Search

Your search keyword '"Gao Li"' showing total 493 results
Start Over Author "Gao Li" Publisher ieee
493 results on '"Gao Li"'

27. A Comparative Study of Deep Reinforcement Learning-based Transferable Energy Management Strategies for Hybrid Electric Vehicles

Author

Xu, Jingyi, Li, Zirui, Gao, Li, Ma, Junyi, Liu, Qi, and Zhao, Yanan

Subjects
FOS: Computer and information sciences, Computer Science - Machine Learning, Artificial Intelligence (cs.AI), Computer Science - Artificial Intelligence, FOS: Electrical engineering, electronic engineering, information engineering, Systems and Control (eess.SY), Electrical Engineering and Systems Science - Systems and Control, Machine Learning (cs.LG)
Abstract

The deep reinforcement learning-based energy management strategies (EMS) have become a promising solution for hybrid electric vehicles (HEVs). When driving cycles are changed, the neural network will be retrained, which is a time-consuming and laborious task. A more efficient way of choosing EMS is to combine deep reinforcement learning (DRL) with transfer learning, which can transfer knowledge of one domain to the other new domain, making the network of the new domain reach convergence values quickly. Different exploration methods of DRL, including adding action space noise and parameter space noise, are compared against each other in the transfer learning process in this work. Results indicate that the network added parameter space noise is more stable and faster convergent than the others. In conclusion, the best exploration method for transferable EMS is to add noise in the parameter space, while the combination of action space noise and parameter space noise generally performs poorly. Our code is available at https://github.com/BIT-XJY/RL-based-Transferable-EMS.git.

Published
2022
Full Text
View/download PDF

28. A Comparative Study of Deep Reinforcement Learning-based Transferable Energy Management Strategies for Hybrid Electric Vehicles

Author

Xu, Jingyi (author), Li, Z. (author), Gao, Li (author), Ma, Junyi (author), Liu, Qi (author), Zhao, Yanan (author), Xu, Jingyi (author), Li, Z. (author), Gao, Li (author), Ma, Junyi (author), Liu, Qi (author), and Zhao, Yanan (author)

Abstract

The deep reinforcement learning-based energy management strategies (EMS) have become a promising solution for hybrid electric vehicles (HEVs). When driving cycles are changed, the neural network will be retrained, which is a time-consuming and laborious task. A more efficient way of choosing EMS is to combine deep reinforcement learning (DRL) with transfer learning, which can transfer knowledge of one domain to the other new domain, making the network of the new domain reach convergence values quickly. Different exploration methods of DRL, including adding action space noise and parameter space noise, are compared against each other in the transfer learning process in this work. Results indicate that the network added parameter space noise is more stable and faster convergent than the others. In conclusion, the best exploration method for transferable EMS is to add noise in the parameter space, while the combination of action space noise and parameter space noise generally performs poorly. Our code is available at https://github.com/BIT-XJY/RL-based-Transferable-EMS.git., Green Open Access added to TU Delft Institutional Repository 'You share, we take care!' - Taverne project https://www.openaccess.nl/en/you-share-we-take-care Otherwise as indicated in the copyright section: the publisher is the copyright holder of this work and the author uses the Dutch legislation to make this work public., Transport and Planning

Published
2022
Full Text
View/download PDF

40. On a Tracial Version of Haemers Bound.

Author

Gao, Li, Gribling, Sander, and Li, Yinan

Subjects
*QUANTUM numbers, *THETA functions, *QUANTUM entanglement
Abstract

We extend upper bounds on the quantum independence number and the quantum Shannon capacity of graphs to their counterparts in the commuting operator model. We introduce a von Neumann algebraic generalization of the fractional Haemers bound (over $\mathbb {C}$) and prove that the generalization upper bounds the commuting quantum independence number. We call our bound the tracial Haemers bound, and we prove that it is multiplicative with respect to the strong product. In particular, this makes it an upper bound on the Shannon capacity. The tracial Haemers bound is incomparable with the Lovász theta function, another well-known upper bound on the Shannon capacity. We show that separating the tracial and fractional Haemers bounds would refute Connes’ embedding conjecture. Along the way, we prove that the tracial rank and tracial Haemers bound are elements of the (commuting quantum) asymptotic spectrum of graphs (Zuiddam, Combinatorica, 2019). We also show that the inertia bound (an upper bound on the quantum independence number) upper bounds the commuting quantum independence number. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

