Energy System Control with Deep Neural Networks

Slides:



Advertisements
Similar presentations
Neural networks Introduction Fitting neural networks
Advertisements

Adaptive Data Collection Strategies for Lifetime-Constrained Wireless Sensor Networks Xueyan Tang Jianliang Xu Sch. of Comput. Eng., Nanyang Technol. Univ.,
Neural Networks Chapter Feed-Forward Neural Networks.
Dan Simon Cleveland State University
CSCI 347 / CS 4206: Data Mining Module 04: Algorithms Topic 06: Regression.
Integrating Neural Network and Genetic Algorithm to Solve Function Approximation Combined with Optimization Problem Term presentation for CSC7333 Machine.
Chapter 11 – Neural Networks COMP 540 4/17/2007 Derek Singer.
11 CSE 4705 Artificial Intelligence Jinbo Bi Department of Computer Science & Engineering
Using Neural Networks to Predict Claim Duration in the Presence of Right Censoring and Covariates David Speights Senior Research Statistician HNC Insurance.
Computer Architecture for Embedded Systems (CAES) group Faculty of Electrical Engineering, Mathematics and Computer Science.
Statistical Tools for Solar Resource Forecasting Vivek Vijay IIT Jodhpur Date: 16/12/2013.
PAPER PRESENTATION Real-Time Coordination of Plug-In Electric Vehicle Charging in Smart Grids to Minimize Power Losses and Improve Voltage Profile IEEE.
Mathematical Models & Optimization?
Reservoir Uncertainty Assessment Using Machine Learning Techniques Authors: Jincong He Department of Energy Resources Engineering AbstractIntroduction.
IHP Im Technologiepark Frankfurt (Oder) Germany IHP Im Technologiepark Frankfurt (Oder) Germany ©
Neural Networks The Elements of Statistical Learning, Chapter 12 Presented by Nick Rizzolo.
Deep Learning Overview Sources: workshop-tutorial-final.pdf
Learning with Neural Networks Artificial Intelligence CMSC February 19, 2002.
Combining Models Foundations of Algorithms and Machine Learning (CS60020), IIT KGP, 2017: Indrajit Bhattacharya.
Machine Learning Supervised Learning Classification and Regression
Neural networks and support vector machines
Big data classification using neural network
CS 9633 Machine Learning Support Vector Machines
Reinforcement Learning
Market Architectures Integrating Ancillary Services from Distributed Energy Resources Olivier Devolder Head of Energy Group N-SIDE.
Deep Feedforward Networks
Optimization of multifluid microgrids, the REIDS project in Singapore
Computer Science and Engineering, Seoul National University
DeepCount Mark Lenson.
Solver & Optimization Problems
Table 1. Advantages and Disadvantages of Traditional DM/ML Methods
Determining the optimal solution to a real-world engineering problem
System Control based Renewable Energy Resources in Smart Grid Consumer
NATIONAL TECHNICAL UNIVERSITY OF ATHENS
Scene 1: Show EV cars charging in a city
Announcements HW4 due today (11:59pm) HW5 out today (due 11/17 11:59pm)
Classification with Perceptrons Reading:
Intelligent Information System Lab
Neural Networks A neural network is a network of simulated neurons that can be used to recognize instances of patterns. NNs learn by searching through.
The Management of Renewable Energy
EE5900: Cyber-Physical Systems
Predict House Sales Price
HOMER.
Policy Compression for MDPs
Overview of Supervised Learning
For Monochromatic Imaging
Random walk initialization for training very deep feedforward networks
Neural Networks: Improving Performance in X-ray Lithography Applications ECE 539 Ryan T. Hogg May 10, 2000.
First simulation results
Optimization of PHEV/EV Battery Charging
Energy Technology, products and solutions for sustainable energy
2500 R Midtown Sacramento Municipal Utility District
Connecting Data with Domain Knowledge in Neural Networks -- Use Deep learning in Conventional problems Lizhong Zheng.
Photovoltaic Systems Engineering Session 16 Solar+Storage Systems
Neural Networks Geoff Hulten.
المشرف د.يــــاســـــــــر فـــــــؤاد By: ahmed badrealldeen
SESO 2018 International Thematic Week
Overfitting and Underfitting
Boltzmann Machine (BM) (§6.4)
Forecasting Electricity Demand and Prices with Machine Learning
Oemof user meeting 09-10/05/2017 Berlin RLI.
Overview of deep learning
Neural networks (1) Traditional multi-layer perceptrons
Jakov Chavez Vega Kalle Valtavirta
Towards sustainable integrated energy systems – distributed low emission production, storage and smart grid Jukka Paatero Aalto University Department.
A HYBRID AND SMART APPROACH TOWARDS RENEWABLE ENERGY CAPACITY ADDITION
Deep Learning Libraries
ELEC-E Smart Grid Demand Response of EV Loads
CS249: Neural Language Model
Electricity Distribution and Energy Decarbonisation
Presentation transcript:

