Sep 18, 2020 
By leveraging AI and ML, CSPs, NEPs and telecom-focused ISVs can improve the efficiency and performance of their network labs and drive better user experience.
This is the second of two blogs that address how AL and ML can improve the management and operations of network labs. Part 1 focused on how AI and ML can accelerate lab transformation and improve efficiencies. Part 2 focuses on root cause analysis, power management, optimization, security and solution validation.
The Problem. Communications service providers (CSPs), network equipment providers (NEPs) and telecom-focused independent software vendors (ISV) host and operate dedicated network labs to validate new services, evaluate and test the readiness of new technologies and solutions and integrate vendor solutions and devices.
To remain competitive in today’s dynamic environment, communications companies need to be more efficient, deliver services faster and take advantage of automation, all while managing costs. Altran research has identified the management and operation of the network lab as a critical area of focus. The challenges they face were detailed in the first blog and are summarized here:
- Hard to manage short-term and long-term costs and resources
- Loss of staff and poor equipment productivity
- Unnecessary downtime
- Inefficient asset and inventory tracking
- Non-optimized utilization of equipment and tools
Key Use Cases
While artificial intelligence (AI) and machine learning (ML) are gaining traction in core network operations, product development and testing, their application in the lab environment has been limited. Working with CSPs, NEPs and ISVs, Altran has identified many high impact opportunities for boosting the performance of network labs.
In the first blog, we identified four opportunities for the application of AI and ML, and we detail five more below:
Root Cause Analysis: AI/ML techniques can be applied to automatically identify the root cause of problems occurring inside the lab environment and help deliver key benefits, including early detection of failures, reduced recurrence of failures and proactive identification of bottlenecks. Some of the critical issues reported include an unstable test environment, random equipment failures, a surge in the volume of fault events and validation of defects.
AI/ML algorithms can classify the issues into specific root-cause categories by using historical data and logs for training data models. In addition to identifying anomalies, root cause analysis helps detect false positives.
Power and Energy Management: Network labs continue to face challenges optimizing power and energy consumption due to various factors including improper rack placement, poorly designed and inefficient UPS, lighting and cooling systems, peak loads of lab environment usage and unused hardware.
An AI/ML approach can analyze historical data of hardware and systems power usage, cooling and lighting usage and historical equipment uptime to model and predict future usage and optimize energy requirements. Also, the AI model can identify inefficient and unused infrastructure elements, such as redundant hardware, UPS systems running with a low load factor, and underutilized test environments that can be decommissioned or switched off when not required.
Lab Equipment and Tools Optimization: Lab resource assignment for test environment setup and test execution is traditionally done manually based on availability and usage duration. By using AI and ML, a test-environment setup requiring physical lab resources and third-party cloud and vendor resources can be managed more efficiently and cost-effectively.
For example, AI and ML can quickly predict and schedule the optimal resources and configuration by analyzing the relevant hardware and software specifications, resource cost, availability and scheduled usage, physical and virtual location of equipment and its status and utilization, past success and failure data, and repair and maintenance schedules.
Lab Infrastructure Security: Given the complexity and criticality of the lab environment, ensuring the security of physical infrastructure and networks is a top priority. The typical lab environment is accessed internally by staff within the company and remotely by external users from vendors and partners. Labs are prone to security threats when connected to external networks, which requires a dynamic management approach.
Complementing the standard firewall configuration and user-access policies, an AI/ML-based approach can analyze network traffic and user access behavior, detect anomalies and identify security threats.
Service and Solution Validation: An integral part of the lifecycle management of the test environment is deploying and validating the hardware, software and associated services. Typically, every test environment setup is followed by a manual or automated test-execution cycle.
An AI/ML-based test approach can be used to improve the efficiency and effectiveness of this validation process. Historical data associated with past test execution, test cases and defect history can be used to guide and generate predictions. For example, test-case prioritization ranks test cases that are likely to find more defects early in the test cycle. And test-case minimization helps identify and remove duplicate, redundant and obsolete test cases using natural-language processing techniques.
AI/ML use-case implementation in the network lab is critical for cost and resource optimization and reducing financial risk. Maximizing the value of AI/ML technologies requires access to large data sets—the more historical data, the better—and implementation of the right infrastructure and equipment.
Altran provides powerful AI/ML software frameworks for our CSP, NEP and ISV customers that deliver business value. The first step is to perform a gap analysis that identifies areas for improvement and optimization, maps relevant AI/ML use cases and defines the roadmap. Conducting a proof-of-concept exercise for selective use cases is a good starting point to gain confidence and showcase the benefits.
Altran Solutions
Altran offers four AI/ML solutions to help communications companies improve efficiency and reduce CAPEX and OPEX.
TANTEM: The TANTEM framework provides an end-to-end solution for CSPs and NEPs to deliver test-as-a-service to local and remote users by automatically building and deploying test environments and test automation. Virtual environments can be generated as needed and do not need to remain in place after tests have been run. TANTEM uses AI/ML test analytics for continuous optimization of the testing ecosystem.
ATLAS: The ATLAS framework is an intelligent testing solution that uses AI/ML techniques to prioritize test cases, select test cases based on code changes and perform automated root cause analysis to reduce the time needed for regression testing and speed up software delivery while improving software quality.
AVERT: The AVERT security software framework future-proofs your business with state-of-the-art security. The shift to software-defined networking and virtualization, the increased use of mobile devices and other factors demand a new network security approach to manage the ever-evolving cyber-threat landscape.
NetAnticipate: NetAnticipate is the ultimate network AI platform that enables the artificial intelligence software security of tomorrow. It is an intent-based prescriptive AI platform to realize self-learning networks for zero human touch network operation that predicts network anomalies and takes preventive measures in real-time using a cognitive feedback loop.
Connect with an Altran expert for more information about the advantages of a cloud-native architecture for 5G implementations.
RELATED ARTICLES:
- Boost network lab performance with AI and ML
- Altran Lab – 5G Services and Solution Innovations
- 5G Solutions for Next-Generation Carrier Networks
