This paper proposes a new metaheuristic global optimizationalgorithm inspired by wildebeestherding behavior called wildebeestherdoptimization (WHO) algorithm. WHO algorithm mimics the way nomadic wildebeestherds ...
详细信息
This paper proposes a new metaheuristic global optimizationalgorithm inspired by wildebeestherding behavior called wildebeestherdoptimization (WHO) algorithm. WHO algorithm mimics the way nomadic wildebeestherds search vast areas of grasslands efficiently for regions of high food density. The WHO algorithm models five principal wildebeest behaviors: firstly wildebeests have limited eyesight and can only search for food locally, secondly wildebeests stick to the herd to escape predators, thirdly wildebeestherd as a whole migrates to regions of high food availability based on historical knowledge of annual grass growth rates and rainfall patterns, fourthly wildebeests move out of crowded overgrazed regions and finally wildebeests move to avoid starvation. The WHO algorithm is compared to Physics inspired, Swarm based, Biologically inspired and Evolution inspired global optimizationalgorithms on an extended test suite of benchmark optimization problems including rotated, shifted, noisy and high dimensional problems. Extensive simulation results indicate that the WHO algorithm proposed in this paper significantly outperforms state-of-the-art popular metaheuristic optimizationalgorithms like Particle Swarm optimizationalgorithm (PSO), Genetic algorithm (GA), Gravitational Search algorithm (GSA), Artificial Bee Colony algorithm (ABC) and Simulated Annealing (SA) on shifted, high dimensional and large search range problems.
In this paper, an optimized model based on Convolutional neural network (CNN) models is proposed for transport energy forecasting in Republic of China (Taiwan). This study employs various selfreliant parameters includ...
详细信息
In this paper, an optimized model based on Convolutional neural network (CNN) models is proposed for transport energy forecasting in Republic of China (Taiwan). This study employs various selfreliant parameters including individual, gross domestic product, vehicle registrations' number, value of passenger transport, and oil price for modeling. To provide an optimized result of CNN, it is combined with newly defined wildebeest herd optimization algorithm and the model is called WHO/CNN. The model results are compared with multiple regression model and the basic CNN to show its higher efficiency in prediction of the transport energy data. Simulations are compared based on MTOE as well as R-2 to indicate the superiority of the suggested model. Final results show that based on the prediction, however, the demand of transport energy in Taiwan will not increment excessive, being about 37.2 MTOE in 2020 while gross domestic product increasing at the time of the same duration is almost high. The predicted outcomes are in accordance to ROC's green growth strategy, which needs CO2 reduction gas as it is feasible. However, there is minor growing of demand prediction of the transport energy, ROC requires to continue the CO2 emission decreasing. (C) 2020 The Author(s). Published by Elsevier Ltd.
暂无评论