CE 186 Fall 2016 Wes Adrianson, Brooke Gemmell, Tyler Newman and - - PowerPoint PPT Presentation

▶
ce 186 fall 2016
SMART_READER_LITE
LIVE PREVIEW

CE 186 Fall 2016 Wes Adrianson, Brooke Gemmell, Tyler Newman and - - PowerPoint PPT Presentation

Dec 29, 2023 411 likes •654 views

CE 186 Fall 2016 Wes Adrianson, Brooke Gemmell, Tyler Newman and Borna Poursheikhani Energy Crisis - The Necessary Shift to Renewables - 48% increase in energy consumption from 2012 to 2048 (IEOE) - 1.2 billion people without access to

slide-1
SLIDE 1

CE 186 Fall 2016

Wes Adrianson, Brooke Gemmell, Tyler Newman and Borna Poursheikhani

slide-2
SLIDE 2
  • 48% increase in energy consumption from

2012 to 2048 (IEOE)

  • 1.2 billion people without access to electricity

in 2016 (WEO)

  • Photovoltaics and efficient devices are more

effective and less expensive than ever

  • Opportunity for solar industry and

technological leapfrogging

Energy Crisis - The Necessary Shift to Renewables

Why mePV? Hardware Optimization Visualization

slide-3
SLIDE 3

Solar Forecasting

  • What is it?
  • What specifically does it apply to?
  • Off the grid
  • In your home
  • Microgrids
  • In the grid itself

*Our Renes based forecasted power

Why mePV? Hardware Optimization Visualization

slide-4
SLIDE 4

Off the grid

This is Ted...

  • Ted lives in a tiny house off the grid
  • Solar forecasting allows Ted to proactively manage his use of energy given

how much he can expect to produce the next day

Why mePV? Hardware Optimization Visualization

slide-5
SLIDE 5

In your home

  • Minimize use of grid electricity
  • Minimize cost (tier pricing)
  • Optimize EV charging
  • Combine with WattTime

mePV is um... quite good

Why mePV? Hardware Optimization Visualization

slide-6
SLIDE 6

Microgrids

  • Manage communal loads and storage

proactively based on forecasted solar generation

  • Forecasting can increase microgrid

resilience to weather events

Why mePV? Hardware Optimization Visualization

slide-7
SLIDE 7

Why mePV? Hardware Optimization Visualization

In the grid

slide-8
SLIDE 8

Introducing:

Why is our product different?

mePV is a consumer-scale machine-learning system for PV power forecasting Running automatically, it adapts to new data without human interference

Why mePV? Hardware Optimization Visualization

slide-9
SLIDE 9

Raspberry Pi 3 Model B Arduino Pro Mini and sensor network Arduino Irradiance MPPT Charge Controller Temperature & Relative Humidity Power Resistor

Why mePV? Hardware Optimization Visualization

Hardware

slide-10
SLIDE 10
  • Array location characteristics
  • Seasonal considerations
  • Weather events

Data Collection

Why mePV? Hardware Optimization Visualization

slide-11
SLIDE 11

Three days of real power data representative of unique PV conditions

Why mePV? Hardware Optimization Visualization

slide-12
SLIDE 12

Connectivity

Why mePV? Hardware Optimization Visualization

P_measured (Real) P_forecast (RENES) P_estimate (mePV)

slide-13
SLIDE 13

Why mePV? Hardware Optimization Visualization

Optimization

slide-14
SLIDE 14

Creating the mePV Forecast

Stacked Retrospective Rolling-Horizon Optimization

Approach 1 (Daily Data) Approach 2 (Hourly Data)

Why mePV? Hardware Optimization Visualization

slide-15
SLIDE 15

Optimization 01

Thursday Friday Renes Forecast: Red Actual Power: Black Renes Forecast: Red mePV Forecast: Blue Power

  • utput:

Watts Sunlight hours [7:00-16:00] Sunlight hours [7:00-16:00] At 00:01AM, use Thursday’s data to calculate mePV Forecast for Friday

Why mePV? Hardware Optimization Visualization

slide-16
SLIDE 16

Renes Forecast: Red mePV Forecast: Blue Actual Power: Black Renes Forecast: Red mePV Forecast: Blue Power

  • utput:

Watts Sunlight hours [6:00-18:00] Sunlight hours [6:00-18:00] At 00:01AM, use Friday’s data to calculate mePV Forecast for Saturday Friday Saturday

Optimization 02

Why mePV? Hardware Optimization Visualization

slide-17
SLIDE 17

Web Visualization

https://mepv-bornap.c9users.io/

Why mePV? Hardware Optimization Visualization

slide-18
SLIDE 18

Why does it matter?

  • Traditional solar forecasting for a single-system

demonstrates error of 30 - 40% rRMSE. ( Lorenz et. al.)

  • Forecasts can help utility providers and

regulators add stability to the grid and avoid the waste of energy.

mePV as a Product

  • Affordable, wireless, and compact
  • Easily deployable for Microgrid and Off-grid usage

with customizable load profiling

  • Minimize electricity costs due informed energy

sourcing in a tiered electricity economy

Why mePV? Hardware Optimization Visualization

slide-19
SLIDE 19

Next steps

  • Continue collecting data and perfecting our optimization
  • Improve stacked parallel optimization parameters
  • Add additional optimization models into stacked ensemble
  • Add load profiling options for users
  • Become Elon Musk

Why mePV? Hardware Optimization Visualization

slide-20
SLIDE 20

mePV_loop runs three functions: both

  • ptimizations and RENES

API request

Creating the mePV Forecast

Why mePV? Hardware Optimization Visualization

slide-21
SLIDE 21

Creating the mePV Forecast

Combined Retrospective Rolling Horizon Optimization = Linear Regression Approach 1 (Daily Data) Linear Regression Approach 2 (Hourly Data) +

Why mePV? Hardware Optimization Visualization

slide-22
SLIDE 22

Combined Retrospective Rolling Horizon Optimization = Linear Regression Approach 1 (Daily Data) Linear Regression Approach 2 (Hourly Data) +

Creating the mePV Forecast

Why mePV? Hardware Optimization Visualization

slide-23
SLIDE 23

Power Temp RH