Agent–cellular automata model for the dynamic fluctuation of EV traffic and charging demands based on machine learning algorithm

Electric Vehicle Charging Simulation Framework Considering Traffic, User, and Power Grid

“…In order to focus on the interactions among the traffic, user, and power grid, the buses of the power grid are simplified in the proposed framework [24], [25], where TSC and total charging power are used. [23] Trip chain [19] Multi-agent [14], [15] CA [16] Agent-cellular [17] CA Function list Vehicle √ √ √ Note: √ means that the method has the function and × means that the method does not have the function.…”

“…Reference [16] proposes a traffic-power model to investigate the charging power in the charging station based on CA by modeling the charging station alongside the road in a CA system. Reference [17] combines the CA method with the agent method to describe the dynamic process of EV charging and analyzes the charging load in a 25-node traffic network. The charging tempo-spatial distribution is obtained through Monte Carlo method.…”

System‐level performance simulation analysis of non‐orthogonal multiple access technology in 5G mobile communication network

“…Next row will use the ascending decoding, namely, translation out as far as the user first, the direct view other users directly to its target for the unknown interference signal decoding, then translate the longest user minus from the superposition of quantity, decoding step by step, until recently the user is out without interference, and row, despite the use of mathematical deduction can prove that the upside scenario decoding order does not affect the overall system throughput, but usually adopts the ascending decoding, namely, first translate user recently, step by step out and eliminate, the final out as far as the user (14 to 15). Different channel conditions are utilized at different power levels: compared with the previous OMA scheme, the channel conditions differences of each user are not utilized, or resources are not allocated according to different channel conditions of users. Similarly, in NOMA system with simple single antenna, the power distribution coefficient of each user, namely, the combination coefficient in the superposition code, is determined by the user's channel conditions: in superposition encoding, has a strong channel gain the user will be smaller share in the power of the distribution coefficient, the weaker the channel gain users will have greater power allocation coefficient, accounting for larger proportion of superposition, so that the recovery will not drown in target signal in strong user, thus effectively use different channel conditions by each user will be a win‐win way of distribution, can bring the system throughput significantly increased, and the channel between the two users gain the gap, the greater the NOMA system throughput than the OMA of ascension, the more obvious, It also further illustrates the advantages of utilizing the channel condition differences of each user 14–16 …”

Transferência de Dados entre Agentes em um Sistema Multiagente no Domínio do Gerenciamento de Energia em Veículos Elétricos

“…Um dos fatores que provoca mais rejeic ¸ão na adoc ¸ão é a dificuldade em gerenciar a energia elétrica, gerando ansiedade ao usuário. Para mitigar esta dificuldade no gerenciamento da energia elétrica em VE, vários pesquisadores têm realizado trabalhos que utilizam técnicas de aprendizado de máquina ("Machine Learning" -ML) [Almaghrebi et al 2021, Shahriar et al 2021, Zhai et al 2019, Alqahtani et al 2022, sistemas multiagentes ("Multi-Agent System -MAS) e métodos de otimizac ¸ão [Shahriar et al 2020]. Entretanto, para que essas técnicas sejam aplicadas, faz-se necessário um volume de dados muito grande e confiável [Calearo et al 2021], sendo necessário transmitir estes dados de um agente para outro de forma confiável e segura.…”