Case-based reasoning of operation strategies recommendation for UAV swarm

doi:10.23919/JSEE.2025.000178

Journal of Systems Engineering and Electronics ›› 2025, Vol. 36 ›› Issue (6): 1548-1561.doi: 10.23919/JSEE.2025.000178

• SYSTEMS ENGINEERING • Previous Articles

Case-based reasoning of operation strategies recommendation for UAV swarm

Meigen HUANG(), Tao WANG(), Tian JING(), Song YANG(), Xin ZHOU(), Hua HE()

College of Systems Engineering, National University of Defense Technology, Changsha 410073, China

Received:2024-09-20 Online:2025-12-18 Published:2026-01-07
Contact: Tao WANG E-mail:huangmg19@nudt.edu.cn;wangtao1976@nudt.edu.cn;jingtiannudt@163.com;ysxwc@163.com;zhouxin09@nudt.edu.cn;hehua3566@nudt.edu.cn
About author:
HUANG Meigen was born in 1990. He received his Ph.D. degree from Information Engineering University in 2019. He is currently a lecturer in National University of Defense Technology. His research interests are unmanned aerial vehicle swarm operation, intelligent generation of combat plans, and simulation evaluation of combat effectiveness. E-mail: huangmg19@nudt.edu.cn

WANG Tao was born in 1976. He received his Ph.D. degree from National University of Defense Technology in 2017. He is currently a profess in National University of Defense Technology. His research are systems engineering and simulation, the design and intelligent optimization of unmanned aerial vehicle operation systems. E-mail: wangtao1976@nudt.edu.cn

JING Tian was born in 1994. He received his M.S. degree from National University of Defense Technology in 2019. He is currently a lecturer in National University of Defense Technology. His research interest is unmanned aerial vehicle swarm operation simulation and optimization. E-mail: jingtiannudt@163.com

YANG Song was born in 1991. He received his M.S. degree from Nanjing University of Science and Technology in 2016. He is pursuing his Ph.D. degree in the National University of Defense Technology. His research interests are system of system modeling and simulation, unmanned system mission planning. E-mail: ysxwc@163.com

ZHOU Xin was born in 1990. He received his Ph.D. degree from National University of Defense Technology in 2019. He is an associate profess in National University of Defense Technology. His research interest are systems engineering and simulation, multi-agent decision making under uncertainty and reinforcement learning. E-mail: zhouxin09@nudt.edu.cn

HE Hua was born in 1991. He received his Ph.D. degree from National University of Defense Technology in 2019. He is a senior engineer in National University of Defense Technology. His research interest is the design and optimization of unmanned aerial vehicle systems. E-mail: hehua3566@nudt.edu.cn
Supported by:
This work was supported by the National Natural Science Foundation of China (72101263) and the Natural Science Foundation of Hunan Province (2023JJ40677).

Abstract

Abstract:

Aiming at the characteristics of autonomy, confrontation, and uncertainty in unmanned aerial vehicle (UAV) swarm operations, case-based reasoning (CBR) technology with advantages such as weak dependence on domain knowledge and efficient problem-solving is introduced, and a recommendation method for UAV swarm operation strategies based on CBR is proposed. Firstly, we design a universal framework for UAV swarm operation strategies from three dimensions: operation effectiveness, time, and cost. Secondly, based on the representation of operation cases, certain, fuzzy, interval, and classification attribute similarity calculation methods, as well as entropy-based attribute weight allocation methods, are suggested to support the calculation of global similarity of cases. This method is utilized to match the source case with the most similarity from the historical case library, to obtain the optimal recommendation strategy for the target case. Finally, in the form of red blue confrontation, a UAV swarm operation strategy recommendation case is constructed based on actual battle cases, and a system simulation analysis is conducted. The results show that the strategy given in the example performs the best in three evaluation indicators, including cost-effectiveness, and overall outperforms other operation strategies. Therefore, the proposed method has advantages such as high real-time performance and interpretability, and can address the issue of recommending UAV swarm operation strategies in complex battlefield environments across both online and offline modes. At the same time, this study could also provide new ideas for the selection of UAV swarm operation strategies.

Key words: case-based reasoning (CBR), unmanned aerial vehicle (UAV) swarm, operation strategy, mixed retrieval

Meigen HUANG, Tao WANG, Tian JING, Song YANG, Xin ZHOU, Hua HE. Case-based reasoning of operation strategies recommendation for UAV swarm[J]. Journal of Systems Engineering and Electronics, 2025, 36(6): 1548-1561.

