IOH Achieves 85% Fault Resolution with AI-Driven Automation
IOH's deployment of AI-driven fault resolution now allows for the auto-resolution of 85% of common wireless access faults in a single step, significantly boosting network operations efficiency.
Key Facts
- IOH's AI agents resolve 85% of faults in one step, enhancing operational efficiency and reducing costs.
- Field productivity up 20-30% indicates successful tech adoption, improving competitive positioning.
- Alarm volume reduced by 95% allows focus on actionable incidents, revealing operational vulnerabilities.
- Reskilling staff to AI roles suggests strategic shift towards higher-value tasks, enhancing workforce value.
- "Agent everywhere" model indicates long-term vision for proactive operations, driving market evolution.
Summary
Summary
Indosat Ooredoo Hutchison (IOH) faced challenges in managing its extensive network operations, which included handling millions of alarms daily and frequent outages. To address this, IOH implemented AI-native, agentic operations that automated fault monitoring and resolution. As a result, the company now resolves up to 85% of common wireless access faults in a single step, significantly improving operational efficiency.
Background
Indosat Ooredoo Hutchison (IOH) operates one of the largest and most geographically complex telecommunications networks in Southeast Asia, managing over 55,000 base stations and more than 170,000 network devices. Prior to deploying AI solutions, IOH's operations teams struggled with alarm floods, siloed vendor tools, and manual workflows, which made it difficult to efficiently identify and resolve network issues.
Challenge
The primary challenge IOH sought to overcome was the inefficiency of human-driven, ticket-based operations and maintenance (O&M). With network expansion occurring at a rate of up to 4,000 new sites per year, the existing model was unsustainable, leading to delays in fault resolution and misdiagnosis of issues.
Solution
IOH transitioned to AI-native operations by deploying a unified platform and a digital twin of its mobile broadband access network. This included the introduction of AI copilots and autonomous agents for fault monitoring, demarcation, remediation, and field execution. Key components of the solution included the Field Maintenance Engineer (FME) Copilot, Digital Intelligence Operations Center (DIOC) Front Office Copilot, and domain-specific fault handling agents.
Results
The implementation of AI tools has led to significant improvements: AI agents now auto-resolve up to 85% of common wireless access faults in a single step. The FME Copilot has replaced nearly 90% of interactions between field engineers and back-office staff, resulting in a 20% to 30% increase in field productivity. Additionally, network operations center efficiency has improved by over 20%, while network availability and traffic have reached record highs.
Key Insights
Organizations aiming to enhance operational efficiency should consider integrating AI solutions to automate repetitive tasks. Reskilling employees to take on higher-value roles can lead to a more effective workforce. A unified data platform is crucial for successful AI implementation, as it provides the necessary foundation for decision-making.
Customer Testimonial
“We don’t want people doing repetitive Excel work anymore. We want them doing higher-value work. Agents and copilots handle the repetition.” — Luthfi Auzan, Vice President of Operations at IOH.
Entities Mentioned
Companies
Products
Technologies
People
Key Concepts
Definitions
- agentic AI
- A type of artificial intelligence that operates autonomously to perform tasks and make decisions without human intervention.
- digital twin
- A digital replica of physical assets, processes, or systems that can be used for monitoring and analysis.
- Model Context Protocol (MCP)
- A protocol used for communication between AI agents to coordinate actions and share information.
- retrieval-augmented generation (RAG)
- An AI technique that enhances the generation of responses by retrieving relevant information from a database.
- zero touch operations
- An operational model where processes are automated to the extent that minimal human intervention is required.
Use Cases
- →automated fault monitoring
- →demarcation of network issues
- →remediation of faults
- →field execution of network operations
- →real-time troubleshooting assistance
- →data governance and management
Frequently Asked Questions
What is the main benefit of using AI in network operations?
The main benefit is the automation of fault resolution, which allows for faster response times and reduces the need for human intervention in routine tasks. This leads to improved efficiency and productivity in network operations.
How does IOH ensure data quality for AI operations?
IOH emphasizes data governance, ensuring that data is accurately managed and cleansed. This is crucial because the effectiveness of AI tools depends heavily on the quality of the data they process.
What role do engineers play in the new AI-driven model?
Engineers are being reskilled to take on new roles such as AI builders and data engineers, focusing on higher-value tasks rather than repetitive manual work. This transformation allows them to contribute to the development and governance of AI systems.
What challenges does IOH face in its operations?
IOH faces challenges such as frequent power instability and extensive construction activities that lead to network disruptions. These external factors complicate fault identification and resolution.
What is the future vision for IOH's operations?
IOH envisions an 'agent everywhere' model where AI agents will be deployed across various operational processes, transforming operations from reactive to strategic functions that drive network evolution.