The existing energy sector has its systems and organization. The grid controls all forms of power distribution and is more like transferring power from a source to different receiving ends. However, with the inclusion of renewable energy, the need for decentralized energy resources cannot be overemphasized, and the NEMoGrid project achieves this.
Renewable energy sources are diverse, making them of various applications, and they have different capacities. Also, the amount of energy produced always needs proper regulation because of fluctuations. The NEMoGrid project aimed to make market designs that fit in, especially for energy communities. This way, optimal integration results occur with renewables on the grid.
The NEMoGrid project rounded off this past year (2020). Also, earlier this year, we conducted some evaluations. An important strategy used in this application is blockchain technology. There are nine (9) partners that synergized to make this project a success. The partners are the University of Applied Sciences and Arts of Southern Switzerland (SUPSI), Centre for Solar Energy and Hydrogen research – Zentrum für Sonnenenergie- und Wasserstoff-Forschung, Baden-Württemberg (ZSW), the professorship Cognitive and Engineering Psychology at the Chemnitz University of Technology (TU Chemnitz), Sustainable Innovation (SUST), Wüstenrot, Ngenic, Sonnen, Upplands Energi and Hive Power.
Problems Solved by NEMoGrid
Some other market models existed before the concept of decentralized energy resources used in the NEMoGrid. They had their limitations, and those particular issues became solved in the NEMoGrid project. Some of these problems include:
- Lack of flexibility in double auction markets – the double auction market is not flexible enough to regulate market participants. It involves a high number of participants who have to provide their energy forecasts and some other information. The double auction market could also easily get manipulated to the advantage of any market actor.
- The possibility of the iterative price discovery mechanism being prone to collusion – this method is highly dependent on initial declarations and capitalizes on flexibility. It is not a mechanism that can easily fish out such culprits because of the information available from the start.
How NEMoGrid Works – Decentralized Energy Resources
There are various actors in the market mechanism used in the NEMoGrid project. They include prosumers, energy communities, distribution system operators, middle actors (aggregators, balance-responsible parties, and virtual power plants), and legislators who work with energy regulators. In addition, NEMoGrid applies the distributed control theory to overcome the challenges of other market methods.
Some things influenced the choice of markets mechanisms, including:
- non-complex nature
- robust price formation
- clearing in pseudo-real-time, say every 15 minutes
Beyond meeting these, the market formulation that NEMoGrid operates considers decentralized energy resources. Its settings involve two factors – allowance for a group of end-users to control alterable loads and an independent system operator with a defined business model. These two factors make for a spread in control.
The end users can always control the usage of some devices and loads. These loads include heat pumps, electric boilers, and the likes. For being this flexible, the end-users get a reward from the distributed capital gain. The business model exploited by the independent system operator is such that it does the redistribution based on how flexible the end-users are.
Hive Power’s Role in NEMoGRid
Energy communities have a naturally decentralized structure. The structure entails the smart meters that collect, process, and store data of prosumers. Hive Power has a solution based on blockchain technology and uses its solution in the NEMoGrid project (to effectively manage this system).
The use of blockchain still encounters some challenges that limit its adoption. These challenges (such as scalability issues and privacy) are all considered in the application by Hive Power. Furthermore, with the creation of local energy communities on the blockchain, the economic and technical points of view come into play with the Hive Platform community manager module since the goal is to optimize all resources.
Milestones and Current Progress on the NEMoGrid Project
Currently, we have completed the NEMoGrid project, and evaluation is going on. You can access the results of the user research on the NEMoGrid website. The three pilots where we evaluated this project across Europe were in:
- Rolle, Switzerland
- Björklinge, Sweden
- Wüstenrot, Germany
The peer-to-peer scenario used in the blockchain market in these energy communities proved profitable and successful when evaluated.
There are seven (7) work packages involved in the NEMoGrid project managing decentralized energy resources. They include project management (WP0), the definition of future scenarios up to 2025 (WP1), market and tariff management design (WP2), the modelling framework (WP3), social acceptance (WP4), scalability and reliability (WP5), and dissemination and reporting (WP6). At this time, we have completed everything.
Also, the project received funds from the joint programming initiative, ERA-Net Smart Energy Systems focus Initiative (Smart Grids Plus), supported by the European Union Horizon 2020 research program (under grant agreement No. 646039). Also, national funding agencies supported the partners in the NEMoGrid project (Swiss, German and Swedish). These brought it to the point of being a success.
What’s Next For NemoGrid?
Adopting the solutions proffered by NEMoGrid can be extended to more applications with increasing energy communities. However, we need the stage to allow these communities to thrive and apply the flexibility of markets. The control algorithms in the NEMoGrid project, when used, will maximize the potential of these self-consumption communities.
The coming steps in the future would involve more implementation of the solutions discovered and improvements. There would always be room for additional extensions or extensive research. At the same time, the project has already put its propositions forward in a reasonable and proven manner. Any further complications or limitations in the course of usage will be recorded and worked on as part of maintenance strategies.