Figures/Tables 15

Fig 1

Table 1

Fig 2

Table 2

Fig 3

Table 3

Table 4

Table 5

Table 6

Table 7

Table 8

Fig 4

Table 9

Table 10

Fig 5

References 25

1	SADAF J, ALI H, RIZWAN A, et al. State-ofthe-art and future research challenges in UAV swarms. IEEE Internet of Things Journal, 2024, 11: 19023–19045.
2	ELGHITANI F Dynamic UAV routing for multi-access edge computing. IEEE Trans. on Vehicular Technology, 2024, 73 (6) doi: 10.1109/TVT.2024.3394433
3	KIM J Y, OH H, YU B Y, et al Optimal task assignment for UAV swarm operations in hostile environments. International Journal of Aeronautical and Space Sciences, 2021, 22 (2): 456- 467. doi: 10.1007/s42405-020-00317-z
4	KONG L H, WANG L Z, CAO Z Z, et al Resilience evaluation of UAV swarm considering resource supplementation. Reliability Engineering & System Safety, 2024, 241, 109673.
5	LIU D, WASSON R, VINCENZI D A Effects of system automation management strategies and multi-mission operator-to-vehicle ratio on operator performance in UAV systems. Journal of Intelligent & Robotic Systems, 2009, 54 (5): 795- 810.
6	SUN L K, QIU H X, WANG Y Z, et al. Autonomous UAV maneuvering decisions by refining opponent strategies. IEEE Trans. on Aerospace and Electronic Systems, 2024, 60(3): 3454–3467.
7	ZHANG B Q, LIN X, ZHU Y F. Enhancing multi-UAV reconnaissance and search through double critic DDPG with belief probability maps. IEEE Tran. on Intelligent Vehicles, 2024, 9(2): 3827–3842.
8	ZHANG X, BAI Y J, HE K On countermeasures against cooperative fly of UAV swarms. Drones, 2023, (3): 172.
9	XU J W, DENG Z H, SONG Q, et al Multi-UAV counter-game model based on uncertain information. Applied Mathematics & Computation, 2020, 366, 124684.
10	RAN W Z, LUO R, ZHANG F N, et al Research on efficient multiagent reinforcement learning for multiple UAVs’ distributed jamming strategy. Electronics, 2023, 12, (8): 3874.
11	WU X L, LIN D X, ZHEN R, et al Avoidance priority operation strategy of UAV based on improved greycorrelation projection method. Journal of Hebei University of Science and Technology, 2022, 43 (4): 374- 385.
12	ZHENG J, WANG Y M, CHEN S Q Dynamic case retrieval method with subjective preferences and objective information for emergency decision making. IEEE/ CAA Journal of Automatica Sinica, 2018, 5 (3): 749- 757. doi: 10.1109/JAS.2016.7510232
13	SIMON P, CLAUDE T Knowledge-intensive diagnostics using case-based reasoning and synthetic case generation. IEEE Trans. on Computer-Aided Design of Integrated Circuits and Systems, 2023, 42 (7): 2404- 2417. doi: 10.1109/TCAD.2022.3222287
14	TARCHOUNE I, DJEBBAR A, MEROUANI H F D, et al 3FS-CBR-IRF: improving case retrieval for case-based reasoning with three feature selection and improved random forest. Multimedia Tools and Applications, 2024, 83, 72939- 72973. doi: 10.1007/s11042-024-18360-3
15	CHEN J H, WANG B Q, WANG F, et al Identification of outcropping strata from UAV oblique photogrammetric data using a spatial case-based reasoning model. International Journal of Applied Earth Observation and Geoinformation, 2021, 103, 102450.
16	PINTO M F, MELO A G, MARCATO A L M, et al. Case-based reasoning approach applied to surveillance system using an autonomous unmanned aerial vehicle. Proc. of the IEEE 26th International Symposium on Industrial Electronics, 2017: 1324−1329.
17	GU L C, GUO Q Y, CAO M Case retrieval algorithm based on structure matrix. Journal of Multimedia, 2013, 8 (6): 712- 719.
18	FAN Z P, LI Y H, WANG X H, et al Hybrid similarity measure for case retrieval in CBR and its application to emergency response towards gas explosion. Expert Systems with Applications, 2014, 41 (5): 2526- 2534. doi: 10.1016/j.eswa.2013.09.051
19	WANG Y M, FEI L G, FENG Y Q A hybrid retrieval strategy for case-based reasoning using soft likelihood functions. Soft Computing, 2022, 26 (7): 3489- 3501. doi: 10.1007/s00500-022-06733-5
20	ABDELHAK M, BAGHDAD A Representative case-based retrieval to support case-based reasoning for prediction. International Journal of Strategic Decision Sciences, 2021, 12 (3): 14- 35. doi: 10.4018/IJSDS.2021070102
21	KOVALENKO I I, SHVED A V, KOVAL N V A modified case-based reasoning method based on the rough set theory. Radio Electronics, Computer Science, Control, 2018, (4): 106- 112.
22	PREEJA P, MARTA C, ANJANA W A practical exploration of the convergence of case-based reasoning and explainable artificial intelligence. Expert Systems with Applications, 2024, 255, 124733. doi: 10.1016/j.eswa.2024.124733
23	AAMODT A, PLAZA E Case-based reasoning: foundational issues, methodological variations, and system approaches. AI Communications, 1994, 7 (1): 39- 59. doi: 10.3233/AIC-1994-7104
24	KEANU S, JULIE D, JULIEN T Wasserstein dictionaries of persistence diagrams. IEEE Trans. on visualization and computer graphics, 2024, 30 (2): 1638- 1651. doi: 10.1109/TVCG.2023.3330262
25	MATSOUAKA R, LIU Y, ZHOU Y J. Overlap, matching, or entropy weights: what are we weighting for? [J]. Communications in Statistics: Simulation & Computation, 2024, 53(2): 2672–2691.

