1 s2.0 S1877050923018872 Main

You might also like

Download as pdf or txt
Download as pdf or txt
You are on page 1of 8

Available online at www.sciencedirect.

com
Available online at www.sciencedirect.com
ScienceDirect
AvailableScienceDirect
online at www.sciencedirect.com
Procedia Computer Science 00 (2023) 000–000
Procedia Computer Science 00 (2023) 000–000 www.elsevier.com/locate/procedia
ScienceDirect www.elsevier.com/locate/procedia

Procedia Computer Science 228 (2023) 551–558

3rd International Conference on Machine Learning and Big Data Analytics for IoT Security and Privacy
3rd International Conference on Machine Learning and Big Data Analytics for IoT Security and Privacy
Satellite Communication System Resource Scheduling
Satellite Communication
Algorithm Based onSystem Resource
Artificial Scheduling
Intelligence
Algorithm Based on Artificial Intelligence
Linli Chen*, Yufu Zheng
Linli Chen*, Yufu Zheng
School of Electronic and Information Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China
School of Electronic and Information Engineering, Lanzhou Jiaotong University, Lanzhou 730070, China

Abstract
Abstract
With the rapid growth of social economy, the requirements for resource utilization are becoming higher and higher. How to
effectively solvegrowth
With the rapid the problem of energy
of social economy,shortage has become a for
the requirements hot resource
topic. However, there
utilization areare still manyhigher
becoming deficiencies in theHow
and higher. current
to
resource
effectivelyscheduling algorithm.
solve the problem For example,
of energy shortage for
has different
become atypes of satellites
hot topic. However,withtheredifferent needsdeficiencies
are still many and requirements, their
in the current
performance indicators
resource scheduling are different,
algorithm. For and in the satellite
example, communication
for different system, the
types of satellites withinteraction
differentbetween multiple
needs and nodes needs
requirements, to
their
be considered.
performance Therefore,
indicators this paper
are different, studies
and in the artificial
the satellite intelligence
communication algorithm,
system, and proposes
the interaction an improved
between multiple particle
nodes needs to
complementary
be considered. scheduling
Therefore, strategy
this paperfor astudies
single user
the in view ofintelligence
artificial the shortcomings of theand
algorithm, existing particle
proposes an swarm optimization
improved particle
(PSO) algorithm.scheduling
complementary On this basis, this for
strategy paper appliesuser
a single thisinmethod
view ofto theevaluate the system
shortcomings of performance and verify
the existing particle its effectiveness.
swarm optimization
The
(PSO)verification
algorithm.results
On thisshow thatthis
basis, thepaper
utilization efficiency
applies this methodof theto satellite
evaluatecommunication system resource
the system performance scheduling
and verify algorithm
its effectiveness.
is above
The 93%. results show that the utilization efficiency of the satellite communication system resource scheduling algorithm
verification
© above
is 2023 The93%.Authors. Published by ELSEVIER B.V.
© 2023
This The
is an Authors.
open Published
accessPublished by Elsevier
article under B.V.
the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0)
© 2023 The Authors. by ELSEVIER B.V.
This is an
Peer-review open access
under article under
responsibility the CC BY-NC-ND
of the scientific committeelicense (https://creativecommons.org/licenses/by-nc-nd/4.0)
of the 3rd International Conference on Machine Learning and Big
This is an open access article under CC BY-NC-ND license
Peer-review under responsibility of the scientific committee (https://creativecommons.org/licenses/by-nc-nd/4.0)
of the 3rd International Conference on Machine Learning and
Data Analytics
Peer-review for responsibility
under IoT Security and of Privacy
the scientific committee of the 3rd International Conference on Machine Learning and Big
Big Data Analytics for IoT Security and Privacy
Keywords: Artificial
Data Analytics for Intelligence;
IoT SecuritySatellite Communication; Resource Scheduling; Communication Algorithm
and Privacy
Keywords: Artificial Intelligence; Satellite Communication; Resource Scheduling; Communication Algorithm

1. Introduction
1. Introduction
With the exploration and research of nature, artificial intelligence has become one of the most challenging and
With thehigh-tech
promising exploration and research
technologies in of
thenature, artificialItintelligence
21st century. has become
plays an important roleone
in of
thethegrowth
most challenging and
of the national
promising At
economy. high-tech
present,technologies in the
China is in the 21st
stage of century.
transitionItfrom
playsindustrialization
an important role in the growth
to information of the
society. Asnational
a large
economy. At present, China is in the stage of transition from industrialization to information society. As a large

* Corresponding author. Tel.: +0-000-000-0000 ; fax: +0-000-000-0000 .


