The electricity-gas transformation problem and related intrinsic mechanisms are considered.First,existing schemes for the optimization of electricity-gas integrated energy systems are analyzed through consideration of...The electricity-gas transformation problem and related intrinsic mechanisms are considered.First,existing schemes for the optimization of electricity-gas integrated energy systems are analyzed through consideration of the relevant literature,and an Electricity Hub(EH)for electricity-gas coupling is proposed.Then,the distribution mechanism in the circuit of the considered electricity-gas integrated system is analyzed.Afterward,a mathematical model for the natural gas pipeline is elaborated according to the power relationship,a node power flow calculation method,and security requirements.Next,the coupling relationship between them is implemented,and dedicated simulations are carried out.Through experimental data,it is found that after 79 data iterations,the optimization results of power generation and gas purchase cost in the new system converge to$54,936 in total,which is consistent with the data obtained by an existing centralized optimization scheme.However,the new proposed optimization scheme is found to be more flexible and convenient.展开更多
Traffic congestion is widely distributed around a network. Generally, to analyze traffic congestion, static traffic capacity is adopted. But dynamic characteristics must be studied because congestion is a dynamic proc...Traffic congestion is widely distributed around a network. Generally, to analyze traffic congestion, static traffic capacity is adopted. But dynamic characteristics must be studied because congestion is a dynamic process. A Dynamic Traffic Assignment modeling fundamental combined with an urban congestion analysis method is studied in this paper. Three methods are based on congestion analysis, and the stochastic user optimal DTA models are especially considered. Correspondingly, a dynamic system optimal model is suggested for responding congestion countermeasures and an ideal user optimal model for predicted congestion countermeasure respectively.展开更多
The control problem of trajectory based path following for passenger vehicles is studied. Comprehensive nonlinear vehicle model is utilized for simulation vehicle response during various maneuvers in MATLAB/Simulink. ...The control problem of trajectory based path following for passenger vehicles is studied. Comprehensive nonlinear vehicle model is utilized for simulation vehicle response during various maneuvers in MATLAB/Simulink. In order to follow desired path, a driver model is developed to enhance closed loop driver/vehicle model. Then, linear quadratic regulator(LQR) controller is developed which regulates direct yaw moment and corrective steering angle on wheels. Particle swam optimization(PSO) method is utilized to optimize the LQR controller for various dynamic conditions. Simulation results indicate that, over various maneuvers, side slip angle and lateral acceleration can be reduced by 10% and 15%, respectively, which sustain the vehicle stable. Also, anti-lock brake system is designed for longitudinal dynamics of vehicle to achieve desired slip during braking and accelerating. Proposed comprehensive controller demonstrates that vehicle steerability can increase by about 15% during severe braking by preventing wheel from locking and reducing stopping distance.展开更多
Buildings are a major energy consumer and carbon emitter,therefore it is important to improve building energy efficiency to achieve our sustainable development goal.Deep reinforcement learning(DRL),as an advanced buil...Buildings are a major energy consumer and carbon emitter,therefore it is important to improve building energy efficiency to achieve our sustainable development goal.Deep reinforcement learning(DRL),as an advanced building control method,demonstrates great potential for energy efficiency optimization and improved occupant comfort.However,the performance of DRL is highly sensitive to hyper-parameters,and selecting inappropriate hyper-parameters may lead to unstable learning or even failure.This study aims to investigate the design and application of DRL in building energy system control,with a specific focus on improving the performance of DRL controllers through hyper-parameter optimization(HPO)algorithms.It also aims to provide quantitative evaluation and adaptive validation of these optimized controllers.Two widely used algorithms,deep deterministic policy gradient(DDPG)and soft actor-critic(SAC),are used in the study and their performance is evaluated in different building environments based on the BOPTEST virtual testbed.One of the focuses of the study is to compare various HPO techniques,including tree-structured Parzen estimator(TPE),covariance matrix adaptation evolution strategy(CMA-ES),and combinatorial optimization methods,to determine the efficacy of different hyper-parameter optimization methods for DRL.The study enhances HPO efficiency through parallel computation and conducts a comprehensive quantitative assessment of the optimized DRL controllers,considering factors such as reduced energy consumption and improved comfort.The results show that the HPO algorithms significantly improve the performance of the DDPG and SAC controllers.A reduction of 56.94%and 68.74%in thermal discomfort is achieved,respectively.Additionally,the study demonstrates the applicability of the HPO-based approach for enhancing DRL controller performance across diverse building environments,providing valuable insights for the design and optimization of building DRL controllers.展开更多
文摘The electricity-gas transformation problem and related intrinsic mechanisms are considered.First,existing schemes for the optimization of electricity-gas integrated energy systems are analyzed through consideration of the relevant literature,and an Electricity Hub(EH)for electricity-gas coupling is proposed.Then,the distribution mechanism in the circuit of the considered electricity-gas integrated system is analyzed.Afterward,a mathematical model for the natural gas pipeline is elaborated according to the power relationship,a node power flow calculation method,and security requirements.Next,the coupling relationship between them is implemented,and dedicated simulations are carried out.Through experimental data,it is found that after 79 data iterations,the optimization results of power generation and gas purchase cost in the new system converge to$54,936 in total,which is consistent with the data obtained by an existing centralized optimization scheme.However,the new proposed optimization scheme is found to be more flexible and convenient.
