Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2501.12247

Plastic computing, the cloud continuum journey beyond infinity

Xavi Masip-Bruin·Jordi Garcia·Adrian Asensio·Francesco DAndria·Admela Jukan·Shahrok Daijavad·Panos Trakadas
View original source ↗Read source document ↗Export metadata ↓

Abstract

The ever increasing challenges introduced by the diversity of current and envisioned network technologies and IT infrastructure draw a highly distributed and heterogeneous topology where innovative services must be optimally deployed to guarantee maximum level of quality for users. Indeed, paradigms such as the cloud continuum, bringing together edge and cloud computing, along with the new opportunities coming out by considering non-terrestrial networks connecting future 6G ecosystems, all with no doubt facilitate the development of innovative services in many different areas and verticals. However, considering the intensive data and quality requirements demanded by these services, the distribution of the execution tasks must be optimally designed. On the infrastructure side, several initiatives are already active aimed at providing a Meta-OS that may seamlessly manage the different actors (services, infrastructure and users) playing under this paradigm. However, several aspects remain yet limited, particularly when referring to the mapping of resources into services, where innovative technologies based on bidirectional coordination and modeling may be pivotal for an optimal performance. In addition, the upcoming demands coming from the adoption of network technologies easing users connection with high levels of quality, such as 6G, as well the study of NTN open up the traditional cloud continuum to include also satellites that may extend the cloud paradigm further than ever considered. This paper shows a seed work toward an extendable paradigm so called as plastic computing whose main objective is to optimize service performance and users satisfaction, through considering a bidirectional strategy, easily extendable to adopt novel network and IT technologies and paradigms. Finally, two examples are briefly introduced to highlight the potential benefits of the plastic computing adoption

Explore related subjects

cs.ET

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Xavi Masip-Bruin, Jordi Garcia, Adrian Asensio, Francesco DAndria, Admela Jukan, Shahrok Daijavad, Panos Trakadas. 2025-01-21. Plastic computing, the cloud continuum journey beyond infinity. https://arxiv.org/abs/2501.12247

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Whole-Blood Boundary Analysis of BioFET-Based ctDNA Detection for Intravascular Sensing in Intrabody Nanonetworks

Liquid biopsy can detect tumor-derived biomarkers such as circulating tumor DNA (ctDNA), but ultra-low-fraction assays remain costly, slow, and difficult to scale. This motivates interest in intravascular in vivo sensing in the context of intrabody nanonetworks, where nanosensors could support local biomarker monitoring. BioFET-based nanosensors are relevant here because they are label-free, highly miniaturizable, and have shown strong ctDNA sensitivity in controlled media. We examine whether this sensitivity still yields reliable ctDNA detection in whole blood using a reduced-order stochastic simulation model that links operating-point selection, Debye-screened charge transduction, stochastic finite-capacity binding, nonspecific adsorption, background fluctuations, and intrinsic electronic noise to blank-threshold detection. Monte Carlo evaluation with physiologically grounded parameters shows that short Debye length and several-nanometer charge-to-channel separation attenuate the current shift, while low-frequency noise and background fluctuations reduce the margin between target-present and blank responses. Under the tested quasi-static charge-gating regime, the simulated current shifts do not reliably exceed the blank-derived threshold at low ctDNA concentrations. The model therefore provides a whole-blood boundary analysis that identifies which interface configurations and operating conditions most strongly limit reliable BioFET-based intravascular ctDNA detection.

cs.ET↗
arXiv2026

Beyond HBM-on-GPU: Thermal Design Envelope for 3D Volumetric DRAM-on-GPU Integration

The scaling of GPUs for AI and HPC workloads is increasingly constrained by the capacity, bandwidth, and thermal limits of both 2.5D HBM-GPU and direct-stacked 3D HBM-on-GPU integration. This work establishes the thermal design envelope for 3D volumetric DRAM-on-GPU integration, in which vertically oriented DRAM dies and interleaved cooling cavities reshape heat flow and memory interfacing above the GPU. Using a package-level thermal model anchored to a consistent HBM-on-GPU baseline and driven by a realistic reticle-scale non-uniform GPU power map, we quantify the key parameters governing thermal feasibility. Stack height is the dominant limiter of peak temperature, while cooling-cavity conductivity shifts the feasible region, and mold insertion and stack orientation further modulate thermal behavior. A distributed memory-controller and network-on-chip tier introduces only a moderate thermal penalty. Although die-level parallelism increases bandwidth, the reduction in simulated training time saturates once execution becomes compute-bound. These results define a bounded co-design space across bandwidth, capacity, and thermal constraints for 3D volumetric DRAM-on-GPU integration.

cs.ET↗
arXiv2026

Droop-Aware Foundation Model Power Flow

This paper develops a droop-aware extension of the GridFM power systems foundation model, embedding droop gains and frequency/voltage deadband parameters as per-bus node features to enable control-aware AC power-flow analysis. Existing power-flow datasets encode only static electrical features, conflating operating points from qualitatively different control regimes; this work resolves that gap by exposing droop and deadband parameters as structured node features, with deadband discontinuities handled through a smooth tanh approximation that preserves solver differentiability. A transformer-based graph neural network is pre-trained on masked reconstruction and fine-tuned on the resulting control-aware datasets. The framework is validated against PSCAD electromagnetic-transient simulations on a two-bus system (0.11% maximum steady-state error) and cross-validated against an independent PyPower droop solver on the IEEE 24-bus RTS. On the 24-bus system the surrogate attains R2 = 0.9996 for active generation and 0.0015 p.u. voltage-magnitude RMSE; scalability is confirmed on the IEEE 300-bus system (0.0036 p.u. RMSE, R2 = 0.9841 for voltage magnitude across 299,700 predictions). A three-mode control study further shows that the deadband widens the control-error distribution while leaving total droop compensation unchanged, establishing deadband width as an actionable node-level design feature.

cs.ET↗