Uhana by VMware correlates and enriches high volumes of streaming data from mobile network elements to provide comprehensive insights at a subscriber level. Using AI, Uhana automatically determines the root cause of network issues and recommends remediations.
Uhana analyzes streaming data to provide mobile operators with real-time customer experience metrics, allowing MNOs to understand call quality and data performance on a per subscriber basis, in real-time.
Uhana prioritizes alerts based on subscriber impact. This is done in an automated fashion, using machine learning to determine which issues will have the largest impact.
Uhana’s AI platform leverages machine learning to detect, classify and localize issues in the mobile network in an automated fashion. Where possible, the platform determines a root cause and recommended fix.
Due to the fine-grain visibility of the platform, Uhana reveals new network insights, processing millions of events and calculating hundreds of performance KPIs in real-time.
Automatically joins call trace events such as establishment, & release procedures, and radio measurements belonging to the same user session in real-time to create subscriber session records.
Leverage eNodeB trace data to provide fine-grained, real-time, subscriber level visibility to quickly analyze RAN performance and utilization and subscriber Quality of Experience.
Uhana’s AI-enabled Alerts Pipeline automatically detects and clusters (temporally and spatially) anomalies of subscriber level KPIs using neural networks.
Prioritization of alerts is based on impact analysis, e.g. how many subscribers are affected and the significance of service degradation, so that responses can be prioritized accordingly.
Each alert is further analyzed by identifying a root cause (leveraging neural network classifiers) and providing relevant KPIs and recommendations specific to the identified root cause.
Uhana ingests and analyzes millions of continuously streaming events from tens of thousands of cells, for actionable insights, predictions & remediation recommendations.
The Uhana AI platform is a state-of-the-art cloud-native application leveraging a micro-services architecture. Built on Docker containers, micro-services enable resiliency and scale-out.
Leveraging an interactive UI, operators can create custom KPIs within minutes, combining multiple metrics together as needed and saving weeks of time.
Automate detection and classification of uplink interference (external, PIM, infrastructure) with prioritization based on type and number of subscribers impacted.
Localize external interference with a prioritized list of search area and heatmap visualization. Reduce area of interference triangulation from miles/kms to blocks, saving hours of reconnaissance time.
Use machine learning root cause and impact analysis algorithms to determine if cause of poor downlink throughput is related to load imbalance of antenna frequencies for optimum use of spectrum.
Increase effective spectral capacity by improving RAN optimization engineering. Prioritize network investments that maximize subscriber impact and reduce CAPEX spending.
Automate RAN optimization analysis and improve efficiency of RAN optimization engineering & operations through AI based RCA, granular visibility, and impact prediction.
Reduce data science analysis cycle time by up to 30% through the automation of data preparation, freeing up valuable time for higher value functions.
Uhana by VMware is an advanced analytics and AI solution that provides real-time network and subscriber analytics. It enables mobile network operators to improve their customer experience management, optimize their operations, automatically detect and triage interference, predict future issues, and recommend appropriate remediations. All of this is done with the goal of achieving optimal control of mobile network operator’s (MNO’s) high-value cellular infrastructure in an automated fashion.
While mobile network operators employ many of the best and brightest technologists and data scientists on the planet, even they are limited by the state of traditional RAN network analytics and telemetry. Coarse-grained telemetry data restricts capacity planning and performance measurements to historical analysis. Worse, because actual network conditions occur on very short time scales (seconds and milliseconds), any application performance, user experience or network efficiency guidance derived from coarse grained data (minutes) will suffer from “average blindness” and severely limited visibility.
Today’s network controllers, SONs and MMEs provide performance data counters on a cell site level, in 15 minute increments. This means that the peaks and valleys of performance within these 15 minutes will be smoothed out by averaging and may not be visible. Network conditions that are critical to accurate guidance, will be masked by the average and hidden from the decision algorithm. Additionally, the data provided by the MME is at a cell site level and does not drill down to the specific subscribers using that cell site.
The Uhana AI platform ingests and processes concurrent data feeds from tens of thousands of cells, correlates with user session data and calculates real-time Key Performance Indicators (KPIs). This data is combined with application specific inputs and operator specified policies to deliver unprecedented network visibility, anomaly detection and real-time, predictive network intelligence, including application and/or RAN control guidance.
Uhana by VMware applies breakthrough deep learning techniques, combined with application specific inputs and operator specified policies to deliver unprecedented network visibility, anomaly detection and real-time, predictive network intelligence, including application and/or RAN control guidance. For the first time, operators are able to offer application developers API access to accurate, fine-grained network intelligence and predictive “what-if” modeling. This network intelligence is applied to optimize application performance, dramatically improve subscriber quality-of-experience and programmatically control the RAN in conjunction with modern infrastructure automation platforms. With Uhana, mobile operators’ vision for a programmable network services platform, beyond connectivity, can finally be realized.
Uhana can be deployed on-premise (or on a public cloud). The typical deployment scenario is that Uhana is installed in the mobile operator’s cloud compute environment, however the portal can be accessed via a VPN. Uhana was developed as a cloud-native application leveraging a microservices architecture. Built on Docker containers, microservices enable resiliency and scale-out. This also allows the platform to be deployed on bare-metal or virtual machine infrastructure.
No, Uhana is not collecting inline data and does not see customer payload. Uhana ingests information directly from the eNodeB and MMEs in the RAN. The data is collected offline and therefore has no impact on the performance of the network. Uhana enriches this information with real-time location data and customer data such as IMSIs for insights that are actionable by the mobile operator.
Yes. Leveraging the eNodeB (and in the future gNodeB) trace data, Uhana provides multi-vendor device performance comparisons (across different device models and software versions) at a cell, sector, or eNB / gNB level in order understand how different devices are performing and impacting the network. Uhana will also automatically establish device performance baselines and detect anomalies introduced by device and RAN software upgrades. Conversely, when new device hardware or software is introduced into the network, Uhana will characterize the performance impact this new hardware or software has had on the RAN. Mobile operators can further improve network operations, improve customer experience and speed up the troubleshooting of issues by joining device analytics output with MME and packet core traces for richer insights.
Agility. Creating custom KPIs with current operator processes can take weeks. Uhana’s KPI Composer gives mobile operators a simplified way to rapidly create new KPIs needed for analytics use cases and provide metrics tailored to the requirement at hand. Drop down options make defining new KPIs easy and multiple metrics can be combined to create a comprehensive, tailored KPI that meets individual operator’s requirements.