Reducing water loss isn’t a single technology decision, it’s a journey that requires the right foundation, informed tradeoffs, and lessons learned along the way. Many utilities still rely on customer reports or periodic surveys to identify leakage, making response largely reactive. This session focuses on how utilities are shifting toward a proactive water loss strategy by leveraging network data, analytics, and improved visibility into system behavior. Speakers will discuss how combining distribution system data—such as pressure trends, asset age, material, and failure history—enables earlier identification of emerging issues before they result in surface leaks or main breaks.

The grid is becoming increasingly dynamic and complex, and utilities are at the forefront of this transformation. While some have established smart metering programs, others are embarking on grid edge and distributed intelligence by modernizing meter‑to‑cash and distribution operations. Whether driven by regulatory mandates or enabled by federal funding, building a defensible business case that supports a rate case is critical. This session shares utility perspectives from different stages of Grid Edge Intelligence (GEI) implementation, highlighting how open, interoperable, standards‑based platforms help meet regulatory requirements, prioritize high‑value use cases, operationalize benefits and reduce risk. Attendees will gain practical guidance on translating GEI value—such as improved reliability, decarbonization and customer outcomes—into actionable next steps that justify investment and support execution.

Managing meter data exceptions is one of the most time‑consuming and resource‑intensive parts of the billing process—and it’s only getting harder as data volumes grow. In this session, Itron introduces its first agentic AI capability, purpose‑built to transform exception management within meter data management (MDM). By combining proven MDM validation rules with autonomous AI agents, this new approach can detect, diagnose, and recommend—or even resolve—billing exceptions with minimal human intervention. Attendees will see how agentic AI shifts exception management from manual triage to intelligent automation, helping utilities improve billing accuracy, reduce operational burden, and scale without adding staff.

The session will show how AI‑driven exception management can reduce manual billing reviews while maintaining trust, accuracy, and auditability, and offer real‑world insight into how AI agents analyze meter reads, events, and contextual system data to pinpoint root causes and recommend next actions. Participants will also gain a practical view of how utilities can adopt this capability incrementally—starting with AI‑assisted recommendations and evolving toward greater automation—along with a forward‑looking perspective on the future of MDM, where intelligent agents continuously learn, adapt, and scale alongside growing data and operational demands.

Old Dominion Electric Cooperative (ODEC), a generation and transmission provider based in Richmond, Virginia, reached a critical point when vendor support for its meter data management and wholesale power billing systems was ending. Because these platforms were central to settlements, reporting, and daily operations, replacement was not a simple IT refresh. We took a structured, utility‑led approach to define requirements, assess risk, and build a roadmap for full system replacement that the business and executive leadership could support.

In this session, we share how we prepared for this transition—starting with analyzing end‑to‑end business processes, defining functional and technical requirements, and building internal alignment. We walk through how we structured the RFP, evaluated vendor and implementation options, selected the right partners, and navigated contract and statement‑of‑work negotiations. Attendees will gain a practical, real‑world perspective on replacing mission‑critical systems and lessons learned that can be applied to similar modernization efforts.

Itron’s Grid Edge Intelligence portfolio is a comprehensive, integrated, end‑to‑end suite of solutions that unlocks the power of data across a utility’s service territory—from the grid edge and neighborhood transformer to the substation. Learn how our grid edge intelligence–based platform supports utilities’ decarbonization, reliability, sustainability and customer experience goals through interoperable, standards‑based, pre‑integrated solutions that build on existing AMI infrastructure to deliver real‑time visibility and distribution load management.

Old Dominion Electric Cooperative (ODEC), a generation and transmission provider based in Richmond, Virginia, relied for years on highly customized—but very stable—meter data management and wholesale power billing systems. When vendor support for those platforms was coming to an end, we faced the challenge of replacing systems that were deeply embedded in our operations while continuing to meet settlement, reporting, and reliability requirements. We embarked on a multi‑year effort to transition from legacy platforms to Itron’s IEE solution.

In this session, we share an honest look at what it takes to move off long‑standing custom systems and implement a modern enterprise solution. We discuss the key challenges we encountered, the opportunities we identified along the way, and the lessons learned from an 18‑month implementation. Topics include our configuration and requirements alignment process, running shadow billing and parallel operations, and managing operational risk while making significant system changes. Attendees will gain practical insights into what worked, what we would do differently, and what to consider when planning a similar modernization effort.

Tampa Electric Company (TEC) set out to address a long‑standing operational challenge: managing AMI and non‑AMI meter data across separate systems—particularly for large commercial and industrial (C&I) customers. While TEC’s legacy MV‑90 environment continued to support billing, detailed load profile data from approximately 1,200 high‑value C&I meters, representing a substantial portion of distribution revenue, remained largely disconnected from broader operational and analytical use. To close that gap, TEC implemented Service Mode within Itron Enterprise Edition (IEE), consolidating AMI and non‑AMI data into a single platform and establishing IEE as the system of record for both billing and analytics.

In this session, TEC shares how Service Mode enabled automated data collection, validation, and integration across its full metering portfolio. We walk through key architecture and integration decisions, data governance considerations, and the operational benefits realized—from improved data consistency to expanded access for analytics, planning, and customer engagement teams. Attendees will gain practical insights into how unifying meter data can strengthen decision‑making and better connect metering investments to business outcomes.

Tampa Electric is using the expanded data available through AMI 2.0 to turn meter data collected in IEE MDM into a powerful source of operational insight. By managing millions of interval reads, meter events, and alarms within a centralized, analytics‑ready meter data management environment, the utility has gained deeper visibility into system performance and day‑to‑day operations.

In this session, Tampa Electric shares how historical AMI 2.0 data—analyzed through an MDM‑centric, cloud‑based approach—is supporting key operational use cases such as revenue assurance, outage analysis, and system operations. By combining 15‑minute interval readings with device‑level event data, teams are able to identify discrepancies, validate system conditions, and uncover issues that were previously difficult to detect.

Attendees will learn how utilities can move beyond basic reporting to apply scalable analytics on trusted meter data, improve operational decision‑making, and lay the foundation for broader enterprise analytics and future cloud‑enabled use cases—while maximizing the value of their AMI 2.0 investments.