Energy Analytics

PReducing maintenance energy expenses on cell sites is a problem statement.
Whiteklay works with one of the biggest cell site service providers to help them gain efficiency in energy using the IZAC Framework, with the below objectives:

Whiteklay works with one of the biggest cell site service provider to help them gain efficiencyon energy using Izac Framework, with the below objectives :

  • Real-time ingestion of all IOT data from cell sites into the IZAC platform
  • Prediction of Generator Energy
  • Prediction of Mains Energy Consumption
  • Prediction of Total Energy Consumption
  • Analytics on data for various business benefits

solution

To create a single real-time analytical view of the cell sites, the solution needs to collect, process, store, and analyse huge amounts of data in real time. We proposed the IZAC data exchange system, which provided them with a consistent, standardised way of exchanging data and information. The data exchange platform is built using open source technologies and will provide a consistent data repository which can help universities manage and share their data assets. It provides features for effective collaboration without compromising data integrity and access controls. The tool is built using standards like those mentioned in https://www.internationaldataspaces.org/, which lay down the principles of data sharing. Some of the features of the tool are as follows:

  • Real-time data connectivity to multiple sources of data
  • Inbuilt data profiling capabilities to check the quality and structure of data
  • Data Marketplace to facilitate effective collaboration.
  • Rich functions to transform data assets
  • Significant reduction in data engineering and it is simple to use for non-coders.
  • Metering data usage for individuals to check data usage
  • Easy and standard way of sharing data with industries or other academic institutions for research and development.
  • Mitigate legal risk by adding consent management to the data assets.
  • Auditing of data assets

The solution consists of the following phases:

  • Data Extraction and Ingestion
  • Cleaning and analysing data
  • Model Training and Prediction
  • Visualization

Data cleaning and analysis:

  • Filtering of unrequited noise and disturbances from sensor data for better analysis.
  • Analysis of cleaned data for model selection, insight generation and primary testing of accuracy.

Model Training and Prediction

After model selection and creation of the algorithm, the best ensemble machine learning model was trained against the data and predictions were generated for each sight.