A Real-Time Anomaly Detection in Satellite Telemetry Data Using Artificial Intelligence Techniques Depending on Time-Series Analysis

Document Type : Original Article


High Institute for Computers and Information Technology AL-Shorouk Academy


To effectively detect and identify the anomaly data in massive satellite telemetry data 
sets, the novel detection and identification method based on the Auto-regressive integrated 
moving average (ARIMA), Prophet, Long Short Term Memory (LSTM), and Auto-encoder 
algorithms were proposed in this paper. The proposed model is used to find anomalous events 
by comparing the actual observed values with the predicted intervals of telemetry data.
First, preprocessing for the raw telemetry data were Handled for the missing values using 
linear interpolation. Second, Down-casting to reduce the memory storage. Based on this 
symbolization, the pseudo-period of the data was extracted. Third, the Data Transformation and 
Scaling to normalize the data within a particular range to helps in speeding up the calculations
were applied. Finally, the experimental results for the Prophet model show predictions with high 
efficiency, stable when detecting anomalies, and requires little computational time. The results of 
Prophet compared with other applied algorithms, demonstrate the effectiveness and superiority 
of the proposed model. 


Main Subjects