Singapore, 5 April 2023 – Avanseus Pte. Ltd., a software company skilled in developing AI-based solutions driven by machine learning and cognitive computing has announced version 6.0 of its AI-based, augmented operations platform. This includes several enhancements to Avanseus Predictive Maintenance’s capabilities and introduced the smart asset procurement application.
Augmented operations, previously called cognitive assistant for networks, leverages AI to advance how telecom providers, data centres, and other enterprises manage network reliability, resiliency, and maintenance costs. The platform enables customers to predict and prevent equipment failure and protects companies and customers from unplanned outages and potential safety issues.
The product includes the following key applications:
- Predictive maintenance
- Smart asset procurement
- Fault prediction
- Topology discovery
- Health index prediction
This software platform model delivers multiple applications that benefit from the patented AI engine capabilities centered around universal prediction, intelligent prioritisation, predictive root cause analysis, and self-learning-based recommendations.
“This latest release represents the maturation of the Avanseus core platform that is driving a paradigm shift from reactive to predictive network monitoring and maintenance,” says Bhargab Mitra, Avanseus CEO. “With the transition to 5G and eventually 6G and the proliferation of devices under the Internet of Things, traditional approaches to monitoring network health and stability cannot match the new scale and complexity. The ability of our AI platform to identify failure points before they happen, maximise the value of installed equipment, and create a more consistent consumer experience is transformative.”
“We are excited to bring these enhancements in augmented operations to market,” says Dennis Lorenzin, Chief Product Officer, “and accelerate the journey into the future of Intelligent Network Operations for our Telco Operations customers by leveraging our scalable and proven AI capabilities.”
The APM solution now comes enriched with topology auto stitching and discovery, a multi-domain, multi-technology, and vendor-agnostic technology that automatically groups and visualises predicted fault clusters based on topology and boosts in-depth root cause identification accuracy. If topology information is incomplete or missing, the new Topology Automatic Discovery capability will rebuild the necessary data and logical connections, maintaining and updating them through each facet of the cross-correlated analysis. APM’s Root Cause Analysis unlocks substantial value for Avanseus customers, sustaining network health while reducing operating costs.
APM can now integrate with RedHat Ansible, an enterprise-wide automation platform, enabling the closed-loop implementation of APM’s recommended resolutions, reducing execution time and the need for manual intervention. The integration of these two technologies signifies a significant step toward realising the company’s “zero-touch” operational vision and helps network operators to increase automation, speed, and effectiveness.
The Smart Asset Procurement solution is the Company’s latest off-the-shelf application specifically targeting telecom operators. It is designed to address inventory optimisation by leveraging predictive maintenance to improve spare parts procurement and logistics. With a precise list of predicted hardware faults, SAP helps operators plan and precisely deliver the necessary parts, significantly reducing handling costs and network element downtimes. Applicable to both internal and outsourced spare parts management, SAP easily integrates with customers’ procurement ordering tools.
The enhanced functionality of the Company’s augmented operations product enables significant operational benefits in terms of incident ticket reduction, mean time to resolution, network uptime, and field force cost reduction.
Comment on this article below or via Twitter: @IoTNow_OR @jcIoTnow
via https://www.AiUpNow.com
April 10, 2023 at 08:23AM by Shriya Raban, Khareem Sudlow