Acronym	Type	Main feature	Applicable scenario
EO	Effectiveness-oriented strategy	Prioritize achieving operation effectiveness, such as increasing UAV or payload scale	Close reconnaissance on key target objects
TO	Time-oriented strategy	Prioritize reducing operation time, such as decreasing reconnaissance frequency	Tracking and striking time-sensitive target objects
CO	Cost-oriented strategy	Prioritize compressing operation costs, such as reducing ammunition quantity	Routine harassment of regular target objects
EA	Effectiveness-averse strategy	Weigh operation time and cost, such as adopting high-altitude reconnaissance	Lowthreat reconnaissance of target areas
TA	Time-averse strategy	Weigh operation effectiveness and cost, such as adopting air-ground coordination action	Cost-effective strike on key target objects
CA	Cost-averse strategy	Weigh operation effectiveness and time, such as adopting reconnaissance and strike integrated action	Saturated strike on time-sensitive target objects

Case		Problem description				Solution	Solution effectiveness
Case		$ {a}_{1} $	$ {a}_{2} $	…	$ {a}_{K} $	$ {r}_{1} $	$ {e}_{1} $	$ {e}_{2} $
Source cases	$ {S}_{1} $	$ {s}_{\mathrm{1,1}}^{A} $	$ {s}_{\mathrm{1,2}}^{A} $	…	$ {s}_{1,K}^{A} $	$ {s}_{1}^{R} $	$ {s}_{\mathrm{1,1}}^{E} $	$ {s}_{\mathrm{1,2}}^{E} $
	$ {S}_{2} $	$ {s}_{\mathrm{2,1}}^{A} $	$ {s}_{\mathrm{2,2}}^{A} $	…	$ {s}_{2,K}^{A} $	$ {s}_{2}^{R} $	$ {s}_{\mathrm{2,1}}^{E} $	$ {s}_{\mathrm{2,2}}^{E} $
	$\vdots $	$\vdots $	$\vdots $		$\vdots $	$\vdots $	$\vdots $	$\vdots $
	$ {S}_{I} $	$ {s}_{I,1}^{A} $	$ {s}_{I,2}^{A} $	…	$ {s}_{I,K}^{A} $	$ {s}_{I}^{R} $	$ {s}_{I,1}^{E} $	$ {s}_{I,2}^{E} $
Target cases	$ {T}_{1} $	$ {t}_{\mathrm{1,1}}^{A} $	$ {t}_{\mathrm{1,2}}^{A} $	…	$ {t}_{1,K}^{A} $	−	−	−
	$ {T}_{2} $	$ {t}_{\mathrm{2,1}}^{A} $	$ {t}_{\mathrm{2,2}}^{A} $	…	$ {t}_{2,K}^{A} $	−	−	−
	$\vdots $	$\vdots $	$\vdots $		$\vdots $	−	−	−
	$ {T}_{J} $	$ {t}_{J,1}^{A} $	$ {t}_{J,2}^{A} $	…	$ {t}_{J,K}^{A} $	−	−	−