* E-mail zc15117188356@126.com
address:author.
Corresponding Tel.: +0-000-000-0000 ; fax: +0-000-000-0000 .
E-mail address: zc15117188356@126.com
1877-0509 © 2023 The Authors. Published by ELSEVIER B.V.
This is an open
1877-0509 access
© 2023 Thearticle under
Authors. the CC BY-NC-ND
Published by ELSEVIER license
B.V. (https://creativecommons.org/licenses/by-nc-nd/4.0)
Peer-review under
This is an open responsibility
access of the
article under the scientific
CC BY-NC-NDcommittee of the
license 3rd International Conference on Machine Learning and Big Data Analytics for
(https://creativecommons.org/licenses/by-nc-nd/4.0)
IoT Securityunder
Peer-review and Privacy
responsibility of the scientific committee of the 3rd International Conference on Machine Learning and Big Data Analytics for
IoT Security and Privacy
1877-0509 © 2023 The Authors. Published by Elsevier B.V.
This is an open access article under the CC BY-NC-ND license (https://creativecommons.org/licenses/by-nc-nd/4.0)
Peer-review under responsibility of the scientific committee of the 3rd International Conference on Machine Learning and
Big Data Analytics for IoT Security and Privacy
10.1016/j.procs.2023.11.063
552 Linli Chen et al. / Procedia Computer Science 228 (2023) 551–558
2 Linli Chen, Yufu Zheng / Procedia Computer Science 00 (2019) 000–000

population and resource-consuming country, the fact that environmental problems are increasingly serious makes
people pay more attention to the importance of its sustainable use to promote the transformation of economic growth
mode. At the same time, due to the progress of science and technology, human production and living standards have
been continuously improved, and the ecological pollution caused by the increased demand for energy has also
prompted people to pay more and more attention to the topic of rational and efficient use of natural resources.
There have been many related studies on satellite communications. Some scholars have proposed a resource
scheduling algorithm based on fuzzy mathematics. This method finds the best optimization scheme by analyzing and
studying the existing satellite network. Some scholars have combined traditional scheduling strategies with
intelligent decision-making. Through the analysis of existing data, it is concluded that this theory can be applied to
practice. At the same time, considering the characteristics of satellite communication such as irreversibility in a
certain period of time, too many uncertain factors and huge amount of information, adopting PSO as the optimal
search method can effectively avoid the interference effect and premature phenomenon caused by randomness, and
also has a good effect in improving efficiency [1-2]. Other scholars proposed to solve the data link routing problem
in the system based on fuzzy programming theory and genetic algorithm. They believe that when considering the
global optimal solution, the time occupied by search space should be reduced as much as possible. At the same time,
it is also necessary to comprehensively consider the impact of multi-dimensional factors such as individual, parent
and child on resource allocation to carry out a reasonable resource scheduling scheme design, in order to maximize
network bandwidth savings and improve communication quality [3-4]. Therefore, this paper studies the resource
scheduling algorithm of satellite communication system based on artificial intelligence. With the rapid growth of
artificial intelligence, it has a broad application prospect in the field of satellite communications. However, due to
the strong self-organization ability of data, the high degree of information asymmetry and the large interaction
between individuals, it is difficult to calculate, so there are still some defects. So this paper studies the modeling of
satellite communication system based on fuzzy neural network algorithm. First, it introduces the theory and relevant
knowledge of artificial intelligence optimization, and then analyzes the intelligent search method and principle of
resource scheduling. In this paper, the effectiveness and superiority of the algorithm are verified with practical
examples, and the better results are obtained. The conclusion is drawn by comparing the algorithm performance
under different parameters.

