Application of Neural Network in Performance
Evaluation of Satellite Communication System:
Review and Prospect
Shaochi Cheng
(&) , Yuan Gao, Jiang Cao, Yang Guo, Yanchang Du,
and Su Hu
PLA Academy of Military Science, Beijing 100091, China
csc04@tsinghua.org.cn
Abstract. Satellite communication has become an indispensable means of
communication. As satellite communication constellations become more and
more complex, performance evaluation for satellite design, networking and
applications grows more and more important. This paper summarizes current
research on performance evaluation of satellite communication system and
proposes application prospect of neural network in performance evaluation of
satellite communication system. Identifying key parameters, adjusting evaluation model adaptively and comparing different satellite constellations’ performance are supposed to be three key application areas.
Keywords: Neural network Á Performance evaluation Á Satellite
communication
1 Introduction
Nowadays, satellite communication has become an indispensable means of communication because it has longer communication distance, more extensive coverage and
higher quality of transmission than ground communication. There are totally 2062
operating satellites which include 773 communication satellites as of November 30,
2018 [1]. These communication satellites are playing an increasingly important role in
agriculture, fisheries, transportation, disaster relief and national defense. In recent
years, many advanced satellite communication programs have been put forward. For
instance, SpaceX has planned to launch nearly 12,000 communication satellites by the
mid-2020s [2], and Amazon said that it was planning to launch thousands of communication satellites to achieve global coverage in April 2019 [3]. These satellite
constellations consist of a surprising number of satellites and highly complex satellite
communication links, which would need performance evaluation for satellite design,
networking and applications.
Neural network is a basic algorithm for deep learning. Its development history has
influenced the development of deep learning, thus affecting the history of artificial
intelligence. Recently, the improvement of computing power and diversity of data
feature provided by big data has created favorable conditions for the rapid development
of neural network. Neural network could classify, cluster, and predict data, which
© Springer Nature Singapore Pte Ltd. 2020
Q. Liang et al. (Eds.): Artificial Intelligence in China, LNEE 572, pp. 239–244, 2020.
https://doi.org/10.1007/978-981-15-0187-6_27
Evaluation of Satellite Communication System:
Review and Prospect
Shaochi Cheng
(&) , Yuan Gao, Jiang Cao, Yang Guo, Yanchang Du,
and Su Hu
PLA Academy of Military Science, Beijing 100091, China
csc04@tsinghua.org.cn
Abstract. Satellite communication has become an indispensable means of
communication. As satellite communication constellations become more and
more complex, performance evaluation for satellite design, networking and
applications grows more and more important. This paper summarizes current
research on performance evaluation of satellite communication system and
proposes application prospect of neural network in performance evaluation of
satellite communication system. Identifying key parameters, adjusting evaluation model adaptively and comparing different satellite constellations’ performance are supposed to be three key application areas.
Keywords: Neural network Á Performance evaluation Á Satellite
communication
1 Introduction
Nowadays, satellite communication has become an indispensable means of communication because it has longer communication distance, more extensive coverage and
higher quality of transmission than ground communication. There are totally 2062
operating satellites which include 773 communication satellites as of November 30,
2018 [1]. These communication satellites are playing an increasingly important role in
agriculture, fisheries, transportation, disaster relief and national defense. In recent
years, many advanced satellite communication programs have been put forward. For
instance, SpaceX has planned to launch nearly 12,000 communication satellites by the
mid-2020s [2], and Amazon said that it was planning to launch thousands of communication satellites to achieve global coverage in April 2019 [3]. These satellite
constellations consist of a surprising number of satellites and highly complex satellite
communication links, which would need performance evaluation for satellite design,
networking and applications.
Neural network is a basic algorithm for deep learning. Its development history has
influenced the development of deep learning, thus affecting the history of artificial
intelligence. Recently, the improvement of computing power and diversity of data
feature provided by big data has created favorable conditions for the rapid development
of neural network. Neural network could classify, cluster, and predict data, which
© Springer Nature Singapore Pte Ltd. 2020
Q. Liang et al. (Eds.): Artificial Intelligence in China, LNEE 572, pp. 239–244, 2020.
https://doi.org/10.1007/978-981-15-0187-6_27