Spectrum-NET is a cloud-native, horizontally scalable solution based on a Kubernetes-orchestrated microservices architecture. With the option for AWS hosting, Spectrum-NET automatically ingests and analyzes RAN data from NR and LTE RAN equipment. Spectrum-NET integrates with other tools (e.g., collaboration systems, network topology databases, trouble ticket systems, SON tools) to maximize automation. Spectrum-NET supports SMO/non-RT RIC for greenfield and brownfield implementations.

Spectrum-NET incorporates Deep Convolutional Neural Network models that are trained offline with labeled measurement samples (interference signatures from known interference cases) from mobile operator networks across the globe. Labeled data is added to the ML training data set and used for future classifications.

Spectrum-NET enables operators to rapidly resolve harmful RF interference, improve network KPIs, increase network capacity, and strategically deploy scarce field resources. Operators across the globe deploy Spectrum-NET to drive RF interference mitigation processes and effectively address RF network interference. Spectrum-NET provides a valuable new perspective on RF interference by enhancing visibility into spectral efficiency, quantifying performance by RF band, and providing key insights for making sound spectrum investments and strategies.

Learn more about the most significant RF interference challenges and the benefits of Spectrum-NET.

• Identifies cells with external interference with high accuracy using ML-trained CNNs.
• Determines damaging external interference source types in consumer, industrial and government networks.
• Characterizes external RF interference by time, frequency and intensity.
• Aggregates all cells impacted by the common interference signature.
• Locates the interference source by analyzing interference magnitudes at each cell and applying weighted Bayesian inference. Applies horizontal and vertical antenna radiation pattern and Topography data.
• Measures the KPI impact (e.g., session drop rate, access failure rate, handover failure rate, downlink/uplink throughput and latency) from the external interference on each of the affected cells for prioritization.

• Identifies cells experiencing uplink RGI with high accuracy using ML-trained CNNs.
• Characterizes RGI interference by time, frequency and intensity.
• Aggregates cells affected by the same source of the uplink RGI into clusters.
• Performs cell utilization analysis on RGI clusters.
• Determines the root cause of the RGI such as overshooting cells, insufficient separation between antennas, imbalanced traffic load among layers, or misconfigured parameters.
• Measures the KPI impact (e.g., session drop rate, access failure rate, handover failure rate, downlink/uplink throughput, latency and QoS.) from the RGI on each of the cells in the affected clusters for prioritization.

• Identifies cells with PIM interference with high accuracy using ML-trained CNNs.
• Determines whether the PIM source is internal (in cabling or antenna) or external (beyond antenna).
• Analyzes site frequencies to determine contributors to PIM interference (IM2-IM5).
• Identifies cells with faulty hardware issues such as persistent high noise rise, defective Rx branches and crossed antenna feeders.
• Measures the KPI impact (e.g., session drop rate, access failure rate, handover failure rate, downlink/uplink throughput, latency and QoS.) from the PIM interference on each of the affected cells for prioritization.

• Identifies cells experiencing TDD self-interference for LTE and NR during periods of tropospheric ducting (victim cells).
• Aggregates cells affected by the same sources of the ducting interference.
• Identifies the dominant aggressor cells causing the majority of TDD Self-Interference.
• Reconfigures parameters on dominant aggressor cells to mitigate the impact of ducting interference while optimally preserving capacity.
• Detects the victim cells from cross-border interference and identifies the locations of cross-border interference sources.
• Measures the KPI impact (e.g., session drop rate, access failure rate, handover failure rate, downlink/uplink throughput, latency and QoS.) from ducting interference on each of the victim cells.