Charging demand of Plug-in Electric Vehicles: Forecasting travel behavior based on a novel Rough Artificial Neural Network approach

Abstract

The market penetration of Plug-in Electric Vehicles (PEVs) is escalating due to their energy saving and environmental benefits. In order to address PEVs impact on the electric networks, the aggregators need to accurately predict the PEV Travel Behavior (PEV-TB) since the addition of a great number of PEVs to the current distribution network poses serious challenges to the power system. Forecasting PEV-TB is critical because of the high degree of uncertainties in drivers' behavior. Existing studies mostly simplified the PEV-TB by mapping travel behavior from conventional vehicles. This could cause bias in power estimation considering the differences in PEV-TB because of charging pattern which consequently could bungle economic analysis of aggregators. In this study, to forecast PEV-TB an artificial intelligence-based method -feedforward and recurrent Artificial Neural Networks (ANN) with Levenberg Marquardt (LM) training method based on Rough structure -is developed. The method is based on historical data including arrival time, departure time and trip length. In this study, the correlation among arrival time, departure time and trip length is also considered. The forecasted PEV-TB is then compared with Monte Carlo Simulation (MCS) which is the main benchmarking method in this field. The results comparison

Optimal Charging of Plug-In Electric Vehicle: Considering Travel Behavior Uncertainties and Battery Degradation

“…where Wa s (t) is the active power that the wind turbines produce, La s (t) is the real part of load demand, and PEVa s (t) is the absorbed or injected active power by PEVs in time t and scenario s. Wr s (t) is the reactive power produced by the wind turbines, Lr s (t) is the reactive part of the demand and PEVr s (t) is the absorbed reactive power that is consumed by the charging equipment. Plossa s (t) and Plossr s (t) are power loss in a transmission line that can be calculated using Equations (4) and (5) [19]: (5) where i and j are indices of buses and n is the number of buses. G and B are the real and imaginary part of the admittance matrix, and θ is the voltage angle in this equation.…”

“…The most significant restraint in PEVs charging and discharging problem is the state of charge (SOC) of the batteries which should fulfill the minimum boundaries at the moment of departure. This constraint is presented in Equation (8) [19]:…”

“…In this study, for customers convenience, it is assumed that the SOC dep is at least 80 percent of the total capacity [19]. Here, SOC p,s (t dep ) shows SOC of p-th PEV battery at the departure time (t dep ) in scenario s. The undermentioned constraint must be satisfied for all PEVs' battery.…”

Goal Programming Application for Contract Pricing of Electric Vehicle Aggregator in Join Day-Ahead Market

“…The scheduling problems of EVAs have been assessed in a number of recent papers that evaluate the impact of EVAs on various problems, including: the effects of a high EV penetration in the electricity market [16][17][18][19], modeling driving behaviors and fluctuation of electricity prices [20,21], and applying risk-based strategies [22,23].…”

The Recent Development of Artificial Intelligence for Smart and Sustainable Energy Systems and Applications

“…There is an increasing portion of new buyers purchasing electric or plug-in hybrid electric vehicles, which can reduce the usage of fuel. Various AI techniques have been applied to plug-in hybrid electric vehicles, for instance, artificial neural network [32] and integrated model predictive controller [33]. When it comes to electric vehicles, biased coupling, torque estimation, and cognitive heuristic techniques were adopted in [34] and deep neural networks in [35].…”