To improve the level of active traffic management,a short-term traffic flow prediction model is proposed by combining phase space reconstruction(PSR)and extreme gradient boosting(XGBoost)algorithms.Firstly,the traditi...To improve the level of active traffic management,a short-term traffic flow prediction model is proposed by combining phase space reconstruction(PSR)and extreme gradient boosting(XGBoost)algorithms.Firstly,the traditional data preprocessing method is improved.The new method uses hierarchical clustering to determine the traffic flow state and fills in missing and abnormal data according to different traffic flow states.Secondly,one-dimensional data are mapped into a multidimensional data matrix through PSR,and the time series complex network is used to verify the data reconstruction effect.Finally,the multidimensional data matrix is inputted into the XGBoost model to predict future traffic flow parameters.The experimental results show that the mean square error,average absolute error,and average absolute percentage error of the prediction results of the PSR-XGBoost model are 5.399%,1.632%,and 6.278%,respectively,and the required running time is 17.35 s.Compared with mathematical-statistical models and other machine learning models,the PSR-XGBoost model has clear advantages in multiple predictive indicators,proving its feasibility and superiority in short-term traffic flow prediction.展开更多
As an essential lifeline engineering system,water distribution network should provide enough water to maintain people's life after earthquake in addition to working under daily operation.However,the design of wate...As an essential lifeline engineering system,water distribution network should provide enough water to maintain people's life after earthquake in addition to working under daily operation.However,the design of water distribution network usually ignores the influence of earthquake,resulting in water stoppage in large area during many recent strong earthquakes.This study introduced a seismic design approach of water distribution network,i.e.,topology optimization design.With network topology as the optimization goal and seismic reliability as the constraint,a topology optimization model for designing water distribution network under earthquake is established.Meanwhile,two element investment importance indexes,a pipeline investment importance index and a diameter investment importance index,are introduced to evaluate the importance of pipelines in water distribution network.Then,four combinational optimization algorithms,a genetic algorithm,a simulated annealing genetic algorithm,an ant colony algorithm and a particle swarm algorithm,are introduced to solve this optimization model.Moreover,these optimization algorithms are used to optimize a network with 19 nodes and 27 pipelines.The optimization results of these algorithms are compared with each other.展开更多
基金The National Natural Science Foundation of China (No.71771019, 71871130, 71971125)the Science and Technology Special Project of Shandong Provincial Public Security Department (No. 37000000015900920210010001,37000000015900920210012001)。
文摘To improve the level of active traffic management,a short-term traffic flow prediction model is proposed by combining phase space reconstruction(PSR)and extreme gradient boosting(XGBoost)algorithms.Firstly,the traditional data preprocessing method is improved.The new method uses hierarchical clustering to determine the traffic flow state and fills in missing and abnormal data according to different traffic flow states.Secondly,one-dimensional data are mapped into a multidimensional data matrix through PSR,and the time series complex network is used to verify the data reconstruction effect.Finally,the multidimensional data matrix is inputted into the XGBoost model to predict future traffic flow parameters.The experimental results show that the mean square error,average absolute error,and average absolute percentage error of the prediction results of the PSR-XGBoost model are 5.399%,1.632%,and 6.278%,respectively,and the required running time is 17.35 s.Compared with mathematical-statistical models and other machine learning models,the PSR-XGBoost model has clear advantages in multiple predictive indicators,proving its feasibility and superiority in short-term traffic flow prediction.
基金supported by the Ministry of Science and Technology of China (Grant No. SLDRCE09-B-12)the Natural Science Funds for Young Scholars of China (Grant No.50808144)
文摘As an essential lifeline engineering system,water distribution network should provide enough water to maintain people's life after earthquake in addition to working under daily operation.However,the design of water distribution network usually ignores the influence of earthquake,resulting in water stoppage in large area during many recent strong earthquakes.This study introduced a seismic design approach of water distribution network,i.e.,topology optimization design.With network topology as the optimization goal and seismic reliability as the constraint,a topology optimization model for designing water distribution network under earthquake is established.Meanwhile,two element investment importance indexes,a pipeline investment importance index and a diameter investment importance index,are introduced to evaluate the importance of pipelines in water distribution network.Then,four combinational optimization algorithms,a genetic algorithm,a simulated annealing genetic algorithm,an ant colony algorithm and a particle swarm algorithm,are introduced to solve this optimization model.Moreover,these optimization algorithms are used to optimize a network with 19 nodes and 27 pipelines.The optimization results of these algorithms are compared with each other.
