Offline-Online Multiple Agile Satellite Scheduling using Learning and Evolutionary Optimization
Bibliographic record
Abstract
The recent generation of Agile Earth Observation Satellite (AEOS) has emerged to be highly effective due to its increased attitude maneuvering capabilities. However, due to these increased degrees of freedom in maneuverability, the scheduling problem has become increasingly difficult than its non-agile predecessors. The AEOS scheduling problem consists of finding an optimal assignment of user-requested imaging tasks to the respective AEOSs in their orbits by satisfying the operational resource constraints in a specified time frame. Some of these tasks might require imaging the same area of interest (AOI) multiple times, while in some tasks, the AOIs are too large for the AEOS to image in a single attempt. Some tasks might even arise while the AEOSs are preoccupied with existing tasks. This thesis focuses on formulating the AEOS scheduling models where onboard energy and memory constraints while operating and the task specifications are diverse. A mixed-integer non-linear scheduling problem with a reward factor has been considered in order to handle multiple scan requirements for a task. Although initially, it is assumed that the AOIs are small, this work is extended to a three-stage optimization framework to handle the segmentation of large AOIs into smaller regions that can be imaged in a single scan. The uncertainty regarding scan failure is handled through a Markov Decision Process (MDP). These two proposed methods have significant benefits when tasks are available to schedule prior to the mission. However, they lack the flexibility to accommodate newly arrived tasks during the mission. When multiple new tasks arrive during the mission, predictive scheduling based on learning historical data of task arrivals is proposed, which can schedule tasks in an online manner faster than complete rescheduling and minimize disruption from the original schedule. Evolutionary optimization-based solution methodologies are proposed to solve these models and are validated with simulations.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".