Article
Computer Science, Information Systems
Geetha Anbazhagan, Daegeon Kim, M. Maragatharajan
Summary: Driving patterns require both average and momentary power demands, which can be met by batteries and ultracapacitors respectively. Smart energy management and IoT-based decision-making modules help optimize energy utilization and hybridization of energy storage systems. Experimental findings highlight the significance of intelligent energy management control for the overall performance of hybrid ESSs.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Artificial Intelligence
Xinyou Lin, Guangji Zhang, Shenshen Wei
Summary: A vehicle velocity prediction model based on DPR and MC is proposed to reduce prediction errors significantly. The results demonstrate high accuracy of the velocity prediction model and its applicability in energy consumption evaluation.
APPLIED SOFT COMPUTING
(2021)
Article
Thermodynamics
Xinyou Lin, Jiayun Wu, Yimin Wei
Summary: The fuel economy of a plug-in hybrid electric vehicle depends on battery energy usage, with ELVP and AR-SOC based on MPC EMS strategy improving fuel economy. Integration of multiple velocity prediction models enhances prediction accuracy and reduces computational cost. By using an adaptive reference SOC trajectory planning method to guide battery energy distribution, optimal torque distribution decisions were derived.
Article
Thermodynamics
Changyin Wei, Yong Chen, Xiaoyu Li, Xiaozhe Lin
Summary: This paper proposes an adaptive equivalent consumption minimization strategy for extender range electric logistics vehicles, which aims to improve fuel economy and optimize power allocation. By combining driving pattern recognition and state-of-charge reference planning, the proposed method can adjust control actions in real time, leading to significant reduction in energy consumption and battery power transients.
Article
Energy & Fuels
Chun Wang, Fengchen Liu, Aihua Tang, Rui Liu
Summary: A two-layer adaptive dynamic programming (DP) optimization energy management strategy (EMS) is proposed to achieve optimal real-time power allocation in electric vehicles. The upper layer uses learning vector quantization (LVQ) to produce real-time driving pattern recognition (DPR) results. The lower layer adopts DP optimization strategy to adjust the power distribution between the battery pack and the supercapacitor pack based on the recognition results. Simulation results show that the proposed EMS improves system efficiency by 10% compared with the original rule-based EMS under different temperatures and DPR levels, with a controlled system efficiency gap of 3% compared to DP.
JOURNAL OF ENERGY STORAGE
(2023)
Article
Computer Science, Information Systems
Dongdong Chen, Tie Wang, Tianyou Qiao, Tiantian Yang, Zhiyong Ji
Summary: This study proposes an adaptive equivalent consumption minimization strategy (A-ECMS) based on driving cycle recognition for a parallel hybrid electric vehicle (HEV). By training a neural network for accurate driving cycle recognition, the optimal equivalent factor is selected for the current driving cycle. Simulation results show that compared to logic-based EMS, A-ECMS can reduce fuel consumption and improve battery state of charge in different driving cycles.
Article
Engineering, Mechanical
Changyin Wei, Xiaodong Wang, Yunxing Chen, Huawei Wu, Yong Chen
Summary: This study proposes a fuzzy energy management strategy based on driving pattern recognition using a neural network. By optimizing energy distribution, the strategy achieves optimal fuel economy and shows significant advantages in fuel consumption compared to traditional methods.
Article
Computer Science, Information Systems
Shaowei Weng, Tiancong Zhang, Zhijie Wu, Juan Lin, Wien Hong
Summary: A novel joint image coding and reversible data hiding method for VQ compressed images is proposed. By rearranging the VQ indices and exploiting their correlations, the method achieves improved prediction performance and reduced bitrate.
INFORMATION SCIENCES
(2022)
Article
Energy & Fuels
Iwona Komorska, Andrzej Puchalski, Andrzej Niewczas, Marcin Slezak, Tomasz Szczepanski
Summary: The study aimed to develop an adaptive driving cycle method for optimizing energy consumption and improving driving range of an electric vehicle, using Gaussian process regression to monitor energy consumption and adaptively adjust speed and acceleration.
Article
Economics
Kaile Zhou, Dingding Hu, Fangyi Li
Summary: The COVID-19 pandemic has significantly impacted traffic mobility, making it crucial to understand changes in private driving behavior. This study proposes a data-driven forecasting model to estimate pre-pandemic daily EV charging demand and investigates the dynamic relationship between charging demand changes and potential influencing factors using a VAR model. The results show varying degrees of decline in charging demand across cities, with COVID-19-related factors being the primary causes.
Article
Automation & Control Systems
Bailing Tian, Zhiyu Li, Xiaopeng Zhao, Qun Zong
Summary: In this paper, a novel adaptive multivariable control algorithm is proposed for reusable launch vehicle (RLV). The algorithm is simple and easy to implement, and utilizes Lyapunov-based technique to guarantee error confinement within prescribed regions.
IEEE TRANSACTIONS ON SYSTEMS MAN CYBERNETICS-SYSTEMS
(2022)
Article
Thermodynamics
Junzhe Shi, Bin Xu, Yimin Shen, Jingbo Wu
Summary: This paper proposes a low computational cost EMS for hybrid battery/ultracapacitor electric buses, which effectively reduces energy consumption and battery life degradation through the use of V2C technology and optimized control rules.
Article
Computer Science, Information Systems
Valentina Rizzello, Matteo Nerini, Michael Joham, Bruno Clerckx, Wolfgang Utschick
Summary: We propose a user-driven method for adaptive quantization and feedback of channel state information (CSI) in frequency division duplexing systems. The approach can be combined with existing autoencoder neural networks and requires only a single codebook shared between the users and the base station. Users can provide feedback with different numbers of bits depending on their data rates, without system changes or additional storage requirements. Simulation results show the proposed method outperforms state-of-the-art schemes in dynamically adapting to different feedback rates.
IEEE WIRELESS COMMUNICATIONS LETTERS
(2023)
Article
Environmental Studies
Yiming Ye, Xuan Zhao, Jiangfeng Zhang
Summary: Due to the fundamental differences in motors and internal combustion engines, the real-time energy consumption profiles of ICEVs and EVs are different, which motivates the need to identify the driving cycle for different types of vehicles. This study proposes a systematic method to develop the driving cycle for EVs and ICEVs, and compares them in the same traffic environment to illustrate the impact of driving cycle electrification.
TRANSPORTATION RESEARCH PART D-TRANSPORT AND ENVIRONMENT
(2023)
Article
Education, Scientific Disciplines
Xu Jianqiao
Summary: Self-driving electric vehicles, as a new logistics technology, improve freight efficiency and promote energy saving and emissions reductions. This paper proposes a method for optimizing the scheduling scenario and parameters of self-driving vehicles through computer simulations. An optimization model based on dynamic programming is established, and an optimization simulation algorithm is designed to solve the model, effectively solving the overall planning problem of vehicle scheduling.