Commercial buildings account for a large share of global energy consumption. However, in many commercial buildings, energy is wasted. For example, when the building is empty, the system still provides energy services. The reason for such problems is that commercial buildings are often large and complex systems, which can accommodate a variety of users with different behaviors and needs.
Building energy management system (BMS) must adapt to various user behaviors, so the use of building energy is not always optimal. Now, with the increase of data on building energy use, a variety of information can be used to optimize the BMS so that the BMS can accurately provide energy services when needed.
At the same time, the significant growth of intermittent renewable energy has brought challenges to the grid operators responsible for the stable power supply of the grid. In this environment, supply and demand matching is very important, and storage technology is one solution, while the source of flexible demand is another solution.
Commercial buildings have the potential to participate in the energy market as a source of flexible demand, which can reduce the load when needed and increase the load when the power supply is sufficient, without affecting its operation performance. This will enable building owners to earn more from buyers of flexible loads.
However, this requires complex BMSs that allow buildings to participate in the electricity market in real time and predict energy supply and demand to ensure that building users do not change the energy use of buildings to a large extent.
Now, with the help of machine-based artificial intelligence algorithm, a large amount of existing data can be used to optimize the energy use of commercial buildings and allow commercial buildings to participate in the market to achieve flexible demand.
One of these systems, called flex2x, was developed by grid edge, a British company. The working principle of the system is to combine the data obtained from the existing energy management system of buildings with other data sources, and then use the artificial intelligence algorithm for analysis. The algorithm can optimize the energy use of buildings in real time. These algorithms are considered “artificial intelligence” because they change based on the data they receive, a process called “learning.”. In this way, the software can predict the building energy consumption 24 hours in advance based on the past experience.
The software also connects to meters and the wider grid. In this way, the electricity price and generation can be monitored, and the electricity charge or carbon intensity at any given time can be used to decide when to increase or decrease the electricity load of buildings.
By controlling when buildings use more or less energy, the software converts the power load curve of buildings from more or less fixed load to flexible load. Flexible loads are an important commodity in today’s energy market, because they can help energy market operators better manage the peaks and troughs of demand, and integrate more intermittent renewable energy into the power grid.
The figure below shows the role of grid edge in the energy system.
Scott， J， Grid Edge： Artificial Intelligence for Energy Systems， Presentation delivered at InternaTIonal Energy Agency Workshop on Modernising Energy Efficiency through DigitalisaTIon， Paris， 27 March 2019
This technology is likely to bring many benefits to a range of parties.
For the residents of buildings, increasing the intelligence of building management system should ensure the optimization of comfort, and provide energy services when needed, and reduce the energy cost due to reducing waste. In addition, residents interested in issues such as the sustainability of buildings will have access to real-time data on information such as the carbon intensity of energy supply to buildings.
For the owners / operators of buildings, intelligent building management systems such as grid edge can reduce costs, reduce carbon emissions and maximize comfort by transferring and optimizing loads, and compensate the upgrading costs of buildings by selling their flexible loads. Knowing that the upfront cost of this upgrade can be offset by trading the flexible load of the building may mean that building owners are willing to invest in sustainable upgrades.
For grid operators, the technology is expected to release new and predictable sources of elastic demand, which will help balance supply and demand, especially when the share of intermittent renewable energy increases.
Measurable benefits include:
The cost saved and revenue generated are equivalent to more than 10% of the annual on-site energy cost;
Reduce carbon emissions through load shifting and efficiency measures (proven to reduce by 40%).
Grid edge has deployed its technology to early adopter customers in the UK and is actively building partnerships with global energy and building control companies to expand its technology.
As for the energy demand optimization of the technology, the key obstacles are likely to be distrusted by building owners and occupants, because the technology can reduce energy consumption without damaging energy services and comfort.
With regard to the flexible load side of the technology, the barriers are likely to be adjustable. Energy market rules must allow flexible demand transactions on a scale that allows commercial buildings to participate in the market. For example, in some energy markets, the minimum allowable bid for participation is higher than the size of the flexible load that a commercial building may provide. In addition, some energy markets require participation in user fees, which may constitute barriers to entry for small-scale participants.
Editor in charge: PJ