Case	Attribute value										Strategy	Effectiveness
Case	$ {a}_{1} $	$ {a}_{2} $	$ {a}_{3} $	$ {a}_{4} $	$ {a}_{5} $	$ {a}_{6} $	$ {a}_{7} $	$ {a}_{8} $	$ {a}_{9} $	$ {r}_{1} $	$ {e}_{1} $	$ {e}_{2} $
$ {S}_{1} $	5	2	500	1	4	3	200	4	5	CO	$ \mathrm{Y}\mathrm{e}\mathrm{s} $	0.83
$ {S}_{2} $	5	5	300	3	1	5	300	5	1	EO	$ \mathrm{Y}\mathrm{e}\mathrm{s} $	1.00
$ {S}_{3} $	6	3	500	2	2	4	150	3	4	EO	$ \mathrm{Y}\mathrm{e}\mathrm{s} $	1.17
$ {S}_{4} $	4	4	450	1	1	6	200	2	2	TO	$ \mathrm{Y}\mathrm{e}\mathrm{s} $	0.86
$ {S}_{5} $	6	5	350	4	2	2	350	1	3	TA	$ \mathrm{Y}\mathrm{e}\mathrm{s} $	1.00
$ {S}_{6} $	5	2	500	3	2	6	200	5	5	CA	$ \mathrm{Y}\mathrm{e}\mathrm{s} $	1.17
$ {S}_{7} $	10	2	550	1	3	3	300	1	5	TA	$ \mathrm{Y}\mathrm{e}\mathrm{s} $	1.25
$ {S}_{8} $	4	5	400	2	3	5	180	3	1	TO	$ \mathrm{Y}\mathrm{e}\mathrm{s} $	1.14
$ {S}_{9} $	8	2	300	2	1	4	200	1	3	CO	$ \mathrm{Y}\mathrm{e}\mathrm{s} $	0.75
$ {S}_{10} $	6	5	500	3	2	7	230	3	2	EA	$ \mathrm{Y}\mathrm{e}\mathrm{s} $	0.86
$ {T}_{1} $	8	4	300	3	2	4	400	4	4	−	−	−
$ {T}_{2} $	7	3	400	2	3	3	300	5	3	−	−	−
$ {T}_{3} $	6	2	300	3	1	5	250	2	2	−	−	−
$ {T}_{4} $	3	5	400	4	3	4	300	1	3	−	−	−

$ {S}_{i} $	$ {T}_{j} $
$ {S}_{i} $	Fragile (1)	Poor (2)	Good (3)	Hard (4)
Fragile (1)	1	0.889	0.599	0.352
Poor (2)	0.889	1	0.649	0.391
Good (3)	0.599	0.649	1	0.739
Hard (4)	0.352	0.391	0.739	1
Triangular fuzzy numbers	(0,0,1/3)	(0,1/3,2/3)	(1/3,2/3,1)	(2/3,1,1)

$ {\mathrm{Sim}}\left({S}_{i},{T}_{1}\right) $	Target case
$ {\mathrm{Sim}}\left({S}_{i},{T}_{1}\right) $	$ {T}_{1} $	$ {T}_{2} $	$ {T}_{3} $	$ {T}_{4} $
$ {S}_{1} $	0.659	0.808	0.651	0.709
$ {S}_{2} $	0.781	0.730	0.911	0.765
$ {S}_{3} $	0.762	0.792	0.779	0.712
$ {S}_{4} $	0.610	0.649	0.808	0.693
$ {S}_{5} $	0.786	0.786	0.749	0.799
$ {S}_{6} $	0.721	0.687	0.790	0.713
$ {S}_{7} $	0.723	0.829	0.596	0.673
$ {S}_{8} $	0.642	0.755	0.759	0.803
$ {S}_{9} $	0.829	0.780	0.820	0.675
$ {S}_{10} $	0.705	0.684	0.828	0.69

Case-based reasoning of operation strategies recommendation for UAV swarm

RichHTML

PDF (PC)

Knowledge

Abstract

Cite this article

Share this article

Figures/Tables 15

References 25

Related Articles 8

Recommended Articles

Metrics

Comments

$ {\mathrm{Sim}}\left({S}_{i,k},{T}_{1,k}\right) $	$ {a}_{1} $	$ {a}_{2} $	$ {a}_{3} $	$ {a}_{4} $	$ {a}_{5} $	$ {a}_{6} $	$ {a}_{7} $	$ {a}_{8} $	$ {a}_{9} $
$ {S}_{1} $	0.5	0.333	0.775	0.599	0.333	0.8	0.707	1	0.805
$ {S}_{2} $	0.5	0.667	1	1	0.667	0.8	0.866	0.7	0.441
$ {S}_{3} $	0.667	0.667	0.775	0.649	1	1	0.612	0.3	1
$ {S}_{4} $	0.333	1	0.816	0.599	0.667	0.6	0.707	0.3	0.473
$ {S}_{5} $	0.667	0.667	0.926	0.739	1	0.6	0.935	0.3	0.736
$ {S}_{6} $	0.5	0.333	0.775	1	1	0.6	0.707	0.7	0.805
$ {S}_{7} $	0.667	0.333	0.739	0.599	0.667	0.8	0.866	0.3	0.805
$ {S}_{8} $	0.333	0.667	0.866	0.649	0.667	0.8	0.671	0.3	0.441
$ {S}_{9} $	1	0.333	1	0.649	0.667	1	0.707	0.3	0.736
$ {S}_{10} $	0.667	0.667	0.775	1	1	0.4	0.758	0.3	0.473

