资源分布视角下区域保障调度模型研究

doi:10.12305/j.issn.1001-506X.2024.09.21

摘要/Abstract

摘要：

区域作战中, 装备保障需求呈现出一定分布特征, 保障供应也随时动态变化, 如何匹配供需进而进行保障调度成为提升区域保障能力的关键。针对区域资源供需的分布特性, 运用最优传输理论, 建立资源分布视角下区域保障调度模型。首先, 构建分布视角下的区域保障调度基本模型, 考虑决策层级将其拓展为多分辨率模型, 然后基于sinkhorn算法提出保障调度概率方案作为转换, 进而给出多分辨率模型的保障调度方案求解算法。案例分析表明, 非指数分布和自由竞争环境下, 保障调度方案具有鲁棒性。

关键词: 装备保障, 资源分布, 保障调度, 最优传输

Abstract:

In regional operations, equipment guarantee needs exhibit distribution characteristics, and guarantee supply also dynamically changes. How to match supply and demand and then guarantee shceduling has become the key to improving regional guarantee capabilities. Based on the distribution characteristics of regional resource supply and demand, the optimal transmission theory is applied to establish a regional guarantee scheduling model from the perspective of resource distribution. Firstly, a basic model of regional guarantee scheduling is constructed from a distributed perspective, and considered expanding it into a multi resolution model at the decision-making level. And then, a guarantee scheduling probability scheme is proposed based on the sinkhorn algorithm as a transformation, and provided a solution algorithm for the multi resolution model. Case analysis shows that under non exponential distribution and free competition environments, the guarantee scheduling scheme has robustness.

Key words: equipment guarantee, resource distribution, guarantee scheduling, optimal transmission

中图分类号:

TJ02

胡志刚, 楼京俊, 史跃东. 资源分布视角下区域保障调度模型研究[J]. 系统工程与电子技术, 2024, 46(9): 3093-3102.

Zhigang HU, Jingjun LOU, Yuedong SHI. Research on regional guarantee scheduling model from the perspective of resource distribution[J]. Systems Engineering and Electronics, 2024, 46(9): 3093-3102.