2. Discussion on Satellite Communication System Resource Scheduling Algorithm Based on Artificial


Intelligence

2.1 Satellite Communication

Satellite communication is to send data information to the ground station through the transmitter of the satellite,
and then receive and process the information by the end user, and finally complete the resource sharing and long-
distance transmission among all points on the earth in the global scope. It is flexible and easy to use, and can realize
remote control according to the network service requests of users at different locations [5-6]. Its basic structure
includes: baseband, antenna or on-board equipment, satellite communication network and its related technology
subnets and relay nodes, which form a complete radio spectrum chain. In the satellite communication system, each
node has its own data transmission channel, and the information is transmitted by the network of the satellite
transmitter and receiver. At this time, it is necessary to transmit the received signal to the repeater through the
antenna. After receiving the signals from different points in different directions, the useful information can be output
only after it is amplified by amplification technology [7-8]. In the satellite communication system, due to the
influence of its working environment, operation mode and other factors, it is necessary to receive and send data.
This paper uses a special satellite communication method. It uses the channel to complete the function of
information transmission to realize the signal transmission process. First, transmit an antenna with more than two
different frequencies at a certain interval, and then convert it into high-frequency AC energy between the wireless
transceiver and the transmitter to the microwave receiver, so as to receive the signal. Figure 1 shows the principle
framework of satellite channel technology.
Linli Chen et al. / Procedia Computer Science 228 (2023) 551–558 553
Linli Chen, Yufu Zheng / Procedia Computer Science 00 (2019) 000–000 3

Transmitting Receiving
Input source data Channel estimation
terminal terminal

Variable bit rate


Channel estimation Decipher
coding

Select code
modulation mode

Variable order
Demodulation
modulation
Downlink channel

Figure 1. Principle of satellite channel technology

In this paper, the dispatch and control center would use PSO algorithm to process, analyze and research the status
information data of each channel in the satellite network, and also take into account the differences and special
factors between different regions. It is necessary to coordinate the relationship between nodes on each
communication link to ensure system stability, so as to achieve the goal of achieving the best performance index [9-
10]. The receiver is controlled by satellite, and the transmitter is mainly responsible for sending commands,
processing tasks and other functional services to the ground data center. The receiving station only needs to
complete the analysis of the received information and make decisions to receive the user's request signal to the
terminal equipment, so that it can work [11]. The function of the satellite communication system is to realize and
control between the satellite and the ground station, between the antenna receivers and on their adjacent lines. In this
process, different types of equipment need to be used. Generally, it is only necessary to set the sending signal
address as the starting position of the satellite to complete the task of the receiving end, which would make the
whole system easier to operate and control its operation status [12].

2.2 Resource Scheduling Algorithm

In satellite communication system, resource scheduling algorithm is used to solve some specific problems and
optimize them. When a node fails, it needs to resend another data. Due to the mutual interference between multiple
nodes, which leads to the inability to continue to transmit messages, or the inability to correctly receive other
information and other reasons, the loss caused by multi-hop relay is caused. At the same time, because of these
factors, the resource scheduling algorithm in satellite communication system has a certain degree of robustness. The
existing data information can be used to reasonably allocate and manage the machines and equipment that need to be
optimized [13-14]. In order to improve the efficiency of resource utilization, reduce costs, meet user requirements
and other characteristics, it must adopt appropriate and effective methods to use these data to achieve the optimal
task scheduling problem. When solving the optimal solution, it only considers one constraint, namely, time
constraint and space constraint. However, with the passage of time, the change of uncertain environmental factors
and the change of system parameters, the optimization results would have certain errors. If people want to calculate
accurately or get more accurate data, it must first establish the corresponding mathematical model to realize the
resource scheduling problem involved in the solution process. It decomposes the complex system into a number of
individuals with different capabilities, and several sets of units that are interconnected, interacted or restricted. This
algorithm makes each subgroup contain enough and high-quality functions by solving each node under certain
constraints [15-16]. Because each individual has its own unique characteristics, it cannot fully adapt to the diversity
of other organisms. So when you need to solve a problem, people can only select some particles with specific
requirements to search. It generates particles randomly to achieve the global optimization solution, and uses existing
knowledge to find the optimal value or approximate value. At the same time, it can solve parameters with the same
property attributes as the objective function, and can dynamically update them using multiple iterative strategies to
554 Linli Chen et al. / Procedia Computer Science 228 (2023) 551–558
4 Linli Chen, Yufu Zheng / Procedia Computer Science 00 (2019) 000–000

