Jump to content
  • Energy Analytics

       (0 reviews)

    Nadine Cranenburgh

    Introduction

    Energy analytics is a specific application of IoT data analytics which can be used for several purposes including energy management, predictive maintenance, usage forecasts, anomaly detection and automated reporting.

    To perform effective data analytics using IoT, a good first step is integrating all sources of energy data to a central location for analysis.

    It is worth noting that the difference between energy monitoring and analytics is that monitoring only allows users to view data in a particular format, while analytics provides insights to the user through alerts (for example when there is a system failure or unusually high usage). These insights can also be pushed to business intelligence (BI) tools, building management systems <link>, and data visualisation platforms.

    A diagram depicting a typical energy analytics system is shown below.

    Untitled.thumb.png.f98bf1504ce5f0f00ce1808ed8f550f0.png

    Diagram courtesy of Umesh Bhutoria, EnergyTech Ventures

    Energy Management and anomaly detection

    Like the insights derived from smart metering of water and analysis of the resulting data, the insights from energy analytics can be used to form an understanding of the energy consumption of machinery and plant, and use this to optimise energy consumption and identify problems early. The demand for energy management systems is growing fast, with investment in the tens of billions of dollars.

    An example of an energy management application is shown in the diagram below, the dark green line shows the expected behaviour for a chiller network in a commercial building based on the present week’s consumption. The yellow line shows the expected behaviour based on an earlier consumption period. The difference in the two lines shows that the chiller’s energy consumption has increased over time. This could be linked to maintenance or increased activity. Having this analysis available allows engineers and maintainers to identify and find the source of problems.

    5ae2cd9a3561e_energymanagement.thumb.png.38084f8c4de35c7fef1f015fe5488c97.png

    Diagram courtesy of Umesh Bhutoria, EnergyTech Ventures

    Similarly, anomaly detection using energy analytics looks for variations in observed patterns of energy usage to determine if there is a problem to be rectified. Bringing all the available data together, automating analysis and setting alerts, makes anomaly detection easier than trying to extract information from raw data points in a traditional building management system (BMS).

    Predictive maintenance

    To move towards predictive analytics and predictive maintenance using IoT energy analytics, it is essential to be able to review how systems have behaved in the past, in order to forecast how they will behave in the future.

    While tools such as artificial intelligence and machine learning have potential to predict maintenance requirements, it is necessary to have several years’ worth of maintenance and operation data to train them to predict maintenance requirements effectively.

    A good starting point is putting systems and infrastructure in place and conducting a gap analysis similarly to any other data analytics <link> system implementation and clearly defining your scope and specifications (see the Project Management page for more information)

    Sector-specific energy analytics

    While energy analytic algorithms exist for many generic purposes such as time series and general forecasting, there is a gap in the availability of algorithms specific to particular industry sectors or machinery types.

    For instance, if the objective was to optimise a chiller system, it would be unlikely that an off the shelf algorithmic solution would be available.

    For industry or organisation specific analysis tasks, it might be necessary to seek the expertise of vendors who are able to build the organisation’s understanding of the data to be analysed and to develop tools to use the data to meet business goals.

    Sources:

    The content on this page was primarily sourced from:

    Edited by Nadine Cranenburgh



    User Feedback

    Create an account or sign in to leave a review

    You need to be a member in order to leave a review

    Create an account

    Sign up for a new account in our community. It's easy!

    Register a new account

    Sign in

    Already have an account? Sign in here.

    Sign In Now

    There are no reviews to display.


×