Renewable Energy research for Chile and Germany

Similar documents
Towards a NNORSY Synergistic GOME-2/IASI Ozone Profile ECV

About Nnergix +2, More than 2,5 GW forecasted. Forecasting in 5 countries. 4 predictive technologies. More than power facilities

CARLOS F. M. COIMBRA (PI) HUGO T. C. PEDRO (CO-PI)

Current best practice of uncertainty forecast for wind energy

Improving the accuracy of solar irradiance forecasts based on Numerical Weather Prediction

Multi-Plant Photovoltaic Energy Forecasting Challenge with Regression Tree Ensembles and Hourly Average Forecasts

Probabilistic Energy Forecasting

Heat Load Forecasting of District Heating System Based on Numerical Weather Prediction Model

Multi-Model Ensemble for day ahead PV power forecasting improvement

MODELLING ENERGY DEMAND FORECASTING USING NEURAL NETWORKS WITH UNIVARIATE TIME SERIES

Multi-Plant Photovoltaic Energy Forecasting Challenge: Second place solution

Integrated Electricity Demand and Price Forecasting

Short and medium term solar irradiance and power forecasting given high penetration and a tropical environment

CHAPTER 6 CONCLUSION AND FUTURE SCOPE

SOLAR POWER FORECASTING BASED ON NUMERICAL WEATHER PREDICTION, SATELLITE DATA, AND POWER MEASUREMENTS

Wind Power Forecasting using Artificial Neural Networks

Country scale solar irradiance forecasting for PV power trading

ECML PKDD Discovery Challenges 2017

EUROPEAN EXPERIENCE: Large-scale cross-country forecasting with the help of Ensemble Forecasts

COMPARISON OF CLEAR-SKY MODELS FOR EVALUATING SOLAR FORECASTING SKILL

Irradiance Forecasts for Electricity Production. Satellite-based Nowcasting for Solar Power Plants and Distribution Networks

Multi-terminal Offshore Grid for the North Sea Region for 2030 and 2050 Scenarios

AN INTERNATIONAL SOLAR IRRADIANCE DATA INGEST SYSTEM FOR FORECASTING SOLAR POWER AND AGRICULTURAL CROP YIELDS

Optimal Demand Response

Machine learning in Higgs analyses

Modelling Wind Farm Data and the Short Term Prediction of Wind Speeds

Renewables and the Smart Grid. Trip Doggett President & CEO Electric Reliability Council of Texas

Bayesian Based Neural Network Model for Solar Photovoltaic Power Forecasting

GL Garrad Hassan Short term power forecasts for large offshore wind turbine arrays

COMPARISON OF CLEAR-SKY MODELS FOR EVALUATING SOLAR FORECASTING SKILL

ANN and Statistical Theory Based Forecasting and Analysis of Power System Variables

The document was not produced by the CAISO and therefore does not necessarily reflect its views or opinion.

A SOLAR AND WIND INTEGRATED FORECAST TOOL (SWIFT) DESIGNED FOR THE MANAGEMENT OF RENEWABLE ENERGY VARIABILITY ON HAWAIIAN GRID SYSTEMS

Systems Operations. PRAMOD JAIN, Ph.D. Consultant, USAID Power the Future. Astana, September, /6/2018

Energy Forecasting Customers: Analysing end users requirements Dec 3rd, 2013 Carlos Alberto Castaño, PhD Head of R&D

SHORT TERM LOAD FORECASTING

High Wind and Energy Specific Models for Global. Production Forecast

Forecasting Solar Irradiance from Time Series with Exogenous Information

THE CLIMATE INFORMATION MODULE

On the use of NWP for Cloud Base Height Estimation in Cloud Camera-Based Solar Irradiance Nowcasting

A Deep Interpretation of Classifier Chains

Importance of Numerical Weather Prediction in Variable Renewable Energy Forecast

Alberto Troccoli, Head of Weather and Energy Research Unit, CSIRO, Australia ICCS 2013 Jamaica, 5 December 2013 (remotely, unfortunately)