obtain the best performance indicators and the most reasonable resource allocation scheme [17-18]. The principle of
the resource scheduling algorithm is as follows:

 I 
 
K
      H   GKH  [ ]  S O  0 (1)
 L GK 

Therefore, the algorithm of s in the above formula can be expressed as:

 k
I 
Rank S   Rank  i     H   Ig[ h]S  (2)
 i gk 

Because each organism has its own unique characteristics, genes and evolutionary laws and has strong
randomness, this paper can select the chromosome with high fitness as the initial body, and set the corresponding
order of magnitude sequence to make it enter the group to continue searching until the optimization process stops. In
reality, due to the characteristics of wireless network such as strong time delay, large amount of information
transmission, and the unbalanced transmission signal strength between different regions, the network topology is
complex and changeable, and the capacity is huge.

2.3 AI Algorithm

The research of artificial intelligence algorithm is a very important subject in the field of human understanding of
natural laws and exploring intelligence science. It plays an important role in solving complex, changeable and
multivariable problems. The principle of AI algorithm is to simulate the existing knowledge in the human brain and
convert it into a rule, so that the machine can run according to the preset program. This method uses the human
brain to analyze and perceive the biological evolution process [19-20]. It is composed of a large number of repetitive
neurons, and is mainly used for processing unstructured working signals such as information and data or nonlinear
decision-making problems. It is a parallel system with strong robustness and learning ability, which can simulate
complex and uncertain factors in human brain, thus producing accurate prediction results [21]. Figure 2 shows the
AI algorithm flow.
Design fitness Whether the
Chromosome
Begin Initialize population function to evaluate termination Finish
coding
population conditions are met

Selection, crossover
Get new species
and variation

Figure 2. The artificial insemination algorithm process

The population is generated by natural selection mechanism, and the genetic operation process is to use some
particularity between the gene and the code to generate the population chromosome, and control it to become the
optimal individual. At the same time, it is also to adapt to the environment in a way that simulates the laws of
biological evolution and evolution. In this process, the species can be continuously updated and the original
biodiversity can be eliminated. The artificial neural network can be used to process complex and abstract data to
adapt to the characteristics of massive information and non-linear and multidimensional characteristics. Satellite
communication is a wireless, cross-regional and multi-band network with the advantages of wide coverage, fast
Linli Chen et al. / Procedia Computer Science 228 (2023) 551–558 555
Linli Chen, Yufu Zheng / Procedia Computer Science 00 (2019) 000–000 5

transmission rate and low cost. As a system independent of ground equipment, it can make judgments (including
prediction), analysis and interpretation (such as fuzzy inference rules) and decision-making process on these signals
by sending radio waves through satellites to control the tasks that need to be completed by both sides of the
communication, so as to achieve the optimization of resource allocation in the whole network and realize the
efficient operation of the wireless mobile communication system. In the process of natural biological evolution, a
series of random selection mechanisms are adopted to obtain the optimal solution or individual parameter values,
and then these information is combined with fitness function to generate a new generation of algorithm and applied
to actual production activities to solve the problem. Finally, the best combination method and iteration number are
determined according to the results obtained:

 
okj  f   ij okj   j  (3)
 i 

Equation 4 calculates the error of output layer and intermediate layer.

 kj  okj 1  okj   km mj (4)


m

There are many complex nonlinear functions and laws in the process of biological genetics, which are generated
and stored in nature by varying degrees depending on the cognitive structure of human brain. At the same time,
there are also some uncertain factors that would affect its own existence and eigenvalue. In addition, there are many
other property parameters, which can predict and learn the artificial intelligence algorithm, search for the optimal
solution by iterating randomly generated particles, and judge its state to determine the best solution.