44. An Experimental Implementation of China Digital Radio (CDR) Broadcasting in Hubei.

Author

Gao, Li, Liu, Jun, Huang, Yihang, and Men, Aidong

Subjects
*DIGITAL audio broadcasting, *INTELLIGENT networks, *REGRESSION discontinuity design, *BROADCASTING industry, *QUALITY of service, *ELECTRONIC services
Abstract

This paper presents the research and implementation of a China Digital Radio (CDR) experimental network in Hubei, China with two FM-CDR transmitting stations and four FM-band channels. To study the coverage discontinuity problem in a large service area, the experimental network employs an intelligent networking solution that incorporates multiple service channels carrying Broadcast and Data Services (BADS) and a Common-Regional-Information Channel (CRIC) carrying both service data and system information. The electronic service guide (ESG) carried by CRIC can inform the receivers about the available contents from current and adjacent stations, which can significantly improve the service quality in the overlapping areas, especially under mobile reception environment. Two RF tuners are used in the receiving terminals to access the CRIC, and the BADS channel, respectively. This paper first presents the frequency analysis and coverage tests of the experimental network, and then summarizes the coverage performances with different transmission parameter combinations. The goal is to gain experience in frequency planning, coverage prediction, as well as supportable services of CDR digital audio broadcasting. [ABSTRACT FROM AUTHOR]

Published
2022
Full Text
View/download PDF

45. Design and experimental study of a heat sink temperature regulating system

Author

Zhifei Gu, Xuezhang Wang, Gao Li, Haiyang Zhan, and Xue Yang

Subjects
Refrigerant, Reliability (semiconductor), Materials science, Temperature control, Mode (statistics), Mechanical engineering, Heat sink, Thermal conduction, Maintenance engineering, Near space
Abstract

Environmental simulation test in near space is an important means to verify the reliability of near space vehicle. According to the different test temperature area, different temperature regulation methods are adopted. Compared with the heat source and cold source confrontation mode, the temperature regulation of the carrier refrigerant heat sink in the variable temperature zone has the advantages of good economy, simple equipment structure and excellent performance. In this paper, a temperature regulating system of expansion plate heat sink with heat conduction bath oil as medium is designed, and the equipment performance is verified by simulation and debugging test.

Published
2020
Full Text
View/download PDF

46. LSTM-based Frequency Hopping Sequence Prediction

Author

Jianliang Xu, Weiguo Shen, Zitong Liu, Gao Li, Guoru Ding, and Wei Wang

Subjects
Carrier signal, Sequence, Computer science, Automatic frequency control, 020206 networking & telecommunications, 020302 automobile design & engineering, 02 engineering and technology, High frequency, Time–frequency analysis, Spread spectrum, 0203 mechanical engineering, 0202 electrical engineering, electronic engineering, information engineering, Frequency-hopping spread spectrum, Algorithm
Abstract

The continuous change of communication frequency brings difficulties to the reconnaissance and prediction of non-cooperative communication. The core of this communication process is the frequency-hopping (FH) sequence with pseudo-random characteristics, which controls carrier frequency hopping. However, FH sequence is always generated by a certain model and is a kind of time sequence with certain regularity. Long Short-Term Memory (LSTM) neural network in deep learning has been proved to have strong ability to solve time series problems. Therefore, in this paper, we establish LSTM model to implement FH sequence prediction. The simulation results show that LSTM-based scheme can effectively predict frequency point by point based on historical HF frequency data. Further, we achieve frequency interval prediction based on frequency point prediction.

Published
2020
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results