English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

The Cloud paradigm is at a critical point in which the existingenergy-efficiency techniques are reaching a plateau, while the computingresources demand at Data Center facilities continues to increase exponentially.The main challenge in achieving a global energy efficiency strategy based onArtificial Intelligence is that we need massive amounts of data to feed thealgorithms. This paper proposes a time-series data augmentation methodologybased on synthetic scenario forecasting within the Data Center. For thispurpose, we will implement a powerful generative algorithm: GenerativeAdversarial Networks (GANs). Specifically, our work combines the disciplines ofGAN-based data augmentation and scenario forecasting, filling the gap in thegeneration of synthetic data in DCs. Furthermore, we propose a methodology toincrease the variability and heterogeneity of the generated data by introducingon-demand anomalies without additional effort or expert knowledge. We alsosuggest the use of Kullback-Leibler Divergence and Mean Squared Error as newmetrics in the validation of synthetic time series generation, as they providea better overall comparison of multivariate data distributions. We validate ourapproach using real data collected in an operating Data Center, successfullygenerating synthetic data helpful for prediction and optimization models. Ourresearch will help optimize the energy consumed in Data Centers, although theproposed methodology can be employed in any similar time-series-like problem.

Data augmentation through multivariate scenario forecasting in Data Centers using Generative Adversarial Networks