3. Experimental Process of Satellite Communication System Resource Scheduling Algorithm Based on


Artificial Intelligence

3.1 Resource Scheduling Algorithm Framework of Satellite Communication System Based on Artificial Intelligence

Energy sending end Control circuit Primary converter

Contactless transformer

Energy receiving end Control circuit Secondary converter

Figure 3. Resource scheduling algorithm framework of satellite communication system based on artificial intelligence

Based on the artificial intelligence algorithm framework proposed in this paper (as shown in Figure 3), the initial
population is first screened and a certain number of gene sequences are selected as the original function. Secondly,
the crossover and mutation operation would get a new generation of chromosomes and match them as the optimal
556 Linli Chen et al. / Procedia Computer Science 228 (2023) 551–558
6 Linli Chen, Yufu Zheng / Procedia Computer Science 00 (2019) 000–000

solution. The new individual coding is completed through two steps of random selection and exchange. The resource
scheduling algorithm is used to calculate the optimal parameter value and give the corresponding rules. The ant
colony intelligent search method is used to realize the particle swarm evolutionary optimization, thus achieving the
global minimization problem. In this model, the user selects one of multiple nodes as the decision machine
according to his own needs, and each node selects two or more of them respectively. After calculating the optimal
strategy, the user assigns it to each task unit for specific execution. The information sent by each repeater can be
processed at the same time and returned to the main controller to run the time and space parameters required to
realize the target function module, so as to meet the requirements of multi-hop data transmission and scheduling
under different load conditions. For each data block, they may be affected by other parts. After screening and
processing and analyzing the information, the optimal solution can be obtained or appropriate algorithms can be
selected according to the actual situation to realize the state optimization and performance evaluation of the whole
process. The problem can be considered from the overall situation, and decisions can be made to finally enable the
system to meet the user's needs in different degrees, so as to meet the requirements of efficiency, energy
conservation, environmental protection, etc.

3.2 Performance Test of Satellite Communication System Resource Scheduling Algorithm Based on Artificial
Intelligence

The resource scheduling method of wireless satellite communication system based on artificial intelligence
algorithm is feasible and effective in theory, but for actual operation, the model may have some defects, so it is
necessary to test the running performance of the scheduling algorithm. The idea of particle swarm evolution can be
applied to PSO to deal with the problem. Through the simulated annealing process, the comparison results between
the optimal individual and the global maximum iteration threshold can determine an optimal objective function
range, and the final selection of the appropriate parameters can be determined according to the size of the search
space and the search time. Determine whether it is feasible by randomly selecting the fitness function value and the
optimal parameter value. According to the optimal parameter obtained after selection as the search probability,
calculate the required target distance, maximum average speed and other information from the optimal solution, and
obtain the resource scheduling effect diagram under the condition of meeting the accuracy requirements. In order to
ensure that the model can achieve the expected goal, complete the analysis of the original data set, initial value
function and other aspects, select the appropriate number and type according to the indicators required by the model,
and use the hierarchical method to analyze when selecting variables, so as to obtain the actual results of resource
utilization.

4. Experiment of Satellite Communication System Resource Scheduling Algorithm Based on Artificial


Intelligence

This paper analyzes the existing resource scheduling algorithms, summarizes the conditions that users need to
meet, and how to use the existing satellite network to achieve the optimal allocation. The traditional link bandwidth
can be changed to the current use of bandwidth spread spectrum to expand capacity, and at the same time, channel
loss can be reduced and performance indicators can be improved to achieve this goal. This method is mainly aimed
at improving the traditional line resource scheduling algorithm, so that the results can be better adapted to user needs.

