-compatible training mechanisms can enhance energy efficiency and sharply reduce carbon emissions under renewable-energy constraints.

cs.ET↗

arXiv2026

Greening AI Inference with Accuracy and Latency-aware User Incentives

The widespread use of AI services has raised concerns for its environmental sustainability, towards which recent studies have identified carbon emissions of AI inference as the major contributor. This paper introduces a framework for designing AI inference incentives based on the users' valuation for inference quality and latency, together with their environmental consciousness, while accounting for the tradeoff between carbon emissions and the two QoE parameters. Our approach can accommodate different tradeoffs, that depend on the size and complexity of the AI models and the allocation of resources to serve inference requests. The incentives can be offered through a practical two-tier service subscription that offers users a discount in exchange for reduced carbon emissions. The discounted service option gives the AI provider the flexibility to serve some percentage of inference requests at a lower quality and higher latency during periods of high carbon intensity.

cs.LG↗

arXiv2026

Incentivising green video streaming through a 2-tier subscription model with carbon-aware rewards

We investigate incentives for reducing the carbon emissions of video streaming that depend on the energy consumption of segments in the end-to-end video delivery path, the carbon intensity, and the user type, i.e., quality-sensitive and green or environmentally conscious users. The incentives can be offered through a practical 2-tier subscription model with a discount and carbon rewards, which gives providers the flexibility to reduce the quality for up to a maximum percentage of videos within a time period, such as one month. The key features of our approach are i) it is preferable to offer subscriptions where the reduced-quality tier is set one resolution level below the resolution required for maximum user satisfaction; ii) when a video is streamed from a local data center, the maximum percentage of videos streamed at a lower quality depends solely on the carbon intensity and the average intensity cap, whereas the incentives also depend on the users' level of environmental consciousness; iii) when a video can be streamed from a local or a remote data center with different carbon intensities, the maximum percentage of videos streamed at lower quality and the incentives depend on the relative carbon intensity and energy consumption at the data centers, and the additional network energy costs from the remote data center.

cs.NI↗

arXiv2026

Optimal Energy-Aware Service Management in Future Networks with a Gamified Incentives Mechanism

As energy demands surge across ICT infrastructures, service providers must engage users in sustainable practices while maintaining the Quality of Experience (QoE) at acceptable levels. In this paper, we introduce such an approach, leveraging gamified incentives and a model for user's acceptance on incentives, thus encouraging energy-efficient behaviors such as adaptive bitrate streaming. Each user is characterized by an environmental sensitivity factor and a private incentive threshold, shaping probabilistic responses to energy-saving offers. A serious-game mechanism based on positive behavioral reinforcement and rewards of the users, due to their inclusion in top-K and bottom-M rankings, fosters peer comparison and competition, thus transforming passive acceptance into active engagement. Moreover, within a Stackelberg game formulation, the video streaming service provider--acting as the strategic leader--optimizes both incentive levels and game parameters to achieve network-wide energy and traffic reductions, while adhering to budgetary constraints. This structured approach empowers providers with proactive, application-level control over energy consumption, offering them measurable benefits such as reduced high-bitrate traffic and increased participation in energy-saving behaviors, while also considering user satisfaction. The results of our simulations show that indeed gamification boosts significantly user participation and energy savings provided that the incentive and game parameters are chosen optimally.

cs.ET↗

arXiv2026

User Acceptance Model for Smart Incentives in Sustainable Video Streaming towards 6G

The rapid growth of 5G video streaming is intensifying energy consumption across access, core, and data-center networks, underscoring the critical need for energy and carbon-efficient solutions. While reducing streaming bitrates improves energy efficiency, its success hinges on user acceptance--particularly when lower bitrates may be perceived as reduced quality of experience (QoE). Therefore, there is a need to develop transparent, user-centric incentive models that balance sustainability with perceived value. We propose a user-acceptance model that combines diverse environmental awareness, personalized responsiveness to incentives, and varying levels of altruism into a unified probabilistic framework. The model incorporates dynamic, individualized incentives that adapt over time. We further enhance the framework by incorporating (i) social well-being as a motivator for altruistic choices, (ii) provider-driven education strategies that gradually adjust user acceptance thresholds, and (iii) data-driven learning of user traits from historical offer--response interactions. Extensive synthetic-data experiments reveal the trade-offs between provider cost and network flexibility, showing that personalized incentives and gradual behavioral adaptation can advance sustainability targets without compromising stakeholder requirements.

cs.ET↗