Multi-Objective Optimal Dispatching Of Energy Internet In Consideration Of Electric Vehicles

Energy Internet is a network of information and energy integration formed on the basis of the Internet,and is a new form of energy industry development.In view of the limited fossil energy reserves and increasingly severe environmental pollution,sustainable development is facing severe challenges,and the development of clean and renewable energy utilization technology is urgent.The Energy Internet can embrace renewable energy and play an important role in addressing the scarcity of non-renewable resources and the environmental crisis.Distributed wind,light and other renewable energy generation is uncertain,and its large-scale penetration will have a greater impact on the power quality of the grid.Energy storage devices have the characteristics of dynamic charging and discharging,peak shaving and valley filling,which can effectively make up for the uncertainty of new energy power generation and promote the consumption of renewable energy.As a mobile distributed energy storage device,electric vehicles are applied to the power grid together with distributed renewable energy generation,which has a great impact on the power grid structure,changes the generation,distribution and consumption of electric energy,and diversifies the forms of energy production and consumption.In order to promote the consumption of renewable energy and reduce the rate of abandonment of wind and light,it is usually necessary to schedule the Energy Internet to achieve coordinated development of source-network-load-storage.This article focuses on the multi-objective optimization scheduling problem of the Energy Internet of electric vehicles,and studies the following contents:Firstly,a multi-objective optimization scheduling model of Energy Internet considering electric vehicles is established under the premise of considering the constraints of power balance,power limitation of distributed micro power supply,and number limitation of electric vehicles.The distributed micro power sources considered in the model include diesel generators,energy storage batteries,electric vehicles,photovoltaic cells,and wind turbines.Secondly,because the output power of photovoltaic power generation and wind power generation has greater randomness and intermittency,the stability of the Energy Internet is greatly affected.Therefore,it is necessary to predict the output power of photovoltaic power generation and wind power generation before dispatching,which is an inevitable problem to be solved when large-scale integration of photovoltaic power generation system and wind power generation system into the grid.As a result,before solving the multi-objective optimization scheduling model of the Energy Internet for electric vehicles in this paper,a Long Short-Term Memory(LSTM)model with real-time parameter update function is used for photovoltaic power generation and wind power generation.The output power is predicted,and the effectiveness and reliability of the prediction method are verified by Matlab simulation experiments during the prediction process.Finally,based on the bi-level programming principle,this paper solves the multi-objective optimization scheduling problem of Energy Internet including electric vehicles.The upper level optimization takes the system operating cost as the objective function,coordinates the EV with the diesel unit,energy storage battery,wind power,photoelectric and base load,and optimizes the charging/discharging time of EV in the time domain.The quantity of EV charge/discharge in each period is saved and transmitted to the lower layer.The lower-level optimization is based on the IEEE-33 node distribution network topology to perform spatial scheduling of the position of the electric vehicle charge/discharge load in each period.According to the bi-level programming principle,the multi-objective optimization scheduling model of the Energy Internet of electric vehicles is solved.The upper level optimization takes the system operating cost as the objective function,coordinates the EV with the diesel unit,energy storage battery,wind power,photoelectric and base load,and optimizes the charging/discharging time of EV in the time domain.The quantity of EV charge/discharge in each period is saved and transmitted to the lower layer.The lower-level optimization is based on the IEEE-33 node distribution network topology to perform spatial scheduling of the position of the electric vehicle charge/discharge load in each period.The power loss of the distribution network is minimized by rationally distributing the electric vehicle load in each period to each node of the distribution network.The experimental results show that the time and space scheduling of electric vehicle charging/discharging can not only improve the economics of the Energy Internet,but also improve the safe operation of the Energy Internet.Through the research on the multi-objective optimization scheduling of Energy Internet including electric vehicles,it can provide valuable reference for the economic,low-carbon and stable operation of power system under the environment of Energy Internet.