图/表 12

表1

表2

表3

图1

图2

图3

图4

图5

图6

表4

表5

图7

参考文献 33

1	曹军海, 郭一鸣, 张闯, 等. 复杂装备维修保障模式和人力资源仿真优化研究[J]. 系统仿真学报, 2021, 33 (10): 2307- 2314.
	CAO J H , GUO Y M , ZHANG C , et al. Research on simulation and optimization of maintenance support mode and human resources auocation for complex equipment[J]. Journal of System Simulation, 2021, 33 (10): 2307- 2314.
2	杨帆, 王铁宁, 高晟. 面向任务的装备器材需求预测[J]. 火力与指挥控制, 2021, 46 (4): 48- 53. doi: 10.3969/j.issn.1002-0640.2021.04.009
	YANG F , WANG T N , GAO S . Demand forecasting of equipment materials oriented to tasks[J]. Fire Control & Command Control, 2021, 46 (4): 48- 53. doi: 10.3969/j.issn.1002-0640.2021.04.009
3	王琮, 沈会良, 夏永祥, 等. 装备保障体系关键节点分析[J]. 系统工程与电子技术, 2022, 44 (10): 3134- 3142. doi: 10.12305/j.issn.1001-506X.2022.10.17
	WANG C , SHEN H L , XIA Y X , et al. Analysis of critical nodes in equipment support system[J]. Systems Engineering and Electronics, 2022, 44 (10): 3134- 3142. doi: 10.12305/j.issn.1001-506X.2022.10.17
4	王坚浩, 张亮, 史超, 等. 装备保障任务分配建模与DLS-BCIWBA算法求解[J]. 系统工程与电子技术, 2018, 40 (9): 1979- 1985. doi: 10.3969/j.issn.1001-506X.2018.09.13
	WANG J H , ZHANG L , SHI C , et al. Task allocation modeling and solving algorithm for equipment support using DLS-BCIWBA[J]. Systems Engineering and Electronics, 2018, 40 (9): 1979- 1985. doi: 10.3969/j.issn.1001-506X.2018.09.13
5	李峻森, 方依宁, 张云安, 等. 面向任务的装备保障体系多Agent建模与评估方法[J]. 系统工程与电子技术, 2023, 45 (1): 279- 290. doi: 10.12305/j.issn.1001-506X.2023.01.33
	LI J S , FANG Y N , ZHANG Y A , et al. Multi-agent modeling and evaluation method for mission-oriented equipment support SoS[J]. Systems Engineering and Electronics, 2023, 45 (1): 279- 290. doi: 10.12305/j.issn.1001-506X.2023.01.33
6	MAO W T , LIU J , CHEN J X , et al. An interpretable deep transfer learning-based remaining useful life prediction approach for bearings with selective degradation knowledge fusion[J]. IEEE Trans.on Instrumentation and Measurement, 2022, 71, 3508616.
7	MAO W T , LIU K Y , ZHANG Y N , et al. Self-supervised deep tensor domain-adversarial regression adaptation for online remaining useful life prediction across machines[J]. IEEE Trans.on Instrumentation and Measurement, 2023, 72, 2509916.
8	LIU P P , MING W , HUANG C C . Intelligent modeling of abnormal demand forecasting for medical consumables in smart city[J]. Environmental Technology & Innovation, 2020, 20 (1): 1104- 1111.
9	BABAI M Z , CHEN H , SYNTETOS A A , et al. A compound-poisson Bayesian approach for spare parts inventory forecasting[J]. International Journal of Production Economics, 2020, 232 (8): 107954.
10	BAISARIYEV M , BAKYTZHANULY A , SERIK Y , et al. Demand forecasting methods for spare parts logistics for aviation: a real-world implementation of the bootstrap method[J]. Procedia Manufacturing, 2021, 55 (11): 500- 506.
11	GABRIEL P , MARCO C . Computational optimal transport[M]. Cham: Springer, 2018.
12	CUTURI M. Sinkhorn distances: lightspeed computation of optimal transport[C]//Proc. of the 26th International Confe-rence on Neural Information Processing Systems, 2013.
13	GENEVAY A, PEYRE G, CUTURI M. Learning generative models with sinkhorn divergences[C]//Proc. of the 21st International Conference on Artificial Intelligence and Statistics, 2018.
14	GENEVAY A, CHIZAT L, BACH F, et al. Sample complexity of sinkhorn divergences[C]//Proc. of the 22nd International Conference on Artificial Intelligence and Statistics, 2018.
15	GENEVAY A, PEYRE G, CUTURI M. Learning generative models with sinkhorn divergences[C]//Proc. of the International Conference on Artificial Intelligence and Statistics, 2018.
16	BRANDON A, LEI X, KOLTER J Z. Input convex neural networks[C]//Proc. of the International Conference on Machine Learning, 2017: 146-155.
17	MUHAMMAD A, MAX D, OSCAR L, et al. Invertible generative models for inverse problems: mitigating representation error and dataset bias[C]//Proc. of the International Confe-rence on Machine Learning, 2020: 399-409.
18	SEBASTIAN B , AXEL R , JONAS A , et al. Data-driven nonsmooth optimization[J]. SIAM Journal on Optimization, 2020, 30 (1): 102- 131. doi: 10.1137/18M1207685
19	JOSHUA B, LOIC R. Noise2self: blind denoising by self-supervision[C]//Proc. of the International Conference on Machine Learning, 2019: 524-533.
20	GEORGIOS B, MARCELLO C, CHRISTIAN E, et al. CAFLOW: conditional autoregressive flows[EB/OL]. [2023-10-04]. http://doi.org/10.48550/arXiv.2106.02531.
21	BLONDEL M, SEGUY V, ROLET A. Smooth and sparse optimal transport[C]//Proc. of the 21st International Conference on Artificial Intelligence and Statistics, 2018.
22	CUTURI M, KLEIN M, ABLIN P. Monge, bregman and occam: interpretable optimal transport in high-dimensions with feature-sparse maps[C]//Proc. of the 40th International Conference on Machine Learning, 2023: 6671-6682.
23	GRAVE E, JOULIN A, BERTHET Q. Unsupervised alignment of embeddings with wasserstein procrustes[C]//Proc. of the 22nd International Conference on Artificial Intelligence and Statistics, 2019: 1880-1890.
24	MARTIN A, SOUMITH C, LEON B. Wasserstein generative adversarial networks[C]//Proc. of the 34th International Conference on Machine Learning, 2017: 214-223.
25	NEKRASHEVICH M, KOROTIN A, BURNAEV E. Neural Gromov-Wasserstein optimal transport[EB/OL]. [2023-10-04]. http://doi.org/10.48550/arXiv.2303.05978.
26	NILES-WEED J , RIGOLLET P . Estimation of Wasserstein distances in the spiked transport model[J]. Bernoulli: Official Journal of the Bernoulli Society for Mathematical Statistics and Probability, 2022, 28 (4): 2663- 2688.
27	ZHANG Z X, GOLDFELD Z, MROUEH Y, et al. Gromov-Wasserstein distances: entropic regularization, duality, and sample complexity[EB/OL]. [2023-10-04]. http://doi.org/10.48550/arXiv.2212.12848.
28	RIOUX G, GOLDFELD Z, KATO K. Entropic Gromov-Wasserstein distances: stability, algorithms, and distributional li-mits[EB/OL]. [2023-10-04]. http://doi.org/10.48550/arXiv.2306.00182.
29	JANATI H, CUTURI M, GRAMFORT A. Wasserstein regularization for sparse multi-task regression[C]//Proc. of the 22nd International Conference on Artificial Intelligence and Statistics, 2019: 1407-1416.
30	SCETBON M, KLEIN M, PALLA G, et al. Unbalanced low-rank optimal transport solvers[EB/OL]. [2023-10-04]. http://doi.org/10.48550/arXiv.2305.19727.
31	AMBROGIONI L, GUCLU U, GERVEN M V. Wasserstein variational gradient descent: from semi-discrete optimal transport to ensemble variational inference[EB/OL]. [2023-10-04]. http://doi.org/10.48550/arXiv.1811.02827.
32	BACKURS A, DONG Y, INDYK P, et al. Scalable nearest neighbor search for optimal transport[C]//Proc. of the International Conference on Machine Learning, 2020: 497-506.
33	PEYRE G , CUTURI M . Computational optimal transport: with applications to data science[J]. Foundations and Trends in Machine Learning, 2019, 11 (56): 355- 607.

