Open AccessAn Approach Inspired by Simulation Points to Accelerate Smart Cities Simulations
Author(s) -
Francisco Wallison Rocha,
Emílio Francesquini,
Daniel Cordeiro
Publication year - 2021
Language(s) - English
Resource type - Conference proceedings
DOI - 10.5753/eradsp.2021.16703
Subject(s) - computer science , cluster (spacecraft) , series (stratigraphy) , scale (ratio) , standard deviation , data mining , simulation , statistics , mathematics , paleontology , physics , quantum mechanics , biology , programming language
Approaches using simulations are of great value for smart cities research. However, city-scale simulators can be both processing and memory-intensive, and hard to scale. To speed up these simulations and to allow executing larger scenarios, this work presents an approach based on an technique named Simpoint to estimate the result of new simulations using previous simulations. This technique aims to identify and cluster recurring patterns during a simulation. Then, unique representatives of each cluster are selected and their simulation is used to estimate the simulation results of the remaining cluster elements. The experimental results for our estimates are promising.On a dataset with 16,993 time series, our technique was able to estimate the original series with an average error of 1.60979e-11 and standard deviation of 9.18228e-11.