文摘Traffic congestion is widely distributed around a network. Generally, to analyze traffic congestion, static traffic capacity is adopted. But dynamic characteristics must be studied because congestion is a dynamic process. A Dynamic Traffic Assignment modeling fundamental combined with an urban congestion analysis method is studied in this paper. Three methods are based on congestion analysis, and the stochastic user optimal DTA models are especially considered. Correspondingly, a dynamic system optimal model is suggested for responding congestion countermeasures and an ideal user optimal model for predicted congestion countermeasure respectively.
文摘The control problem of trajectory based path following for passenger vehicles is studied. Comprehensive nonlinear vehicle model is utilized for simulation vehicle response during various maneuvers in MATLAB/Simulink. In order to follow desired path, a driver model is developed to enhance closed loop driver/vehicle model. Then, linear quadratic regulator(LQR) controller is developed which regulates direct yaw moment and corrective steering angle on wheels. Particle swam optimization(PSO) method is utilized to optimize the LQR controller for various dynamic conditions. Simulation results indicate that, over various maneuvers, side slip angle and lateral acceleration can be reduced by 10% and 15%, respectively, which sustain the vehicle stable. Also, anti-lock brake system is designed for longitudinal dynamics of vehicle to achieve desired slip during braking and accelerating. Proposed comprehensive controller demonstrates that vehicle steerability can increase by about 15% during severe braking by preventing wheel from locking and reducing stopping distance.
基金supported by the National Natural Science Foundation of China(No.72371072)Jiangsu Association for Science&Technology Youth Science&Technology Talents Lifting Project(No.JSTJ-2023-JS001).
文摘Buildings are a major energy consumer and carbon emitter,therefore it is important to improve building energy efficiency to achieve our sustainable development goal.Deep reinforcement learning(DRL),as an advanced building control method,demonstrates great potential for energy efficiency optimization and improved occupant comfort.However,the performance of DRL is highly sensitive to hyper-parameters,and selecting inappropriate hyper-parameters may lead to unstable learning or even failure.This study aims to investigate the design and application of DRL in building energy system control,with a specific focus on improving the performance of DRL controllers through hyper-parameter optimization(HPO)algorithms.It also aims to provide quantitative evaluation and adaptive validation of these optimized controllers.Two widely used algorithms,deep deterministic policy gradient(DDPG)and soft actor-critic(SAC),are used in the study and their performance is evaluated in different building environments based on the BOPTEST virtual testbed.One of the focuses of the study is to compare various HPO techniques,including tree-structured Parzen estimator(TPE),covariance matrix adaptation evolution strategy(CMA-ES),and combinatorial optimization methods,to determine the efficacy of different hyper-parameter optimization methods for DRL.The study enhances HPO efficiency through parallel computation and conducts a comprehensive quantitative assessment of the optimized DRL controllers,considering factors such as reduced energy consumption and improved comfort.The results show that the HPO algorithms significantly improve the performance of the DDPG and SAC controllers.A reduction of 56.94%and 68.74%in thermal discomfort is achieved,respectively.Additionally,the study demonstrates the applicability of the HPO-based approach for enhancing DRL controller performance across diverse building environments,providing valuable insights for the design and optimization of building DRL controllers.