Bayesian Inference: Principles and Practice 3. Sparse Bayesian Models and the Relevance Vector Machine

Explanatory Information Analysis for Day-Ahead Price Forecasting in the Iberian Electricity Market

Solar Irradiance Prediction using Neural Model

David John Gagne II, NCAR

Forecasting of Renewable Power Generations

P. M. FONTE GONÇALO XUFRE SILVA J. C. QUADRADO DEEA Centro de Matemática DEEA ISEL Rua Conselheiro Emídio Navarro, LISBOA PORTUGAL

1 (19) Hannele Holttinen, Jussi Ikäheimo

arxiv: v1 [cs.lg] 13 Dec 2013

A Hybrid Deep Learning Approach For Chaotic Time Series Prediction Based On Unsupervised Feature Learning

The Value of (Improved) Renewable Energy Forecasts to Operational and Market Stakeholders. Justin Sharp, Ph.D.

AESO Load Forecast Application for Demand Side Participation. Eligibility Working Group September 26, 2017

Statistical Learning Theory. Part I 5. Deep Learning

Dimensionality Reduction and Principle Components Analysis

AN ARTIFICIAL NEURAL NETWORK BASED APPROACH FOR ESTIMATING DIRECT NORMAL, DIFFUSE HORIZONTAL AND GLOBAL HORIZONTAL IRRADIANCES USING SATELLITE IMAGES

J. Sadeghi E. Patelli M. de Angelis

Towards a Bankable Solar Resource

Study on Impact of Solar Photovoltaic Generation by Atmospheric Variables

Day-Ahead Solar Forecasting Based on Multi-level Solar Measurements

CSC321 Lecture 20: Autoencoders

Wind energy production backcasts based on a high-resolution reanalysis dataset

Modelling residual wind farm variability using HMMs

SOLAR RADIATION RESOURCE ASSESSMENT IN INDIA CONTEXT

Tecnomatix Plant Simulation Worldwide User Conference 2016 FLEXIBILIZATION STUDY OF MATERIAL AND ENERGY FLOWS IN MINING

Solar Generation Prediction using the ARMA Model in a Laboratory-level Micro-grid

FORECASTING: A REVIEW OF STATUS AND CHALLENGES. Eric Grimit and Kristin Larson 3TIER, Inc. Pacific Northwest Weather Workshop March 5-6, 2010

Energy produc-on forecas-ng based on renewable sources of energy

Daily solar radiation forecasting using historical data and examining three methods

Retrieval of Cloud Top Pressure

UniResearch Ltd, University of Bergen, Bergen, Norway WinSim Ltd., Tonsberg, Norway {catherine,

Deep neural networks for ultra-short-term wind forecasting

The Changing Landscape of Land Administration

WIND energy has become a mature technology and has

The Center for Renewable Resource Integration at UC San Diego

Machine Learning I Continuous Reinforcement Learning

A Community Gridded Atmospheric Forecast System for Calibrated Solar Irradiance

Fine-grained Photovoltaic Output Prediction using a Bayesian Ensemble

Deep Learning Basics Lecture 8: Autoencoder & DBM. Princeton University COS 495 Instructor: Yingyu Liang

Tools of AI. Marcin Sydow. Summary. Machine Learning

Forecasting demand in the National Electricity Market. October 2017

Remote Sensing and Sensor Networks:

2013 WEATHER NORMALIZATION SURVEY. Industry Practices

Predicting Solar Irradiance and Inverter power for PV sites

How to Prepare Weather and Climate Models for Future HPC Hardware

Data Mining. Chapter 1. What s it all about?