保障机构	u_i	保障单元	X_ik, h_ik
X₁	30	X₁₁	[8, 22, 12]
		X₁₂	[16, 18, 11]
		X₁₃	[18, 13, 7]
X₂	30	X₂₁	[58, 22, 11]
		X₂₂	[55, 19, 11]
		X₂₃	[50, 15, 8]
X₃	20	X₃₁	[25, 8, 10]
X₃	20	X₃₂	[48, 9, 10]
X₄	20	X₄₁	[28, 23, 25]
X₄	20	X₄₂	[39, 22, 21]
X₅	20	X₅₁	[36, 19, 17]
X₅	20	X₅₂	[37, 18, 17]

保障机构	v_j	保障单元	y_jl, g_jl
Y₁	22	Y₁₁	[18, 18, 6]
		Y₁₂	[30, 19, 5]
		Y₁₃	[40, 18, 4]
		Y₁₄	[50, 19, 7]
Y₂	75	Y₂₁	[8, 26, 12]
		Y₂₂	[18, 28, 13]
		Y₂₃	[28, 27, 15]
		Y₂₄	[38, 26, 11]
		Y₂₅	[48, 28, 10]
		Y₂₆	[58, 27, 14]
Y₃	48	Y₃₁	[12, 22, 10]
		Y₃₂	[22, 21, 8]
		Y₃₃	[35, 21, 9]
		Y₃₄	[44, 22, 11]
		Y₃₅	[55, 22, 10]
Y₄	15	Y₄₁	[26, 13, 3]
		Y₄₂	[38, 13, 2]
		Y₄₃	[48, 13, 3]
		Y₄₄	[32, 8, 2]
		Y₄₅	[45, 8, 5]

θ_ji	Y₁	Y₂	Y₃	Y₄
X₁	1e-3	1	1	1e3
X₂	1e3	1e-3	1	1
X₃	1	1e3	1e-3	1
X₄	1	1	1e3	1e-3
X₅	1	1	1	1

类型	供应分布	需求分布	方案余弦距离的误差均值	方案方差的误差均值
供应分布不变，需求分布变化	normrnd(30, 2, 5, 1)	normrnd(30, 2, 1, 4)	0.993 6	0.384 2
	normrnd(30, 2, 5, 1)	exprnd(40, [1, 4])	0.722 0	31.967 9
	normrnd(30, 2, 5, 1)	unifrnd(30, 40, 1, 4)	0.996 0	0.402 4
供应分布变化，需求分布不变	normrnd(60, 2, 5, 1)	normrnd(30, 2, 1, 4)	0.996 5	0.166 4
	exprnd(40, [5, 1])	normrnd(30, 2, 1, 4)	0.580 6	92.287 2
	unifrnd(20, 40, 5, 1)	normrnd(30, 2, 1, 4)	0.966 7	3.444 8

类型	供应分布	需求分布	方案余弦距离的误差均值	方案方差的误差均值
供应分布不变，需求分布变化	normrnd(30, 2, 50, 1)	normrnd(30, 2, 1, 40)	0.993 2	0.000 33
	normrnd(30, 2, 50, 1)	exprnd(40, [1, 40])	0.508 8	0.477 0
	normrnd(30, 2, 50, 1)	unifrnd(30, 40, 1, 40)	0.991 2	0.004 2
供应分布变化，需求分布不变	normrnd(60, 2, 50, 1)	normrnd(30, 2, 1, 40)	0.994 5	0.002 0
	exprnd(40, [50, 1])	normrnd(30, 2, 1, 40)	0.547 0	0.784 9
	unifrnd(20, 40, 50, 1)	normrnd(30, 2, 1, 40)	0.962 9	0.032 2