Subscribe
DSOs must turn vast but fragmented datasets into “business‑ready” intelligence to manage grid congestion.
A new report proposed a bronze‑silver‑gold data architecture, AI‑based load reconstruction and quantified flexibility needs.
This can become a strategic alternative to costly grid reinforcement.
As electrification accelerates across Europe, distribution system operators (DSO) are facing mounting pressure to manage increasingly complex electricity networks, while accommodating electric vehicles, heat pumps, rooftop solar and other distributed energy resources, according to a new report.
The report, The Grid's New Gold: Harnessing DSO Data to Unlock Flexibility, argues that local grid flexibility could help utilities defer capital expenditure and manage network constraints, but only if they can effectively use the vast amounts of data already available from smart meters, supervisory control and data acquisition (SCADA) systems, geographic information systems (GIS) and asset registers.
"Flexibility is becoming a core planning lever for DSOs, but its value depends on trusted, business-ready data," the report stated.
Key challenges stem from the mismatch between rapidly changing electricity demand patterns and traditional grid planning processes. According to ADL, most utility datasets remain fragmented, incomplete and poorly integrated with network topology, limiting their usefulness for forecasting and investment decisions.
The report recommended a three-tier data architecture comprising a "bronze" layer for raw data ingestion, a "silver" layer for cleansing and harmonisation and a "gold" layer that converts information into business-ready products such as customer profiles, asset risk scores and flexibility potential maps.
"Distribution management has become a data-driven discipline," the report noted, adding that utilities should treat data as a strategic asset rather than an operational byproduct.
The report highlighted flexibility services as a potential alternative to costly grid reinforcement projects. By analysing customer-level electricity consumption and local network constraints, utilities can identify situations where demand management and flexibility procurement may be more economical than infrastructure upgrades.
In one case study, ADL worked with a leading DSO to assess future network stress between 2024 and 2029. The analysis found that substations experiencing non-structural overloads could increase from 56 in 2024 to 122 by 2029. Violation hours were projected to rise from about 1,600 hours to 7,800 hours, while flexibility-relevant energy requirements increased from 19 megawatt hours (MWh) to 163 MWh.
The study found that many constraints were localised and time-bound, making them suitable candidates for flexibility services rather than immediate capital investment.
For each non-structural constraint, the model calculated both energy volume above technical thresholds and the duration of overload events, enabling planners to compare operational expenditure and capital expenditure options.
The report also outlined how artificial intelligence is being used to overcome gaps in smart meter coverage. A case study described the deployment of deep neural networks to reconstruct missing customer-level electricity consumption profiles. The system was designed to address incomplete meter data caused by communication failures, outages and missing readings.
According to ADL, the reconstruction engine generated more than 74 million daily load curves in 2024, achieving monthly validation errors below 10 per cent compared with transformer-level energy balances.
The report said such approaches allow utilities to undertake advanced planning even before universal smart meter deployment is achieved.
ADL identified six priorities for utilities seeking to prepare for a flexibility-driven electricity system:
Treat data governance, ownership and quality as executive-level priorities.
Adopt a data-as-a-product operating model that creates reusable datasets.
Focus on cleansing, reconstructing and enriching operational data.
Integrate third-party information such as weather, mobility and electric vehicle charging patterns.
Quantify flexibility requirements to support capital expenditure and operational expenditure trade-offs.
Establish joint delivery models involving business teams, information technology specialists and data scientists.
The report concluded that utilities that can industrialise data and convert it into planning intelligence will be better positioned to optimise investments, manage grid stress, and support the broader energy transition.