Running any kind of business implies taking calculated chances, reducing risks and managing variabilities. Risk taking is practically built in energy trading of power generated from wind and solar energy sources, incl. those located behind the meter (BTM). Whether you are a renewable energy developer, an energy company with a mix of conventional and renewable assets or a utility, managing what gets on the grid and what gets off the grid – all have a need for the most precise information and the highest quality power production forecasts.
The good news is that it is possible to foresee how big of a risk you may be running with relatively high accuracy.
Before we dig into ways of designing and implementing the perfect wind and solar power production forecasting set-up, let’s take a look at the type of risks coming from wind and solar resources that energy companies and utilities – or any other company directly involved in production, distribution and trading of energy – are facing.
Wind and solar energy production, trading, balancing and overall management is typically connected with one or often multiple set of risks, such as:
- Large scale production fluctuations – this can cover year to year changes in wind and solar radiation, but also climatic impact and climate changes.
- Large variation in predictability – highly dependent on where on the globe your farm is located. Is it less complex, rather flat terrain in, incl. offshore in general, or demanding and thermal driven areas?
- Plant outages (non-scheduled) – cut-offs and grid-operator-forced curtailments
- Weather related outages (storm, icing, snow and desert sand)
- Surplus production – when we have been surprised by our forecasts and the actual production has in fact been higher and we now have to deal with surplus energy
i. Higher balancing costs
ii. Low or negative prices
- Similar consequences apply in case of production deficiency
- Penalties – 90% of costs are distributed over 10% of the time
- Ramp events – i.e. sudden, unforeseen drops or increases in especially wind power generation – problematic both for those balancing the Bulk Power System or the grid (TSO/ISO/RTO) and those who trade
- Thermal effects (coastline or mountain area)
Finally, there is also the risk of not knowing and hence not being able to act upon what others are doing on the market/grid.
Now, as we take a closer look at the above list of risk factors, we quickly discover that many of them are weather and weather-and-terrain related. Why is this important? Well, here comes the formula transforming the wind speed into the actual power produced by a wind turbine.
Any motion of wind has an available kinetic energy, which is given by the following equation:
To calculate the actual power a wind turbine produces, we also have to take the power coefficient (Cp) into account, which is the percentage of extracted power of kinetic energy to mechanical energy: Cp = Output/Input = Pturbine/Pwind
Which of the unknowns do you think are the most unpredictable?
– take a wild guess!
Yes! You got it right! – It’s the wind speed or the velocity! Now add to this the wind direction, air stability, all seasoned with machine learning and you come close to predicting the power generation from your wind turbine.
So, taming the weather and minimizing the uncertainty and inaccuracy of weather input to the above formula is the main job of anybody dealing with wind and solar power production forecasts.
Now that we have established the why, let’s continue to the how – how can energy companies ensure high quality and hence high accuracy of power production forecasts for their wind and solar assets in practice? We’ll cover this in Part 2 of this article.
Wind and solar energy sources are entirely dependent on weather. Full stop. Mastering the ability to forecast the weather and hence the energy produced by wind and solar energy sources is the most important task that energy traders, renewable energy developers, energy companies and utilities are facing today. Their raison d’etre, financial results and everyday operational tasks highly rely on accurate power production forecasts.