High throughput computing based distributed genetic algorithm for building energy consumption optimization

A review on hybrid optimization algorithms to coalesce computational morphogenesis with interactive energy consumption forecasting

“…For example, Yang et al, [52] developed a web-based distributed high-through computation framework with parallel genetic algorithm modeling to reduce the computation time of simulation-based building energy optimization problems.…”

“…Past research that focus on computational morphogenesis optimization methods provided us with many interesting hybrid algorithms in which many different methods have been combined to obtain the best optimum solution reducing the computational time. Examples of hybrid algorithms especially developed for building energy performance and computational morphogenesis optimization problems can be found on the literature and are based on web-based parallel genetic algorithms [52], modified simulated annealing algorithms [53], genetic algorithms coupled with artificial neural networks [54] or multi-linear regression meta-models [55], etc.…”

ANN–GA smart appliance scheduling for optimised energy management in the domestic sector

“…The GA based optimisation algorithm needs to generate hundreds of results to find the global optimum solution. In this context, simulation tools are not effective as they require high power computing and parallelisation for the optimisation algorithm [23]. Hence, the aim is to generate the best performing ANN to be utilised instead of a simulation tool.…”

A computational framework for regional seismic simulation of buildings with multiple fidelity models

“…Many distributed computing platforms, such as BOINC [34] , Hadoop [35] and HTCondor [36] , are now available. This study employs HTCondor for implementation because HTCondor is open-source and supports GPUs for distributed computing [37][38] .…”