The Forecaster: using machine learning and weather forecasts to more accurately predict energy consumption and generation.
“It’s hard to make predictions – especially about the future.”- Robert Storm Petersen
Predicting the future might well be hard, but it’s often necessary to run the business. Energy forecasting is of primary importance in day-to-day market operations. Short-term forecasting generally involves forecast horizons that range from a few minutes to a few days ahead. Energy Suppliers and Distribution System Operators benefit from accurate predictions of power demand and generation because they can optimally orchestrate their flexible assets to achieve their business goals.
Hive Platform’s Forecaster module computes short-term stochastic forecasts of aggregated energy consumption and PV generation, using the most advanced machine learning methods available. Stochastic means that we not only predict the “shape” of the load curve over time but also calculate confidence intervals around this curve.
Prediction intervals are essential when it comes to risk management applications, such as predicting the daily or monthly peak of consumption and efficiently activating peak shaving mechanisms.
How does it work?
There is no crystal ball (unfortunately). Instead, the Hive Platform’s Forecaster predicts future consumption and generation by learning what happened in the past and using information available from the future. The Forecaster consists of an ensemble of machine learning models trained on and continuously re-informed by a rich dataset.
The data fed into these models includes the power signal itself, numerical weather predictions (temperature, solar radiation, wind speed and direction, humidity, and heaps of other parameters), seasonality information (the time of the day, the day of the week, the month of the year, etc.), public holidays, school holidays, and custom events (lockdowns, white nights, major events, religious events, etc.).
Weather is king
Weather is by far the most important external factor affecting energy consumption and generation. For this reason, Hive Power decided to conduct an internal research study to review and select the most performant numerical weather prediction provider.
One important criterion we considered was the availability of historical weather forecasts. Many weather providers do not archive and store their predictions. However, historical weather forecasts are of crucial importance to train an energy prediction model. To be robust and reliable, a model should be trained on the same type of data that will be used at inference time.
To understand this point, think of the following. If we trained the model on actual weather observations, the model would learn to trust the weather signals to a certain level. When using this model to predict the future, we would need to replace weather observations with weather predictions, which will not be 100% accurate by definition of prediction. Hence the model will give too much weight to the weather predictions and fool itself into error.
Conversely, if we train the model on weather predictions, the model will learn to trust less the weather parameters and commit less error at inference time. Still sceptical? Try out yourself. Some of our most wary scientists did so and found exactly what was expected.
Weather forecast benchmark
We looked at about a dozen different providers, filtered out those that did not tick our boxes, and ended up with five finalists. We then asked them for a sample of their data to build a benchmark. We requested a year’s worth of hourly predictions of ground-level temperature and solar radiation generated for a single location at around midnight and covering from 24 to 48 hours ahead, which is the typical forecast horizon of our energy prediction models. We compared these predictions with actual local observations and were stunned to discover Meteomatics’ superior performance.
In the figures below, we show some results. In Figure 1, we plotted the distribution of the discrepancy between observed and predicted temperature. In Figure 2, we overlay the five distributions for a more convenient comparison. A similar situation was found for the solar radiation parameters. It was then clear to us that Meteomatics numerical weather predictions were the most accurate and well-calibrated.
Figure 1 – Distribution of the discrepancy between observed and predicted ground temperature for five different weather providers. The vertical dashed lines indicate the mean of each distribution (only Meteomatics’ mean error is centred on zero). The Mean Absolute Error (MAE) is reported on each chart (the lower, the better).
Figure 2 – The same error distributions of Figure 1 overlaid (after estimating their kernel density). Meteomatics’ curve is the narrowest and the only one that is zero-centred.
The beginning of a strategic partnership
“We were looking for a one-stop-shop that could provide us with up-to-date and detailed weather data covering Europe, which needed to be conveniently available via a RESTful API. We took quite some time to evaluate several numerical weather prediction providers. It was not an easy choice because of our demanding list of criteria, but Meteomatics checked all the boxes and exceeded our expectations. We were after a provider that covered the whole world, with a focus on Europe and especially the Alps, which are a challenging region when it comes to high-resolution weather forecasting. It was clear from our own forecast benchmarking exercise that Meteomatics was the most accurate weather forecaster, particularly over the short term. We were pleased to discover the rich plethora of standard and advanced weather parameters that Meteomatics’ API offers. We are thrilled to have switched to Meteomatics as our weather data provider of choice, and we foresee a long and fruitful partnership with them.”, said Gianluca Corbellini, Managing Director at Hive Power.
You can read more about this in Meteomatics’ latest press release: https://www.meteomatics.com/en/meteomatics-and-hive-power-agree-strategic-partnership/ .
Stay tuned for an upcoming webinar (26th of October 2021) where Hive Power and Meteomatics will guide you through an in-depth look at how numerical weather predictions inform energy prediction models.