Interference detection and classification

Interference detection is still an important topic. Most of the interferences present today are caused by human errors – either due to mispointed antenna (cross-polarization or adjacent satellite) or misconfigured equipment (noise introduction, intermodulation, etc.). These parameters cover 70-80% of all interference cases and are not related to terrestrial networks. If there are carrier overlaps, it implies a digital video broadcasting (DVB) carrier overlapping another DVB carrier or a satellite modem transmission, including very small aperture terminal (VSAT) traffic in time division multiple access (TDMA), for instance.

In order to mitigate them, there are several techniques that may help to reduce the levels of interferences. However, in many occasions, it is still difficult to cope with them. Currently, the only way to manage interference is by human intervention and performing an exhaustive analysis, that may take several days to solve the incidence. In other words, there are qualified personnel dedicated to detecting interferences by inspecting figures, such as the spectrum, abnormal error rates increase or degraded user experience.

Autoencoding for Interference Detection

For the aforementioned interference detection problem, we rely on an unsupervised ML model called autoencoder. This technique allows to reproduce the inputs based on its previous training. If the inputs are similar to the training data set, the output is also similar. However, if the inputs are significantly different to the training, the output is completely different. Hence, measuring the error between both signals, it is possible to detect signal perturbations that modify the characteristics of the original signal. For our case, the autoencoder is composed by an encoding convolutional neural network (CNN) and a decoding CNN, stacked sequentially.

The encoder compresses the data blocks and reduces the dimensionality of the input. The data is passed to the decoder, that increases the dimensions and restores the original dimension. The crucial aspect of this approach is the fact that the autoencoder is trained with known sequences and it can recreate the input if it is similar to some of the trained inputs. Particularly, CNN are specially indicated for fixed size inputs and they are capable to extract hidden patterns from the data. Our proposed autoencoding neural network (ANN) is composed by several convolutional and decimating layers, placed sequentially as depicted in the following figure.

CNN architecture for interference detection.
CNN architecture for interference detection.

Deep Learning for Interference Classification & Identification

Upon an interference detection, it is also important to classify the interference to narrow the search of possible interfering sources. This task is not always easy since it requires hard dedication to identify the source of interference. Usually, this task is performed manually by operators. The transmission of allowed signals is stopped during this task in order to maximize the chance of identifying the source.

Obviously, stopping the communication while this task is carried is not the optimal solution. Hence, we propose the implement this task by using a DNN model trained previously with different waveforms corresponding to different Radio Access Networks, such as LTE, UMTS or GSM.

By training a DNN with a DVB-S2 signal interfered with LTE, UTMS or GSM, we are able to perform classification based on these patterns. For this purpose, we design a Neural Network with a single layer based on Long Short-Term Memory (LSTM) Network. This network is suitable for training networks based on time series signals, such as radio signals.

LSTM networks manage to keep contextual information of inputs by integrating a loop that allows information to flow from one step to the next. In contrast to CNN, LSTM networks do not use neurons as processing units, but elementary cells.

Related Resources