DQN-based resource allocation for NOMA-MEC-aided multi-source data stream

EURASIP Journal on Advances in Signal Processing

卷:2023

Research

Fusheng Zhu¹  Junjuan Xia²  Shiwei Lai²  Jing Ling²  Chongzhi Gao²  Venki Balasubramanian³ 

[1] Guangdong New Generation Communication and Network Innovative Institute (GDCNi), Guangzhou, China;

[2] School of Computer Science, Guangzhou University, Guangzhou, China;

[3] School of Science, Engineering and Information Technology, Federation University, 3350, Mount Helen, VIC, Australia;

关键词: MEC;    NOMA;    Multi-source data stream;    DQN;   

DOI  :  10.1186/s13634-023-01005-2

 received in 2023-01-03, accepted in 2023-03-24,  发布年份 2023

来源: Springer

【 摘 要 】

This paper investigates a non-orthogonal multiple access (NOMA)-aided mobile edge computing (MEC) network with multiple sources and one computing access point (CAP), in which NOMA technology is applied to transmit multi-source data streams to CAP for computing. To measure the performance of the considered NOMA-aided MEC network, we first design the system cost as a linear weighting function of energy consumption and delay under the NOMA-aided MEC network. Moreover, we propose a deep Q network (DQN)-based offloading strategy to minimize the system cost by jointly optimizing the offloading ratio and transmission power allocation. Finally, we design experiments to demonstrate the effectiveness of the proposed strategy. Specifically, the designed strategy can decrease the system cost by about 15% compared with local computing when the number of sources is 5.

【 授权许可】

CC BY   
© The Author(s) 2023

【 图 表 】

42004_2022_764_Taba_HTML.png

Fig. 1

Fig. 4

Fig. 1

Fig. 8

Fig. 5

40623_2023_1812_Article_IEq34.gif

Fig. 2

Fig. 1

Fig. 8

Fig. 1

40623_2023_1812_Article_IEq29.gif

Fig. 2

Fig. 7

Fig. 1

40507_2023_167_Article_IEq417.gif

40507_2023_167_Article_IEq416.gif

40507_2023_167_Article_IEq415.gif

Fig. 1

Fig. 4

40507_2023_167_Article_IEq412.gif

Fig. 2

40507_2023_167_Article_IEq410.gif

Fig. 4

Fig. 1

Fig. 3

40507_2023_167_Article_IEq406.gif

Fig. 2

Fig. 2

Fig. 1

40507_2023_167_Article_IEq402.gif

Fig. 3

40507_2023_167_Article_IEq400.gif

Fig. 2

Fig. 1

40507_2023_167_Article_IEq387.gif

Fig. 1

40854_2023_488_Article_IEq38.gif

40854_2023_488_Article_IEq36.gif

40854_2023_488_Article_IEq34.gif

40854_2023_488_Article_IEq33.gif

40854_2023_488_Article_IEq32.gif

40854_2023_488_Article_IEq30.gif

40854_2023_488_Article_IEq29.gif

40854_2023_488_Article_IEq78.gif

40854_2023_488_Article_IEq77.gif

40854_2023_488_Article_IEq76.gif

40854_2023_488_Article_IEq73.gif

40854_2023_488_Article_IEq72.gif

40507_2023_167_Article_IEq334.gif

40854_2023_488_Article_IEq71.gif

40854_2023_488_Article_IEq54.gif

40854_2023_488_Article_IEq62.gif

Fig. 4

40854_2023_488_Article_IEq60.gif

Fig. 1

40854_2023_488_Article_IEq58.gif

40854_2023_488_Article_IEq57.gif

40854_2023_488_Article_IEq56.gif

13073_2023_1171_Article_IEq2.gif

40854_2023_488_Article_IEq70.gif

40854_2023_488_Article_IEq68.gif

40854_2023_488_Article_IEq67.gif

40854_2023_488_Article_IEq79.gif

40854_2023_488_Article_IEq66.gif

Fig. 3

40854_2023_488_Article_IEq28.gif

40854_2023_488_Article_IEq64.gif

40854_2023_488_Article_IEq27.gif

40854_2023_488_Article_IEq63.gif

40854_2023_488_Article_IEq26.gif

40854_2023_488_Article_IEq24.gif

Fig. 1

40854_2023_488_Article_IEq22.gif

40854_2023_488_Article_IEq21.gif

40507_2023_167_Article_IEq303.gif

Fig. 2

Fig. 7

40507_2023_167_Article_IEq300.gif

Fig. 2

Fig. 1

Fig. 1

40854_2023_488_Article_IEq18.gif

Fig. 1

40854_2023_488_Article_IEq16.gif

Fig. 2

40854_2023_488_Article_IEq15.gif

40854_2023_488_Article_IEq13.gif

40854_2023_488_Article_IEq12.gif

13227_2023_212_Article_IEq3.gif

13227_2023_212_Article_IEq2.gif

13227_2023_212_Article_IEq1.gif

40507_2023_167_Article_IEq282.gif

Fig. 6

40507_2023_167_Article_IEq278.gif

40854_2023_488_Article_IEq8.gif

Fig. 2

40854_2023_488_Article_IEq5.gif

Fig. 3

40854_2023_488_Article_IEq3.gif

Fig. 5

Fig. 4

Fig. 3

Fig. 9

Fig. 7