Optimization of the battery usage during eclipses using a machine learning approach

Abstract

During eclipses, the spacecraft cannot rely on solar energy and must exploit the power coming from the on-board batteries. Critical for the payload is to maintain its temperature inside a specific predetermined range to avoid degradation and malfunctioning. For XMM-Newton, this is done through the Temperature Closed Loop (TCL) unit, which automatically turns on and off the heaters when the instruments reach the minimum and maximum temperatures, respectively. A possible scenario is the case when more than a single instrument reaches the minimum temperature simultaneously, thus causing a peak in the demand of power from the batteries and threatening their integrity. Such a circumstance may impact the overall mission and a better battery management is therefore required. Here we propose a solution that uses machine learning to optimize the battery consumption during eclipses. We show that after training the algorithm with past data, we are able to predict the temperature profiles of the instruments with good accuracy. These predictions provide the relevant insight to determine the optimal times at which the heaters should be turned on and off, thus improving and optimizing the current eclipse operations. The approach presented here helps overcome the issue of excessively stressing the batteries and, despite being tailored for XMM-Newton, can be extended and applied to other missions as well.

Machine Learning for Predicting Thermal Power Consumption of the Mars Express Spacecraft

“…In our previous work [4], we propose a solution for predicting spacecraft's power consumption, which can be used for optimizing its operation. This works closely relates to the one of [17], where the authors propose Random Forests for predicting temperature of the instruments to optimize battery usage during eclipses.…”

“…Finally, while the proposed methodology focuses on the thermal subsystem of the MEX spacecraft, it can also be readily applied to the other subsystems. Moreover, it can also be extended to other spacecraft such as the XMM Newton [17], Integral [20] and ExoMars as well as rovers (such as Curiosity and ExoMars) exploring Mars.…”

Machine Learning Modeling Methods for Radiation Belts Profile Predictions

“…One promising avenue of investigation is based on data analytic techniques and machine learning algorithms. These techniques have been applied successfully to several test case including optimising power consumption for currently, or formerly, active European Space Agency satellites, VEX [4], MEX [5][6] & XMM-Newton [7] during their respective eclipse seasons where power generation is severely constrained but significant power load can still exist, particularly to maintain the satellites thermal equilibrium while in the eclipse umbra. Thus far machine learning data analytics have not been actively used operationally for ESA satellites but show great potential for optimisation and automation of certain space activities particularly when large amount of continuous data is available.…”