Case	Attribute similarity		Global similarity
Case	$ {\mathrm{Sim}}\left({S}_{i,1},{T}_{2,1}\right) $	$ {\mathrm{Sim}}\left({S}_{i,3},{T}_{2,3}\right) $	$ {\mathrm{Sim}}\left({S}_{i,7},{T}_{2,7}\right) $	$ {\mathrm{Sim}}\left({S}_{i},{T}_{2}\right) $
$ {S}_{1} $	0.116	0.156	0.142	0.414
$ {S}_{7} $	0.087	0.148	0.174	0.410

Target case	Recommended case	Recommended strategy	Strategy type
$ {T}_{1} $	$ {S}_{9} $	CO	CO strategy
$ {T}_{2} $	$ {S}_{1} $	CO	CO strategy
$ {T}_{3} $	$ {S}_{2} $	EO	EO strategy
$ {T}_{4} $	$ {S}_{8} $	TO	TO strategy

Operation strategy	Action sequence
EO	①③④⑤⑦⑧⑦
TO	④⑤②③⑦
CO	①③④⑥⑦
EA	④⑥②③⑦
TA	①③④⑥⑦⑧⑦
CA	④⑤②③⑦⑧⑦

Operation strategy	Average loss of attack UAVs	Average number of ground facilities destroyed	Cost-effectiveness ratio	Average number of bombs consumed	Average task completion time
EO	4.17	3.986	1.046	35.272	23.468
TO	3.89	3.516	1.106	32	14.306
CO	3.39	3.496	0.970	16	21.976
EA	4.082	2.95	1.384	16	13.922
TA	4.634	3.934	1.178	19.784	26.138
CA	5.99	3.348	1.789	31.46	14.447
Average	4.359	3.538	1.246	25.086	19.043

[1]	Yuelong LUO, Xiuqiang JIANG, Suchuan ZHONG, Yuandong JI. Air-to-ground reconnaissance-attack task allocation for heterogeneous UAV swarm [J]. Journal of Systems Engineering and Electronics, 2025, 36(1): 155-175.
[2]	Zhiwen XIAO, Xiaowei FU. A cooperative detection game: UAV swarm vs. one fast intruder [J]. Journal of Systems Engineering and Electronics, 2023, 34(6): 1565-1575.
[3]	Boyu QIN, Dong ZHANG, Shuo TANG, Yang XU. Two-layer formation-containment fault-tolerant control of fixed-wing UAV swarm for dynamic target tracking [J]. Journal of Systems Engineering and Electronics, 2023, 34(6): 1375-1396.
[4]	Yaozhong ZHANG, Yike LI, Zhuoran WU, Jialin XU. Deep reinforcement learning for UAV swarm rendezvous behavior [J]. Journal of Systems Engineering and Electronics, 2023, 34(2): 360-373.
[5]	Jie LI, Xiaoyu DANG, Sai LI. DQN-based decentralized multi-agent JSAP resource allocation for UAV swarm communication [J]. Journal of Systems Engineering and Electronics, 2023, 34(2): 289-298.
[6]	Hao LI, Hemin SUN, Ronghua ZHOU, Huainian ZHANG. Hybrid TDOA/FDOA and track optimization of UAV swarm based on A-optimality [J]. Journal of Systems Engineering and Electronics, 2023, 34(1): 149-159.
[7]	Yangyang JIANG, Yan GAO, Wenqi SONG, Yue LI, Quan QUAN. Bibliometric analysis of UAV swarms [J]. Journal of Systems Engineering and Electronics, 2022, 33(2): 406-425.
[8]	Jinqiang HU, Husheng WU, Renjun ZHAN, Rafik MENASSEL, Xuanwu ZHOU. Self-organized search-attack mission planning for UAV swarm based on wolf pack hunting behavior [J]. Journal of Systems Engineering and Electronics, 2021, 32(6): 1463-1476.