Energy System Control with Deep Neural Networks Fiodar Kazhamiaka Mikhail Kazhamiaka CS 898

Trends in Energy (over the last decade) Renewable energy distributed energy generation Energy storage technologies are getting cheaper flexibility Emerging players (Virtual Power Plants, electric vehicles, etc.) new applications Emergence of new systems with interesting control problems

Neighbour Energy Grid Tesla + SolarCity concept house: Powerwall 2.0, Model 3 EV, solar roof

Outline Online Control Project Design Preliminary Results Why deep learning? Project Design System under study Training and evaluation setup Preliminary Results Remaining/Future Work

Online Control Control objective: Minimize cost (for example) Doesn’t scale with system complexity Our approach State of the art

MPC vs. Neural Network MPC (Deep) Neural Network Performance High TBD

MPC vs. Neural Network MPC (Deep) Neural Network Performance High TBD Offline Effort Medium (requires mathematical formulation of optimization problem) Medium (requires formulation) High? (training effort, TBD)

MPC vs. Neural Network MPC (Deep) Neural Network Performance High TBD Offline Effort Medium (requires mathematical formulation of optimization problem) Medium (requires formulation) High? (training effort, TBD) Online Computational Cost Low

MPC vs. Neural Network MPC (Deep) Neural Network Performance High TBD Offline Effort Medium (requires mathematical formulation of optimization problem) Medium (requires formulation) High? (training effort, TBD) Online Computational Cost Low Requires Predictions Yes No (but can use, if available)

Why deep NN vs. other learning methods? There’s a huge variety of systems and applications Combinations of storage technology, electricity price, electricity sources, and what the system is being used for; no one-size-fits-all solution We don’t know the features Could probably study a single instance of a system and pick out the right features, but this is tedious [1]. Throw every possible input at a deep NN and have it learn to control [1]. Kazhamiaka, Fiodar, Catherine Rosenberg, and Srinivasan Keshav. "Practical strategies for storage operation in energy systems: design and evaluation." IEEE Transactions on Sustainable Energy 7.4 (2016): 1602-1610.

System Residential building with Photovoltaic (PV) panels and energy storage device (ESD) Objective: Minimize grid payments

Training and Evaluation setup Generate Training Data Train Neural Network Evaluate Control Performance Solve linear programs offline to generate a dataset of optimal control actions Regression problem Simulate the system using the NN to make control decisions

Training data through linear programming buy/sell electricity prices battery model parameters control variables money spent – money earned Optimization problem solved using CPLEX solver

Training data through linear programming Mapping from input to optimal control actions: Perturb solar and load data to generate new optimal control datasets to train on

Neural Network input Load PV generation Battery state (energy) Grid price (for next X hours) PV predictions (for next Y hours) Load predictions (for next Z hours)

Neural Network input Load PV Generation Battery state (energy) Grid price (for next X hours) PV predictions (for next Y hours) Load predictions (for next Z hours) Charging Power Discharging Power Power Bought Power Sold Fully connected network

Neural Networks for Regression Problems Cost function: Mean-Squared Error (MSE) Activation function on output: none Image borrowed from deeplearning4j.org tutorial

Evaluating Performance Simulate system, using NN to make control decision Adjust the control output to satisfy constraints Calculate resulting objective function Neural Network

Visual inspection of NN output May not satisfy power balance constraints of the system, so we can adjust buying and selling to ensure that it does.

Hidden layers, nodes per layer (MSE loss) Training Testing

Hidden layers, nodes per layer (simulated cost) Training Testing

Epochs vs. MSE and simulated grid cost Best NN result: 3 layers, 50 nodes, 10 epochs

Thank you! Future Work Continue to tune the hyper-parameters Add predictions of Solar and Load as input Add PV panel and battery size as inputs Compare with MPC and other control algorithms Explore ways of integrating the “real” evaluation of NN performance into the training Thank you!