Distributed Analytics in Smart Grids with Edge Computing and Computational Intelligence

Published: Dec. 19, 2023

Conventional methods like classification or clustering have limits when it comes to handling the complex task for dispersed data mining across heterogeneous sources and divergent formats. This is especially true in scenarios where stochastic models mathematical formulas may not be feasible. Data centralization a prevalent trend that exacerbates problems including communication channel congestion privacy difficulties related sensitive flows. In order overcome these obstacles, this paper presents Distributed Academic Engine (DAE), an adaptive edge-based scattered analytic engine designed distributed networks. The DAE routinely breaks down divides computations need from multiple among nodes are already place, enabling sharing of partial results without disclosing original data. To get full expression output, master node combines results. decomposed processing jobs using three computational intelligence techniques: genetic algorithm, algorithm evolution control, particle swarm optimization. method's effectiveness illustrated with case study on smart grid KPI identification, which shows noteworthy (over 91%) decrease messages over conventional approaches. demonstrates how well suggested method works reduce mining.

Language: Английский

Serverless Data Pipelines for IoT Data Analytics: A Cloud Vendors Perspective and Solutions

Springer eBooks, Journal Year: 2022, Volume and Issue: unknown, P. 107 - 132

Published: Sept. 22, 2022

Language: Английский