Gefördert auf Grund eines Beschlusses des Deutschen Bundestages

How to do backpropagation in a brain

Lifetime and Durability Study of Perovskite Solar Cells

An Operational Solar Forecast Model For PV Fleet Simulation. Richard Perez & Skip Dise Jim Schlemmer Sergey Kivalov Karl Hemker, Jr.

operational status and developments

Prediction and Uncertainty Quantification of Daily Airport Flight Delays

Accuracy of near real time updates in wind power forecasting with regard to different weather regimes

Optimal combination of NWP Model Forecasts for AutoWARN

SHORT TERM PREDICTIONS FOR THE POWER OUTPUT OF ENSEMBLES OF WIND TURBINES AND PV-GENERATORS

Short Term Solar Radiation Forecast from Meteorological Data using Artificial Neural Network for Yola, Nigeria

Calibration with MOS at DWD

What is one-month forecast guidance?

Lessons learned from market forecasting

Transcription:

IWoRE, La Serena, 5 th July 2018 Renewable Energy research for Chile and Germany Dr. Martin Felder, Anton Kaifel, Kay Ohnmeiß, Dr. Frank Sehnke, Leon Schröder Zentrum für Sonnenenergie- und Wasserstoff-Forschung Baden-Württemberg (ZSW), Stuttgart, Germany In cooperation with: - 0 -

Outline Machine Learning (ML) for RE applications The German-Chilean project PROREC Wind power forecasting with ML Solar power forecasting with ML Integration of RE into the energy system - 1 -

What is Machine Learning (ML) good for? ML methods excel at fitting parameters from data. But even if the problem is not understood well enough to solve physically, a heuristic model can be built, provided we have data. physical or engineering model: known structure controlled experiments generic model (NN, regression, histogram, ): little prior knowledge exploratory data analysis - 2 -

- 3 - Why isn t everyone using ML?

Outline Machine Learning (ML) for RE applications The German-Chilean project PROREC Wind power forecasting with ML Solar power forecasting with ML Integration of RE into the energy system - 4 -

Chile activities: Status and goals Phase 1: WindSageCL (2012 2014) getting to know the country first contacts and wind forecasts CL Phase 2: PROREC (2015 2018) develop PV- and improve wind forecasts simulation of NCRE supply Phase 3:??? hydrogen from NCRE extension to other S-American countries - 5 -

PROREC project structure Prediction of and Optimized Provision with Renewable Energy in Chile Oct. 2015 to Aug. 2018-6 -

Outline Machine Learning (ML) for RE applications The German-Chilean project PROREC Wind power forecasting with ML Solar power forecasting with ML Integration of RE into the energy system - 7 -

Forecast model setup input vector inputs + targets = 1 pattern split available patterns into training set and independent(!) test set All results shown stem from the test set! possibly other weather models wind forecast targets Deep Neural Network (DNN) Training and test data sets - 8 -

Training on GPU hardware 4 Titan + 8 Titan Black 8 TitanX + 8 TitanXP 1x K20, some older models ca. 220 TFLOPS - 9 -

Example results of Wind Power Forecast in Chile Monte Redondo wind farm observación pronóstico Punta Colorada wind farm

Totoral wind farm Input data sensitivity

Probabilistic power forecast Different target encoding => DNN learns variability from training dataset

Probabilistic forecasts as percentile plots Conversion to percentiles makes probabilistic forecast easier to interpret => adds useful information for traders, grid operators, Totoral wind farm 2015-07-01 12:00 UTC e.g. 90% likelihood that power lies in this band 2015-11-21 16:00 UTC

Outline Machine Learning (ML) for RE applications The German-Chilean project PROREC Wind power forecasting with ML Solar power forecasting with ML Integration of RE into the energy system - 14 -

Cascading forecast time scales escala de tiempo 1 s 1 min 1 h 1 d 1 mes cloud camera satellite images numerical weather prediction work in progress - 15 -

Finding Best Network Architecture Maria Elena PV farm Slight preference for 2 hidden layers with 64 neurons each 2015 2016 2 yrs of hourly data from CEN, manual QC

Solar Forecast Percentiles Luna PV farm observation forecast 120h! Event missed in deterministic forecast, but percentiles show significant drop!

