Greek electricity retailers will face stronger incentives to predict customer consumption accurately from November 1. Revised balancing-market rules on significant, systematic demand deviations will take effect then, after transmission operator IPTO confirmed technical readiness, according to energy regulator RAAEY. The changes make demand forecasting a more consequential commercial function for suppliers.
The rules address persistent differences between the electricity demand market participants declare and the volumes their customers actually use. They are not intended to penalise every forecasting error, since electricity consumption cannot be predicted perfectly. Weather changes, industrial output varies and individual customers continuously adjust their behaviour.
The regulatory focus is on significant and recurring deviations that show a portfolio is repeatedly being scheduled inaccurately. Such systematic errors can impose costs on the wider electricity system. When a supplier consistently underestimates customer demand, the transmission operator must procure additional electricity through the balancing market.
Repeatedly overestimating demand can instead require generation to be reduced elsewhere. Both directions can increase balancing requirements, giving poor forecasting a more explicit financial consequence from November. The change affects the economics of electricity retail, where suppliers have traditionally competed through prices, discounts, contract terms and customer acquisition.
Forecasting becomes a source of retail margin
Forecasting quality is becoming another potential source of margin. Two suppliers buying electricity at similar wholesale prices may have different profitability if one repeatedly incurs higher imbalance costs. A retailer that forecasts more accurately can therefore hold a structural advantage.
This creates a commercial opportunity for forecasting-as-a-service. Specialised software providers can combine historical meter readings with weather forecasts, industrial schedules, calendar effects, customer characteristics and real-time consumption data to predict portfolio demand. Machine-learning systems can continually retrain models as customer behaviour changes.
The technology is particularly relevant to suppliers whose customer portfolios are changing quickly. A retailer adding thousands of customers cannot assume that they will behave like its existing customer base. A residential portfolio dominated by electric heating will have different consumption patterns from one relying mainly on conventional heating.
Other customer types also have distinct demand drivers. Hotels respond strongly to tourism patterns, while industrial consumers follow production schedules, and EV charging adds an increasingly variable load. Forecasting is therefore becoming more customer-specific.
Meter data supports forecasting and portfolio management
Smart-meter data can materially improve forecasting accuracy. Traditional monthly readings offer limited detail about when electricity was consumed, whereas interval meters show consumption patterns by individual hour or quarter-hour. Suppliers can use that information to identify customers with predictable peaks and those whose loads are volatile.
The data is useful beyond billing and enables retailers to build more detailed models of their balancing exposure. It can also support aggregation and demand response. For example, if a supplier knows that a customer regularly consumes 5 MW during a particular production period, it can forecast that demand more accurately.
If some of that consumption is flexible, an aggregator may also be able to change the load itself. Forecasting and flexibility can therefore converge: rather than only predicting an imbalance, an advanced portfolio manager may be able to correct it before delivery.
A supplier expecting demand to exceed its nominated position could buy electricity intraday or ask participating flexible customers to reduce consumption. If demand is expected to be lower, controllable loads such as EV charging or thermal systems could potentially be increased. This turns the electricity portfolio into an actively managed position.
Changing demand creates new commercial opportunities
Active portfolio management creates opportunities for companies offering automated intraday trading and optimisation. A modern retail platform could continually forecast demand, compare the projection with existing market positions and execute corrective trades as delivery approaches. Human traders would increasingly supervise automated systems rather than calculate every adjustment manually.
The change comes as Greece’s retail market becomes more complex. Customers are increasingly exposed to fixed, variable and dynamic products, while distributed solar changes net consumption. Smart meters provide more detailed data, and electric vehicles and behind-the-meter equipment add new load patterns.
Data centres and other large consumers are also introducing additional concentrations of demand. Together, these changes make consumption more difficult to forecast using conventional historical averages. The cost of forecast errors also becomes more important as balancing markets grow more sophisticated.
These developments could affect electricity-supplier valuations. Customer numbers alone may become a less informative measure for investors: two suppliers with 500,000 customers can have very different risk profiles depending on customer mix, data quality, forecasting technology and balancing performance. A high-quality consumption dataset and a proven forecasting model could each become an intangible asset.
Industrial customers and aggregators may gain a role
Suppliers may increasingly reward industrial companies that provide accurate operating schedules or access to real-time consumption data. Customers with unpredictable demand create balancing costs for retailers, while those with stable or transparent consumption profiles may become more commercially attractive. Contracts could eventually reflect that difference.
Energy-intensive customers could be offered better terms if they provide production forecasts, allow automated access to meter data or participate in mechanisms that help suppliers manage deviations. This would further narrow the boundary between electricity supply and energy management.
Independent aggregators could also benefit. If the Greek rules increase the financial consequences of systematic forecasting errors, suppliers have stronger incentives to secure flexible resources that can correct their portfolios. Aggregators controlling refrigeration, HVAC, EV charging, industrial processes or distributed generation can offer that capability.
Demand forecasting can therefore create a potential market for flexibility: first predict the deviation, then correct it. The regulatory change will not eliminate imbalance costs, nor should it, because electricity systems rely on balancing markets while forecasts continue to contain errors. Its aim is to discourage persistent behaviour that imposes avoidable costs on the system.
Forecasting is becoming monetisable: software that reduces systematic portfolio errors can directly protect supplier margins, smart-meter data becomes more valuable, automated trading becomes more attractive and flexible customers gain another route to market. A Greek retailer’s performance may increasingly depend not only on buying electricity at the lowest price, but also on predicting customer consumption, correcting forecasts before delivery and minimising the cost of remaining errors.