The steadily growing use of license-free frequency bands requires reliable coexistence management for deterministic medium utilization. For interference mitigation, proper wireless interference identification (WII) is essential.In this work we propose the first WII approach based upon deep convolutional neural networks (CNNs). The CNN naively learns its features through self-optimization during an extensive data-driven GPU-based training process. We propose a CNN example which is based upon sensing snapshots with a limited duration of 12.8 µs and an acquisition bandwidth of 10 MHz. The CNN differs between 15 classes. They represent packet transmissions of IEEE 802.11 b/g, IEEE 802.15.4 and IEEE 802.15.1 with overlapping frequency channels within the 2.4 GHz ISM band. We show that the CNN outperforms state-ofthe-art WII approaches and has a classification accuracy greater than 95 % for signal-to-noise ratio of at least -5 dB.

The steadily growing use of license-free frequency bands requires reliable coexistence management and therefore proper wireless interference identification (WII). In this work, we propose a WII approach based upon a deep convolutional neural network (CNN) which classifies multiple IEEE 802.15.1, IEEE 802.11 b/g and IEEE 802.15.4 interfering signals in the presence of a utilized signal. The generated multi-label dataset contains frequency-and time-limited sensing snapshots with the bandwidth of 10 MHz and duration of 12.8 µs, respectively. Each snapshot combines one utilized signal with up to multiple interfering signals.The approach shows promising results for same-technology interference with a classification accuracy of approximately 100 % for IEEE 802.15.1 and IEEE 802.15.4 signals. For IEEE 802.11 b/g signals the accuracy increases for cross-technology interference with at least 90 %.

Novel industrial wireless applications require wideband, real-time channel characterization due to complex multipath propagation. Rapid machine motion leads to fast time variance of the channel's reflective behavior, which must be captured for radio channel characterization. Additionally, inhomogeneous radio channels demand highly flexible measurements. Existing approaches for radio channel measurements either lack flexibility or wide-band, real-time performance with fast time variance.In this paper, we propose a correlative channel sounding approach utilizing a software-defined architecture. The approach enables real-time, wide-band measurements with fast time variance immune to active interference. The desired performance is validated with a demanding industrial application example.

The factories of the future will be highly digitalized in order to enable flexible and interconnected manufacturing processes. Especially wireless technologies will be beneficial for industrial automation. However, the high density of metallic objects is challenging for wireless systems due to multipath fading. In order to understand the signal propagation in industrial environments, this paper provides results from a number of channel measurement campaigns funded by the German research initiative “Reliable wireless communication in the industry”. We give an overview of different measurement scenarios covering visible light communication and radio communication below 6 GHz. We analyze large and small scale parameters as well as delay statistics of the wireless channels. Finally, we discuss the importance of the results for the definition of industrial channel models.

No abstract