Scribd Logo
Upload

Welcome to Scribd!

  • 64 views

    EgyE 251 Bartolo Final Report

    Uploaded by

    Vincent Bartolo
    This presentation discusses how machine learning can be used as a tool for energy planning. It begins with definitions of machine learning and examples of general applications. It then explores several specific applications of machine learning in energy planning, including load forecasting, predictive maintenance, plant siting and configuration, energy disaggregation, resource assessment, and business recommendations. The presentation provides images and details for each application discussed. It concludes that machine learning has many applications for complex energy planning problems but also relies on availability of substantial data.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd

    EgyE 251 Bartolo Final Report

    Uploaded by

    Vincent Bartolo
    64 views12 pages
    This presentation discusses how machine learning can be used as a tool for energy planning. It begins with definitions of machine learning and examples of general applications. It then explores several specific applications of machine learning in energy planning, including load forecasting, predictive maintenance, plant siting and configuration, energy disaggregation, resource assessment, and business recommendations. The presentation provides images and details for each application discussed. It concludes that machine learning has many applications for complex energy planning problems but also relies on availability of substantial data.

    Original Description:

    energy planning report

    Copyright

    © © All Rights Reserved

    Available Formats

    PPTX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This presentation discusses how machine learning can be used as a tool for energy planning. It begins with definitions of machine learning and examples of general applications. It then explores several specific applications of machine learning in energy planning, including load forecasting, predictive maintenance, plant siting and configuration, energy disaggregation, resource assessment, and business recommendations. The presentation provides images and details for each application discussed. It concludes that machine learning has many applications for complex energy planning problems but also relies on availability of substantial data.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    64 views12 pages

    EgyE 251 Bartolo Final Report

    Uploaded by

    Vincent Bartolo
    This presentation discusses how machine learning can be used as a tool for energy planning. It begins with definitions of machine learning and examples of general applications. It then explores several specific applications of machine learning in energy planning, including load forecasting, predictive maintenance, plant siting and configuration, energy disaggregation, resource assessment, and business recommendations. The presentation provides images and details for each application discussed. It concludes that machine learning has many applications for complex energy planning problems but also relies on availability of substantial data.

    Copyright:

    © All Rights Reserved
    Download as PPTX, PDF, TXT or read online from Scribd
    Download as pptx, pdf, or txt
    of 12

    Can Machine Learning be

    used as a tool for Energy


    Planning?

    Eldion Vincent H. Bartolo


    1
    Outline of Presentation

     What is Machine Learning


     General Applications of Machine Learning
     Applications of Machine Learning in Energy
    Planning
     Conclusion

    22
    What is Machine Learning?

    Imgsrc: https://www.business2community.com/business-innovation/machine-learning-redefining-enterprise-2016-
    01569528#tfrTTQLQeIm7GZpr.97 33
    What is Machine Learning?

    Imgsrc: https://blogs.oracle.com/ai/types-of-machine-learning-and-top-10-algorithms-everyone-should-know 44
    General Applications of ML

    Imgsrc: https://www.business2community.com/business-innovation/machine-learning-redefining-enterprise-2016-
    01569528#tfrTTQLQeIm7GZpr.97
    55
    Imgsrc: https://developer.ibm.com/docloud/blog/videos/how-is-decision-optimization-fueling-growth-in-energy-and-utilities/
    66
    Applications of ML in Energy Planning
     Load Forecasting - Machine learning could be
    used to forecast supply and demand in real time
    and optimize economic load dispatch.
     Predictive maintenance - drones are trained
    using deep learning algorithms to automatically
    identify defects and predict failures without
    interrupting operations.
     Determining Plant Location, Size, and
    Configuration
     Energy Disaggregation – estimating the power
    demand of individual appliances from a single
    meter
     Resource Assessment – ML can determine the
    abundance of each energy resources and predict
    future values
     Business recommendation - could support
    decision making in area of pricing, energy
    production and selling areas

    Imgsrc: “Long-term optimization of Egypt’s power sector: Policy implications”, Mondal et Al


    77
    Resource Assessment: Wind Energy Forecasting
     DeepMind and Google started
    applying machine learning
    algorithms to 700 megawatts of
    wind power capacity in the central
    United States

     Available weather forecasts and


    historical turbine data

     Predict wind power output 36


    hours ahead of actual generation

     Recommends how to make optimal


    hourly delivery commitments to
    the power grid a full day in
    advance.

    Imgsrc: https://deepmind.com/blog/machine-learning-can-boost-value-wind-energy/
    88
    Resource Assessment: Solar Energy
     Deep Solar by Stanford: An accurate
    deep learning model for detecting solar
    panel on satellite imagery.

     Built a nearly complete solar


    installation database for the
    contiguous US. Includes location, size,
    and type (residential/non-residential)

     Identified key socioeconomic factors


    correlating with solar deployment
    density

     A predictive model to estimate solar


    deployment density (1000
    capita/mile2) at census tract level;
    solar radiation threshold (4.5
    kWh/m2/day)

    Imgsrc: https://www.cell.com/joule/fulltext/S2542-4351(18)30570-1
    99
    Business Recommendation: Imitative Learning for Online Planning in
    Microgrids

     Deep Solar by Stanford: An accurate


    deep learning model for detecting solar
    panel on satellite imagery.

     Built a nearly complete solar


    installation database for the
    contiguous US. Includes location, size,
    and type (residential/non-residential)

     Identified key socioeconomic factors


    correlating with solar deployment
    density

     A predictive model to estimate solar


    deployment density (1000
    capita/mile2) at census tract level;
    solar radiation threshold (4.5
    kWh/m2/day)

    Imgsrc: Imitative learning for online planning on microgrids; Aittahar et al


    1
    10
    Business Recommendation: Reinforcement learning for microgrid energy management

     Deep Solar by Stanford: An accurate


    deep learning model for detecting solar
    panel on satellite imagery.

     Built a nearly complete solar


    installation database for the
    contiguous US. Includes location, size,
    and type (residential/non-residential)

     Identified key socioeconomic factors


    correlating with solar deployment
    density

     A predictive model to estimate solar


    deployment density (1000
    capita/mile2) at census tract level;
    solar radiation threshold (4.5
    kWh/m2/day)

    Imgsrc: Imitative learning for online planning on microgrids; Aittahar et al


    1
    11
    Conclusion
     There are many applications of
    Machine Learning in Energy Planning

     Can possible solve complex decisions in


    energy planning

     ML also heavy relies on data

    Imgsrc: EGYE 251 Notes


    12
    12

    You might also like