GenAI for AN
As CSPs begin to deploy cloud-native systems and other advanced
technologies, their networks are becoming more complex, putting
operation and maintenance (O&M) personnel under pressure. In the radio
network, for example, configuring base station parameters can now be a
lengthy procedure making it difficult for CSPs to keep pace with rapid
changes in the network environment, which can quickly result in
deteriorating end user experiences.
This Catalyst is looking to use generative artificial intelligence
(genAI) to address these challenges in a number of ways, while
applying zero-trust and zero-risk principles in the network management
resource layer. For example, the project is developing a series of
digital assistant and digital expert solutions to ensure high
stability in the core network and greatly improve routine O&M
efficiency.
For the radio network, the Catalyst is developing an assurance system
which will use data compression technology to quickly identify network
status changes and accumulate core data. This mechanism will be
supplemented by a decision-making system, based on deep reinforcement
learning and large AI models, which will be able to rapidly optimize
the network to meet multiple objectives and perform closed-loop
management. The Catalyst will also employ machine learning to
automatically expand parameter ranges and optimization objectives,
while absorbing expert optimization experience to improve the model’s
performance.
For the bearer network, the Catalyst will employ natural language
processing technology to automatically identify customer intentions,
select APIs and set parameters. The proposed solution will be able to
query fault-related information through a mobile application running
on end users’ cellphones, greatly reducing the time it takes to obtain
fault information and the mean time to repair. The Catalyst team plans
to measure the project’s feasibility and effectiveness by tracking the
work order automation rate, the work order processing duration, the
fault handling duration and other indicators. The goal is to automate
80% of service fault diagnoses, while enabling real-time responses to
fault information queries, leading to a 60% improvement in O&M
efficiency.
Challenges
* High Expenditures Due to Manual Processes:
* Manual processes on business and operational levels, such as
planning and optimizing networks, lead to high costs.
* Use of Various Platforms and Tools:
* The current approach involves using multiple platforms and
tools for network optimization, which are often less accurate
and slow.
* Inefficient Data Processing and Analysis:
* The existing data processing and analysis methods are
inefficient, leading to high expenditures and slower
decision-making.
Operational and Commercial Impacts
* Failure to Achieve Target EBITDA:
* Not achieving the target EBITDA increase of 30%, impacting
financial performance.
* Inadequate Improvement in Customer Experience:
* Less improvement in customer experience due to suboptimal
network performance and slower response times.
##The Solution ##
Core Capabilities of GenAI for Autonomous Networks (AN):
1. Intent/Experience:
* Understanding Telecom Know-how: GenAI leverages deep domain
knowledge to understand telecom-specific needs and operations.
* Conversational O&M: Utilizing conversational AI for operations
and maintenance, enhancing user interaction and reducing
manual intervention.
2. Awareness/Analysis:
* Multi-modal Perception: GenAI integrates various data sources
to perceive network conditions accurately.
* Complex Network Issue Analysis: Advanced analytics
capabilities to identify and diagnose complex network issues.
3. Decision/Execution:
* Unified Performance Prediction: Predicting network performance
under various conditions to pre-emptively address potential
issues.
* Precise Network Simulation and Decision-making: Running
simulations to test different scenarios and making precise
decisions based on data-driven insights.
Autonomous Network Levels and Effectiveness:
* Level 1 (L1) to Level 5 (L5):
* Progression from manual operation (L1) to high autonomous
networks (L5), with increasing effectiveness through
automation and autonomy.
* GenAI and AI+ enhancements significantly improve network
effectiveness, marking a value leap at Level 4 (L4).
GenAI's Role in Enabling Intelligent Functions:
1. Intelligent Decision-Making:
* Collaborators: China Mobile, ZTE, Huawei, Whale Cloud
* GenAI supports intelligent decision-making by analyzing data
and providing actionable insights, enabling informed and
timely decisions.
2. Intelligent Analysis:
* Collaborators: China Mobile, Telkomsel, Huawei, Sand
Technologies
* GenAI enhances data analysis capabilities, enabling deeper
insights into network performance and customer behavior,
leading to more effective optimization strategies.
3. Intelligent Intents:
* Collaborators: China Mobile, MTN, AsiaInfo, Huawei
* GenAI facilitates the understanding and execution of network
intents, aligning operations with strategic goals and
improving overall network management.
Value Leap at L4:
* Enhanced Effectiveness:
* The integration of GenAI drives a significant leap in network
effectiveness at Level 4, bridging the gap between basic
automation and full autonomy.
* This leap is characterized by more accurate predictions,
efficient resource allocation, and improved network
performance.
* Strategic Impact:
* Achieving Level 4 autonomy translates into strategic
advantages, such as reduced operational costs, increased
service reliability, and enhanced customer satisfaction.
* By automating complex processes and enabling real-time
decision-making, Telkomsel and other collaborators can achieve
substantial improvements in operational efficiency and
financial performance.
These insights underline the transformative potential of GenAI in
enhancing network operations, driving strategic planning, and
optimizing site performance, ultimately leading to improved financial
outcomes and customer experiences.
##Collaboration##
#Diverse Champion Business Use Cases List#
1. Telkomsel with Sand Technologies
Telkomsel and Sand Technologies Collaboration for Enhanced Strategic
Planning and Site Optimization
Telkomsel, Indonesia’s leading telecommunications provider, has
embarked on a groundbreaking collaboration with Sand Technologies to
revolutionize its strategic planning and site optimization processes.
This partnership aims to leverage the advanced capabilities of
generative AI and large language models (LLMs) to develop intelligent
analysis solutions, driving significant improvements in operational
efficiency and financial performance.
At the core of this collaboration is the deployment of an innovative
solution designed to address the complex challenges of strategic
planning and site optimization in the telecommunication sector. By
integrating Telkomsel's extensive network data with Sand Technologies'
cutting-edge AI algorithms, the joint solution aims to provide
actionable insights and predictive analytics that are critical for
informed decision-making.
Key Aspects of the Solution:
* Intelligent Analysis: Utilizing generative AI and LLMs, the
solution offers a sophisticated analysis of network performance,
user behavior, and market trends. This enables Telkomsel to
predict future demand accurately and optimize site deployments
accordingly.
* Strategic Planning: The AI-driven insights facilitate strategic
planning by identifying optimal locations for new sites and
necessary upgrades for existing infrastructure. This ensures that
Telkomsel can meet the growing demand for high-speed connectivity
while maintaining cost efficiency.
* Site Optimization: The solution continuously monitors network
performance and customer usage patterns, providing real-time
recommendations for site enhancements. This proactive approach
minimizes downtime and enhances user experience.