Multi-Satellite Resource Scheduling Based on Deep Neural Network

Resource scheduling is one of the main problems for multi-satellite Tracking, Telemetry and Command (TT&C) networks. Traditional multi-resource joint scheduling algorithms are with long solution time, low efficiency, high computational cost, and simple description on the system. Deep Neural Network (DNN) provides a possible new way to solve those problems, but it is difficult to handle correlations among the input data. This motivates our work to solve the strong correlation problem based on the accumulated historical data, and thus enables DNN for TT&C resource scheduling. By discretizing the data, multiple constraints and related attributes are transformed into different flags, and some binary bits of the data are used to reflect the constraint relationship. Then, we can use DNN model and construct an intelligent TT&C resource scheduling system to handle multiple constraints and data attributes (such as priorities among tasks and others). This improves the efficiency of TT&C resources utilization and automation. Effectiveness of the proposed model is verified by simulations.

[1]  Gilbert Laporte,et al.  Maximizing the value of an Earth observation satellite orbit , 2005, J. Oper. Res. Soc..

[2]  Yingwu Chen,et al.  An adaptive large neighborhood search metaheuristic for agile satellite scheduling with time-dependent transition time , 2017, Comput. Oper. Res..

[3]  Zuren Feng,et al.  An Optimization Model for Multisatellite Resources Scheduling , 2006, 2006 6th World Congress on Intelligent Control and Automation.

[4]  Liu Son.  Prediction Method for Imaging Task Schedulability of Earth Observation Network , 2015 .

[5]  Daniel Vanderpooten,et al.  Enumeration and interactive selection of efficient paths in a multiple criteria graph for scheduling an earth observing satellite , 2002, Eur. J. Oper. Res..

[6]  Hussein A. Abbass,et al.  Evolutionary multi-objective resource allocation and scheduling in the Chinese navigation satellite system project , 2016, Eur. J. Oper. Res..

[7]  Collin Green,et al.  Analogical and Case-Based Reasoning for Predicting Satellite Task Schedulability , 2005, ICCBR.

[8]  Djamal Habet,et al.  Bounding the optimum for the problem of scheduling the photographs of an Agile Earth Observing Satellite , 2010, Comput. Optim. Appl..

[9]  Jin-Kao Hao,et al.  A “Logic-Constrained” Knapsack Formulation and a Tabu Algorithm for the Daily Photograph Scheduling of an Earth Observation Satellite , 2001, Comput. Optim. Appl..

[10]  Dwi Hendratmo Widyantoro,et al.  Comparison study of neural network and deep neural network on repricing GAP prediction in Indonesian conventional public bank , 2016, 2016 6th International Conference on System Engineering and Technology (ICSET).

[11]  Nicolas Zufferey,et al.  Graph colouring approaches for a satellite range scheduling problem , 2008, J. Sched..

[12]  Virginie Gabrel.  Strengthened 0-1 linear formulation for the daily satellite mission planning , 2006, J. Comb. Optim..

[13]  Wu Xiao-yue.  Analysis of requirement and task description method of multi-satellite TT&C scheduling problem , 2009 .

[14]  Jin-Kao Hao,et al.  Upper Bounds for the SPOT 5 Daily Photograph Scheduling Problem , 2003, J. Comb. Optim..

[15]  Sara Spangelo,et al.  Optimization-based scheduling for the single-satellite, multi-ground station communication problem , 2015, Comput. Oper. Res..

[16]  Bin Wang,et al.  Research on CSP Model for Complex TT&C Task Scheduling , 2012 .

[17]  Maria Trocan,et al.  Deep neural network based single pixel prediction for unified video coding , 2018, Neurocomputing.

[18]  Joseph C. Pemberton,et al.  A constraint-based approach to satellite scheduling , 1998, Constraint Programming and Large Scale Discrete Optimization.

[19]  Na Zhang,et al.  Ant colony algorithm for satellite control resource scheduling problem , 2018, Applied Intelligence.

[20]  Lixin Wu,et al.  Imaging-Duration Embedded Dynamic Scheduling of Earth Observation Satellites for Emergent Events , 2015 .

[21]  Li Jing,et al.  An adaptive genetic algorithm for solving ground-space TT&C resources integrated scheduling problem of Beidou constellation , 2014, Proceedings of 2014 IEEE Chinese Guidance, Navigation and Control Conference.

[22]  Jing Li,et al.  Multi-objective TT&C Mission Planning Technique for On-Orbit Service , 2013, 2013 International Conference on Information Science and Cloud Computing Companion.

[23]  Xing Xie,et al.  Satellite mission scheduling based on genetic algorithm , 2010, Kybernetes.

[24]  Jian Bai,et al.  A Multi-dimensional Genetic Algorithm for Spacecraft TT&C Resources Unified Scheduling , 2016 .

[25]  Chen Ying-wu.  Agile earth observing satellites mission scheduling based on decomposition optimization algorithm , 2013 .

[26]  Jianghan Zhu,et al.  Multi-satellite observation integrated scheduling method oriented to emergency tasks and common tasks , 2012 .

[27]  Gérard Verfaillie,et al.  Exact &INEXACT Methods for Daily Management of Earth Observation Satellite , 1996 .

[28]  Maged M. Dessouky,et al.  A genetic algorithm approach for solving the daily photograph selection problem of the SPOT5 satellite , 2010, Comput. Ind. Eng..

[29]  Gerhard Reinelt,et al.  Priority-based and conflict-avoidance heuristics for multi-satellite scheduling , 2018, Appl. Soft Comput..