Forecasting power systems
Electricity producers rely on forecasts of electricity prices for bidding in the markets and power plant scheduling. Markets are changing: A much tighter integration between European markets and a rise in unregulated renewable energy production, especially wind and photo- voltaic, call for joint probabilistic forecasts. Incorporating the transient interplay between productions from renewable sources is critical to power production and financial operations. Multivariate probabilistic forecasts of electricity prices in the short horizon are required. Appropriately characterising multivariate uncertainty will enable more effective operational decisions to be made.
Conventional power grids add extra generation and distribution capacity. Smart grids actively match energy supply and demand and combine the needs of the markets with the limitations of the grid infrastructure. With the implementation of smart meters and grid sensors, enormous amounts of time series data are generated, with seconds resolution. Our objective is to develop new methods that extract the right information from data to optimise grid control and for real time operation.
Error dressing spot price forecasts
Electricity markets “spike” and “crash” when volumes are respectively slightly higher or lower than typical and these extreme price swings make uncertainty quantification a critical part of forecasts. However, the limited degree to which these extremes are observed makes such constructions difficult. We use published bid/ask curves that determine the final price, to construct realistic distributional price forecasts that embed this extreme behaviour. We employ the concept of “error dressing” by using the curves to translate residual behaviour of market volume forecasts into price uncertainties.
Using river inflow projections to augment electricity price spot forecasts
River inflow is a critical quantity that impacts the bidding strategies of hydroelectric operators. We use newly available data on river inflows for Norway and Sweden to build a river inflow component into spot price forecasting system.
Power Matching Problem for the Smart Grid
The Power Matching Problem amounts to determine the optimal (according to user preferences) e-profile, that is the utilization of the available energy during the time horizon by the appliances in the households so that demand and supply meet and all time constraints are satisfied. As such, this can be seen as a Resource Constrained Scheduling Problem with Time Windows and in presence of uncertainty. We can use stochastic optimization, where one minimizes the expected value of a given objective function, based on some probability distribution attached to a set of possible input scenarios. Alternatively, robust optimization does not need such a probability distribution, as just ranges of operations are needed.
Transfer of methodology to Hydro
In 2016 we implemented an “error dressing” methodology that will serve as the core of our distributional forecasting system. This was first implemented for the Nordic electricity market and shared with the industrial partner, Hydro. The results were so promising that Hydro has already put the methodology into production and multiple individuals at Hydro use the model output to inform production and trading decisions on a daily basis.
- Expansion of the error dressing methodology to all other relevant European electricity markets, in particular the German (EEX) market.
- River inflow model for the Nordpool spot market.
- Electricity flow model to capture trading behavior between markets
- Curve disaggregation model to take published system-level bid/ask data and construct regional bid/ask curves
- Power Matching Problem for the Smart Grid