Solar Forecast Percentiles Luna PV farm observation forecast Deterministic forecast would look the same below and above!

Error statistics for different PV farms Input: Three global NWP models, plus live data => Hi-Res NWP model would probably improve results! - 19 -

Cascading forecast time scales escala de tiempo 1 s 1 min 1 h 1 d 1 mes cloud camera satellite images numerical weather prediction work in progress - 20 -

Preparing the image data Inverse polar transformation, because horizon more important than zenith NB: This is not the same image!

Neural network model setup

Neural network model setup Source: www.mdpi.com/1099-4300/19/6/242 Source: neuralnetworksanddeeplearning.com

Presenting the image data concatenated sequential stacked

Solar Power Forecasting using Cloud Camera (5 min forecast of PV power @ Widderstall, Germany) variability of the cloud situation - 28 -

- 29 - Adding satellite images

Compression of Satellite Images with Deep Autoencoder Needed to combine satellites with other sources (data volume!) Special DNN constructed, with 14(!) layers Achieved compression ratio of 32 (using ZCodes of the autoencoder) z - 30 -

- 31 - Cascaded forecast model

- 32 - Combination model for short-term forecasts

Outline Machine Learning (ML) for RE applications The German-Chilean project PROREC Wind power forecasting with ML Solar power forecasting with ML Integration of RE into the energy system - 33 -

- 34 - P²IONEER (Hybrid Power Plant Simulation)

What is Machine Learning (ML) good for? ML methods excel at fitting parameters from data. But even if the problem is not understood well enough to solve physically, a heuristic model can be built, provided we have data. physical or engineering model: known structure controlled experiments generic model (NN, regression, histogram, ): little prior knowledge exploratory data analysis - 35 -

Comparison of assumptions CapEx 2016 (US$/kW) CapEx 2018 (US$/kW) OpEx (invest/a) Wind 2,200 1,800 3.5 % Solar PV 1,600 850 1.5 % Li-Ion 650 550 1.0 % CHP 980 980 2.8 % Diesel 600 600 2.2 % Demand profiles from CEN and GIZ Supply profiles modeled according to Explorador Eólica y Solar Average market prices: Diesel 2016: 5.9 ct/kwh 2018: 4.5 ct/kwh Electricity 2016: 14.3 ct/kwh 2018: 5.67 ct/kwh sources: NRDC, SOWITEC, ZSW

power [MW] Simulation of Hybrid Energy Systems Example Demand has to be met at all hours of the year Excess energy goes into storage and/or is traded over the grid - 37 -

Simulation results for some mines Overall large reduction compared to 2016 run. Cheaper solar power can not quite compensate drop in fuel and electricity prices. Optimization criteria may not be LCOE of electricity alone. => depends on problem! - 38 -

P²IONEER optimization result Here we optimized the supply for a region in Germany, including a local heat distribution network. - 39 -

P 2 IONEER with Power-to-Water component

Conclusions Excellent cooperation between ZSW and ULS produced many interesting results. ML is a powerful tool for dealing with RE data, if applied properly. Forecast quality for wind an PV power depends on availability and quality of local measurements and NWP models. Adding cloud cameras and/or satellite data to improve PV forecasts is non-trivial but probably worthwhile. Interplay of different RE and conventional energy sources, storage and sinks can be simulated with P²IONEER, but results again depend on reliable input data. - 41 -

// Energy with a future // Zentrum für Sonnenenergie- und Wasserstoff- Forschung Baden-Württemberg (ZSW) Thank you for your attention! Contact: martin.felder@zsw-bw.de Stuttgart: Photovoltaics Division (with Solab), Energy Policy and Energy Carriers, Central Division Finance, Human Resources and Legal Widderstall: Solar Test Facility Ulm: Electrochemical Energy Technologies Division, Main Building & elab - 42 - - 42 -