A precedence-rule-based heuristic for satellite onboard activity planning

Liang, J.; Zhu, Yue-he; Luo, Yuling; Zhang, Jiacheng; Zhu, Hai

doi:10.1016/j.actaastro.2020.10.020

Cited by 14 publications

(9 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…But this method greatly needs expert knowledge to make complex rules of execution. It is also less scalable for additional tasks and optimality is not always guaranteed [8]. A genetic algorithm (GA) is another alternative to deal with complex problems such as task scheduling.…”

Section: Autonomous Task Schedulingmentioning

confidence: 99%

“…Scheduling of Earth observation satellites' imaging tasks is generally regarded as an optimization problem and many researchers proposed the implementation of different approaches for solving the problem. Liang et.al [8] proposed a heuristic algorithm for subsystem-level onboard task scheduling, which is designed by considering the precedence of onboard tasks and resources needed by target subsystems executing these tasks and reported that the algorithm generated satisfactory scheduling results in a shorter period. In [9,10] studies, customized heuristic algorithms are designed to support the objective function and competent results are reported with shorter computation time.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A New Strategy of Satellite Autonomy with Machine Learning for Efficient Resource Utilization of a Standard Performance CubeSat

Zeleke

Kim

2023

Aerospace

View full text Add to dashboard Cite

A mega constellation of Nano/microsatellites is the contemporary solution for global-level Earth observation demands. However, as most of the images taken by Earth-observing satellites are covered by clouds, storing and downlinking these images results in inefficient utilization of scarce onboard resources and bandwidth. In addition, the trend of making satellite task execution plans by ground operators demands the efforts of experts or simulators to predict the real-time situation of satellites and to decide which tasks should be executed next. Granting controlled autonomy to satellites to perform onboard tasks will boost mission effectiveness. We experimented with granting controlled autonomy for satellites in performing onboard image classification and task scheduling. We designed a convolutional neural network-based binary image classification model with more than 99% accuracy in classifying clear and cloudy images. The model is configured to perform inference in low-performance computers of ordinary Cubesats. Moreover, we designed an autonomous satellite task scheduling mechanism based on reinforcement learning. It performs better than a custom heuristic-based method in scheduling onboard tasks. As a result, the proposed classification and scheduling techniques with machine learning ensured efficient utilization of onboard memory, power, and bandwidth in the highly resource-constrained CubeSat platforms and mission accomplishment of Nano/microsatellite constellations.

show abstract

Section: Autonomous Task Schedulingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A New Strategy of Satellite Autonomy with Machine Learning for Efficient Resource Utilization of a Standard Performance CubeSat

Zeleke

Kim

2023

Aerospace

View full text Add to dashboard Cite

show abstract

“…Element J OB Shop Scheduling Problem (JSSP) has risen as one of the most relevant Combinatorial Optimization Problems (COPs) [1]. This kind of problem has several applications, mainly those related to manufacturing [2]- [6]. The idea in a JSSP is to organize the execution of jobs (tasks) to optimize their processing.…”

Section: Index Termsmentioning

confidence: 99%

“…Update x a, * , x n, * , and x * using Equations (6) to (8) the fitness from the previous step 11: q ← q + 1 12: end while 13: Generate I * by reshaping x * into a JSSP instance as shown in Figure 3 longer to complete (i.e., Largest Processing Time, LPT), the other targets small jobs first (i.e., Shortest Processing Time, SPT). Similarly, we include two heuristics that seek to schedule a whole job quickly or evenly schedule them all.…”

mentioning

confidence: 99%

Tailoring Job Shop Scheduling Problem Instances Through Unified Particle Swarm Optimization

et al. 2021

View full text Add to dashboard Cite

“…Another challenging task where HHs have proved useful is to solve Job Shop Scheduling Problems (JSSPs). This problem has multiple applications to real-life scenarios, especially those related to manufacturing [18]- [23]. So, it is natural that the JSSP has been tackled with different methods.…”

mentioning

confidence: 99%

Beyond Hyper-Heuristics: A Squared Hyper-Heuristic Model for Solving Job Shop Scheduling Problems

et al. 2022

View full text Add to dashboard Cite

Hyper-heuristics (HHs) stand as a relatively recent approach to solving optimization problems. There are different kinds of HHs. One of them deals with how low-level heuristics must be combined to deliver an improved solution to a set of problem instances. Literature commonly refers to them as selection hyper-heuristics. One of their advantages is that the strengths of each heuristic can be fused into a highlevel solver. However, one of their drawbacks is that sometimes this generalization scheme does not suffice. Additionally, it is not easy to reuse these HHs since the model cannot be easily tweaked. So, in this work, we develop a hyper-heuristic model with an additional layer of generalization. The rationale behind it is to preserve the general structure of selecting an adequate solver for a particular situation but to use HHs instead of low-level heuristics. We call this model a Squared Hyper-Heuristic (SHH). To validate our proposal, we pursue a four-stage methodology that covers several testing scenarios. Our data reveal that, under proper conditions, our model can outperform the base HHs. Moreover, it is flexible enough to allow for an increased number of layers so that the complexity of the final model can be tuned. Additionally, different kinds of instances can be used to train each stage of the model, thus setting the groundwork for developing a transfer learning approach for hyper-heuristics.

show abstract

A precedence-rule-based heuristic for satellite onboard activity planning

Cited by 14 publications

References 25 publications

A New Strategy of Satellite Autonomy with Machine Learning for Efficient Resource Utilization of a Standard Performance CubeSat

A New Strategy of Satellite Autonomy with Machine Learning for Efficient Resource Utilization of a Standard Performance CubeSat

Tailoring Job Shop Scheduling Problem Instances Through Unified Particle Swarm Optimization

Beyond Hyper-Heuristics: A Squared Hyper-Heuristic Model for Solving Job Shop Scheduling Problems

Contact Info

Product

Resources

About