Offering a New Use for Autoencoders in the Utility Industry

By Adam Nathan, Jason Lu, Jonathan Hahn, Kevin Wald and Rich Lack

Each day, utility companies use smart meters to collect an enormous amount of data on energy usage. In this white paper, you will learn how to cluster customers based on patterns in their electricity usage, as well as be presented with potential service enhancements utility companies may be able to make based on results.

Learn more about our work in AI research and development.


Smart meters used by electric utilities collect an enormous amount of data on energy usage each day. Leveraging this data, we can better understand how individual consumers use their electricity by clustering customers according to their pattern of electricity usage. Clustering, however does not perform well on high-dimensional data such as meter readings. To overcome this, a type of deep neural network called an autoencoder can reduce the dimensionality of the meter reading data to a representative set of relevant patterns. Clustering then can be performed on the lower dimensional, representative data to group together consumers with similar patterns of usage. This clustering is a fully unsupervised technique. In general, this process of reducing dimensionality through auto-encoding and subsequent clustering may be used to characterize a variety of high-dimensional data sources other than electric meter readings.

Login or register to view the rest of the white paper.

  • Recommendation Engine: ATC Connect

    A hybrid recommendation engine was built for recommending relevant articles to the users of the WWT ATC Connect mobile application.
  • Deep Learning with NVIDIA DGX-1

    We have highlighted some practical considerations for the Deep Learning practitioner relevant to neural network training on the NVIDIA DGX-1. Benchmarking experiments showed that GPU performance is related to three dimensions.
  • Machine Learning for Shovel Tooth Failure Detection

    Current computer vision-based methods for identifying broken teeth on mining shovels suffer from a prohibitively high false positive rate (FPR). We describe a two-stage methodology for the detection of broken teeth that reduces the FPR.
  • Infographic: Data-driven Insights Create Richer Experiences

    WWT helps retailers unsilo data sources for insights that improve the brand experience, cement customer loyalty and boost ROI. See how in this infographic.
  • FlexPod Outperforms JBOD for Hadoop at Scale

    This white paper explores the FlexPod Select architecture for Hadoop versus JBOD (“Just a Bunch of Disks”) architecture from both a technical and financial perspective.
  • A Flexible Approach to Deploying SAP HANA

    Software designed to capture and analyze big data can help your team quickly respond to new challenges and improve processes throughout your operations. Today, many organizations are looking to SAP HANA® to analyze data in real time. This white paper discuses the efficiencies of the SAP HANA® platform and how WWT can help with your deployment decisions.
  • Solution Guide: Big Data

    In this practical guide, we take an in-depth look at the challenges, use cases, architectural implications, technologies and strategies that must be considered for a successful big data implementation.
  • Buyer's Guide: Big Data and Hadoop

    This Buyer’s Guide presents a series of guidelines that you can use when searching for the essential Hadoop infrastructure that will be sustaining your organization for years to come.
  • Executive Guide: Big Data and Hadoop

    This is an executive-level book that introduces you to big data, describing what it consists of and what’s driving its momentum, including methodologies to harvest knowledge from structured and unstructured data.
  • Brochure: Big Data Infrastructure

    This brief will help you navigate the crowded technology landscape of new software and hardware products and determine what is "noise" and what may be relevant to you.
  • Infographic: Big Data Deployments

    Infographic on WWT's proven methodology for increasing speed of big data deployments.
  • How Utilities Can Derive Value From Sensor Analytics

    Learn how utilities are tapping their data resources to directly impact business models, operations, processes and revenue through big data analytics.