Greek electricity retailers will face stronger incentives to forecast customer consumption accurately from November 1. Revised balancing-market provisions on significant systematic demand deviations will take effect at the start of November, after the Regulatory Authority for Waste, Energy and Water (RAAEY) confirmed technical readiness with the Independent Power Transmission Operator (IPTO). The change gives demand-prediction technology a more direct commercial role in electricity supply.
Rules focus on persistent demand deviations
The provisions address recurring differences between the electricity demand market participants declare and the volumes their customers ultimately consume. They are not intended to penalise every forecasting error: electricity demand cannot be predicted perfectly as weather shifts, industrial production varies and individual customers change their behaviour. Instead, the regulatory focus is on significant and systematic deviations that show a portfolio is repeatedly being scheduled inaccurately.
Persistent errors can create costs for the wider electricity system. When a supplier regularly declares less demand than its customers consume, IPTO must obtain additional electricity through the balancing market. Repeated overestimation can require generation to be reduced elsewhere, and either pattern can increase balancing requirements.
From November, poor forecasting will therefore carry a more explicit financial consequence, changing the economics of electricity retail. Suppliers have traditionally competed on electricity prices, discounts, contract terms and customer acquisition. Forecasting quality is becoming another source of margin: two suppliers buying electricity at similar wholesale prices can have different profitability if one repeatedly incurs higher imbalance costs.
More accurate forecasters gain a structural advantage, creating a commercial opportunity for forecasting-as-a-service. Specialist 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 continuously retrain their models as customer behaviour changes.
Customer data and consumption patterns shape forecasts
Forecasting technology is particularly relevant to suppliers with rapidly changing customer portfolios. A retailer adding thousands of customers cannot assume their consumption patterns will match those of its existing base. A residential portfolio dominated by electric heating behaves differently from one relying mainly on conventional heating, while hotels respond strongly to tourism patterns and industrial consumers follow production schedules.
Electric-vehicle charging adds another increasingly variable load, making forecasts more customer-specific. Smart-meter data can materially improve accuracy because traditional monthly readings offer limited insight into when electricity was consumed. Interval meters, by contrast, show consumption across individual hours or quarter-hours.
With that detail, suppliers can identify customers that create predictable peaks and distinguish them from volatile loads. The information is useful beyond billing: it allows retailers to develop more detailed models of their balancing exposure. The same data can also support aggregation and demand response.
For example, if a supplier knows that a customer regularly uses 5 MW during a particular production period, it can forecast that demand more accurately. If some of the load is flexible, an aggregator may also be able to change consumption. Forecasting and flexibility therefore begin to converge.
Forecasting links to active portfolio management
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 in the intraday market or ask participating flexible customers to reduce consumption. If demand is forecast to be lower, controllable loads such as EV charging or thermal systems could potentially be increased.
This approach turns the electricity portfolio into an actively managed position and creates opportunities for companies offering automated intraday trading and optimisation. A modern retail platform could continuously forecast demand, compare it with existing market positions and execute corrective trades as delivery approaches. Human traders would increasingly oversee automated systems rather than calculate every adjustment manually.
In Greece, the change comes as the retail market becomes more complex. Customers are increasingly exposed to fixed, variable and dynamic products, while distributed solar changes net consumption and smart meters generate more detailed data. Electric vehicles and behind-the-meter equipment add new load patterns, and data centres and other large consumers are creating additional concentrations of demand.
These developments make the system harder to forecast using conventional historical averages. The cost of inaccurate forecasts also becomes more significant as balancing markets grow more sophisticated. As a result, forecasting performance may affect how electricity suppliers are valued.
Forecasting capability may affect suppliers and customers
Customer numbers alone may become a less informative measure when investors assess a retail supplier. Two suppliers with 500,000 customers can have very different risk profiles depending on customer type, data quality, forecasting technology and balancing performance. High-quality consumption data and a proven forecasting model could each become an intangible asset.
The change also has implications for industrial customers. Suppliers may increasingly reward companies that provide accurate operating schedules or allow access to real-time consumption data, because large customers with unpredictable demand create balancing costs for retailers. Companies with stable or transparent consumption profiles may be more commercially attractive, and contracts could eventually reflect that difference.
Energy-intensive customers may be offered better terms if they provide production forecasts, permit automated access to meter data or take part in mechanisms that help their supplier manage deviations. This would further narrow the boundary between electricity supply and energy management.
Independent aggregators could also benefit. If Greece increases the financial consequences of systematic forecasting errors, suppliers have stronger incentives to secure flexible resources that can correct their portfolios. Aggregators controlling refrigeration, heating, ventilation and air-conditioning (HVAC), EV charging, industrial processes or distributed generation can offer that capability.
Demand forecasting thus creates a potential market for flexibility: first predict the deviation, then correct it. The regulatory change will not eliminate imbalance costs, nor is that its purpose, because the electricity system relies on balancing markets when forecasts contain errors. The stated aim is to discourage persistent behaviour that imposes avoidable costs on the system.
This technical regulatory change has wider commercial consequences: forecasting is becoming monetisable, and 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. The Greek retailer’s performance may increasingly depend not only on buying electricity cheaply, but also on predicting customer consumption, correcting forecasts before delivery and minimising the cost of remaining errors.