Table 1. Performance test data of the resource scheduling algorithm


Predicted data Actual amount of
Test times Schedule time(s)
volume data
100 1232 1154 8
200 1435 1362 11
300 1325 1289 10
400 1642 1576 12
500 1457 1373 9
Linli Chen et al. / Procedia Computer Science 228 (2023) 551–558 557
Linli Chen, Yufu Zheng / Procedia Computer Science 00 (2019) 000–000 7

From the test results in Table 1, it can be seen that the satellite communication system resource scheduling
algorithm based on artificial intelligence has good performance and can be optimally configured on the premise of
meeting user requirements. But at present, there is no way to achieve this goal, so it is necessary to analyze the
relationship between the parameters and variables in the model. For a complex nonlinear problem, this paper
establishes an appropriate function to solve the maximum effect of minimizing the difference between the data value
required by the model and the actual data volume, while the processing of multiple attribute variables (such as
interference factor, noise, etc.) is completed through different calculation methods.

500

400
TEST TIMES

300

200

100

91% 92% 93% 94% 95% 96% 97% 98%

RATE

Resource utilization rate

Figure 4. Resource utilization rate

In order to verify the resource scheduling strategy of satellite communication system based on artificial
intelligence, it is necessary to test its operation efficiency. In the calculation process, the PSO method is used to
complete the PSO, the genetic algorithm is used to determine the optimal individual concentration, population size
value, population length and other parameters, and the improved iterative method is used to solve the optimal
solution, and the satisfaction function is substituted into the next generation of evolutionary generations to solve the
problem. In this paper, the artificial intelligence algorithm is used to solve the problem, and finally a good result is
obtained. As can be seen from Figure 4, the utilization efficiency of the satellite communication system resource
scheduling algorithm is above 93%.

5. Conclusions

With the increasing application of artificial intelligence, resource scheduling algorithms based on robot systems
are also developing, and resource scheduling algorithms are receiving more and more attention. This paper studies a
resource scheduling algorithm for satellite communication systems based on artificial intelligence. The improved
algorithm is applicable to existing networks. It has the characteristics of high efficiency, low cost, and can meet user
requirements, and has good performance indicators and strong versatility. In this paper, genetic programming and
fuzzy logic are two typical intelligent computing methods. Then through research, it is found that the PSO method
has the characteristics of high efficiency and fast convergence speed, and an improved data fusion processing
technology suitable for multi-channel parallel transmission in satellite communication environment is proposed.
This method can effectively improve the network load balance and performance indicators, and the control
558 Linli Chen et al. / Procedia Computer Science 228 (2023) 551–558
8 Linli Chen, Yufu Zheng / Procedia Computer Science 00 (2019) 000–000

algorithm based on resource scheduling is used to achieve the solution accuracy and time range of the system
resource scheduling optimization problem.

