Multi-agents modelling of EV purchase willingness based on questionnaires

Traditional experimental economics methods often consume enormous resources of qualified human participants,and the inconsistence of a participant’s decisions among repeated trials prevents investigation from sensitivity analyses.The problem can be solved if computer agents are capable of generating similar behaviors as the given participants in experiments.An experimental economics based analysis method is presented to extract deep information from questionnaire data and emulate any number of participants.Taking the customers’willingness to purchase electric vehicles(EVs)as an example,multi-layer correlation information is extracted from a limited number of questionnaires.Multiagents mimicking the inquired potential customers are modelled through matching the probabilistic distributions of their willingness embedded in the questionnaires.The authenticity of both the model and the algorithmis validated by comparing the agent-based Monte Carlo simulation results with the questionnaire-based deduction results.With the aid of agent models,the effects of minority agents with specific preferences on the results are also discussed.

Scenario-based Unit Commitment Optimization for Power System with Large-scale Wind Power Participating in Primary Frequency Regulation

Continuous increase of wind power penetration brings high randomness to power system,and also leads to serious shortage of primary frequency regulation(PFR)reserve for power system whose reserve capacity is typically provided by conventional units.Considering large-scale wind power participating in PFR,this paper proposes a unit commitment optimization model with respect to coordination of steady state and transient state.In addition to traditional operation costs,losses of wind farm de-loaded operation,environmental benefits and transient frequency safety costs in high-risk stochastic scenarios are also considered in the model.Besides,the model makes full use of interruptible loads on demand side as one of the PFR reserve sources.A selection method for high-risk scenarios is also proposed to improve the calculation efficiency.Finally,this paper proposes an inner-outer iterative optimization method for the model solution.The method is validated by the New England 10-machine system,and the results show that the optimization model can guarantee both the safety of transient frequency and the economy of system operation.

Multi-agent modeling and analysis of EV users' travel willingness based on an integrated causal/statistical/behavioral model

An electric vehicle(EV) centred ecosystem has not yet been formed, the existing limited statistic data are far from enough for the analysis of EV users' travel and charge behaviors, which however tends to be affected by many certain and uncertain factors. An experimental economics(EE)-based simulation method can be used to analyze thebehaviors of key participants in a system. However, it is restricted by the system size, experimental site and the number of qualified human participants. Therefore, this method is hard to be adopted for the behavioral analysis of a large number of human participants. In this paper, a new method combining a questionnaire statistics and the EEbased simulation is proposed. The causal relationship is considered in the design of the questionnaires and data extraction, then a multi-agent modeling integration method is introduced in the EE-based simulation, which enables the integration of causal/statistical/behavioral models into the multi-agent framework to reflect the EV users' travel willingness statistically. The generated multi-agents are used to replace human participants in the EE-based simulation in order to evaluate EV users' travel demands in different scenarios, and compare the differences of simulated or measured travel behaviors between potential EV users and internal combustion engine(ICE) vehicle users.

LSTM-based Energy Management for Electric Vehicle Charging in Commercial-building Prosumers

As typical prosumers,commercial buildings equipped with electric vehicle(EV)charging piles and solar photovoltaic panels require an effective energy management method.However,the conventional optimization-model-based building energy management system faces significant challenges regarding prediction and calculation in online execution.To address this issue,a long short-term memory(LSTM)recurrent neural network(RNN)based machine learning algorithm is proposed in this paper to schedule the charging and discharging of numerous EVs in commercial-building prosumers.Under the proposed system control structure,the LSTM algorithm can be separated into offline and online stages.At the offline stage,the LSTM is used to map states(inputs)to decisions(outputs)based on the network training.At the online stage,once the current state is input,the LSTM can quickly generate a solution without any additional prediction.A preliminary data processing rule and an additional output filtering procedure are designed to improve the decision performance of LSTM network.The simulation results demonstrate that the LSTM algorithm can generate near-optimal solutions in milliseconds and significantly reduce the prediction and calculation pressures compared with the conventional optimization algorithm.