References

[1] Dharminder Dharminder, Pradeep Kumar Dadsena, Pratik Gupta, Sathya Sankaran: A post quantum secure construction of an authentication
protocol for satellite communication. Int. J. Satell. Commun. Netw. 41(1): 14-28 (2023).
[2] Hayder Al-Hraishawi, Houcine Chougrani, Steven Kisseleff, Eva Lagunas, Symeon Chatzinotas:A Survey on Nongeostationary Satellite
Systems: The Communication Perspective. IEEE Commun. Surv. Tutorials 25(1): 101-132 (2023).
[3] Ruirui Shao, Zhigeng Fang, Liangyan Tao, Su Gao, Weiqing You:A comprehensive G-Lz-ADC effectiveness evaluation model for the single
communication satellite system in the context of poor information. Grey Syst. Theory Appl. 12(2): 417-461 (2022).
[4] Uddeshaya Kumar, Manish Garg:A note on an enhanced dynamic authentication scheme for mobile satellite communication systems. Int. J.
Satell. Commun. Netw. 40(5): 317-329 (2022).
[5] Praveen Kumar Singya, Mohamed-Slim Alouini:Performance of UAV-Assisted Multiuser Terrestrial-Satellite Communication System Over
Mixed FSO/RF Channels. IEEE Trans. Aerosp. Electron. Syst. 58(2): 781-796 (2022).
[6] Anna Talgat, Mustafa A. Kishk, Mohamed-Slim Alouini:Stochastic Geometry-Based Analysis of LEO Satellite Communication Systems.
IEEE Commun. Lett. 25(8): 2458-2462 (2021).
[7] Saiah Bekkar Djelloul Saiah, El-Habib Bensikaddour, Ali Kaddouri, Redouane Belbachir, Boualem Nasri, Djamel Eddine Baba
Hamed:Analysis of the communication links between the AlSat-1b satellite and the ground station: The impact of the Auto Tracking system
on antenna pointing accuracy. Int. J. Satell. Commun. Netw. 39(5): 486-499 (2021).
[8] Hayder Al-Hraishawi, Nicola Maturo, Eva Lagunas, Symeon Chatzinotas: Scheduling Design and Performance Analysis of Carrier
Aggregation in Satellite Communication Systems. IEEE Trans. Veh. Technol. 70(8): 7845-7857 (2021).
[9] Tedros Salih Abdu, Steven Kisseleff, Eva Lagunas, Symeon Chatzinotas: Flexible Resource Optimization for GEO Multibeam Satellite
Communication System. IEEE Trans. Wirel. Commun. 20(12): 7888-7902 (2021).
[10] Arti M. K.: Data Detection in Large MIMO Satellite Communication Systems. IEEE Wirel. Commun. Lett. 10(5): 1032-1035 (2021).
[11] Yuma Abe, Masaki Ogura, Hiroyuki Tsuji, Amane Miura, Shuichi Adachi: Resource and Network Management Framework for a Large-
Scale Satellite Communications System. IEICE Trans. Fundam. Electron. Commun. Comput. Sci. 103-A(2): 492-501 (2020).
[12] Sijing Duan, Dan Wang, Ju Ren, Feng Lyu, Ye Zhang, Huaqing Wu, Xuemin Shen: Distributed Artificial Intelligence Empowered by End-
Edge-Cloud Computing: A Survey. IEEE Commun. Surv. Tutorials 25(1): 591-624 (2023).
[13] Amika M. Singh, Munindar P. Singh:Wasabi: A Conceptual Model for Trustworthy Artificial Intelligence. Computer 56(2): 20-28 (2023).
[14] David Fernández Llorca, Emilia Gómez:Trustworthy Artificial Intelligence Requirements in the Autonomous Driving Domain. Computer
56(2): 29-39 (2023).
[15] Emna Baccour, Mhd Saria Allahham, Aiman Erbad, Amr Mohamed, Ahmed Refaey Hussein, Mounir Hamdi:Zero Touch Realization of
Pervasive Artificial Intelligence as a Service in 6G Networks. IEEE Commun. Mag. 61(2): 110-116 (2023).
[16] Bhuvaneswari Swaminathan, Saravanan Palani, Subramaniyaswamy Vairavasundaram, Ketan Kotecha, Vinay Kumar:IoT-Driven Artificial
Intelligence Technique for Fertilizer Recommendation Model. IEEE Consumer Electron. Mag. 12(2): 109-117 (2023).
[17] Dongyue Liu: Opportunities and Challenges of Compensation and Governance of Network Neural Ecological Environment Damage in the
Era of Artificial Intelligence. IEEE Consumer Electron. Mag. 12(2): 57-63 (2023).
[18] Nello Cristianini, Teresa Scantamburlo, James Ladyman:The social turn of artificial intelligence. AI Soc. 38(1): 89-96 (2023).
[19] Josh Cowls, Andreas Tsamados, Mariarosaria Taddeo, Luciano Floridi:The AI gambit: leveraging artificial intelligence to combat climate
change - opportunities, challenges, and recommendations. AI Soc. 38(1): 283-307 (2023).
[20] Jennings Byrd, Paige Paquette: Frankenstein: a creation of artificial intelligence? AI Soc. 38(1): 331-342 (2023).
[21] Ivan Manuel De la Vega Hernandez, Angel Serrano Urdaneta, Elias Carayannis: Global bibliometric mapping of the frontier of knowledge
in the field of artificial intelligence for the period 1990-2019. Artif. Intell. Rev. 56(2): 1699-1729 (2023).

You might also like