Real-time microgrid optimization algorithm
Microgrid, a local energy provider, to self-provide and resilient system. Microgrids can be tailored per user, regardless standalone or grid tied. Many microcontrollers (PLCs) are used to generate data for feedback and control. The data produced can vary from reading load profile of users, detect...
Saved in:
Main Author: | |
---|---|
Other Authors: | |
Format: | Final Year Project |
Language: | English |
Published: |
Nanyang Technological University
2021
|
Subjects: | |
Online Access: | https://hdl.handle.net/10356/149065 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | Nanyang Technological University |
Language: | English |
id |
sg-ntu-dr.10356-149065 |
---|---|
record_format |
dspace |
spelling |
sg-ntu-dr.10356-1490652023-07-07T18:05:15Z Real-time microgrid optimization algorithm Khoo, Ding Yuan Xu Yan School of Electrical and Electronic Engineering Rolls-Royce-NTU Corp Lab Md.Samar Ahmad xuyan@ntu.edu.sg Engineering::Electrical and electronic engineering::Electric power::Production, transmission and distribution Microgrid, a local energy provider, to self-provide and resilient system. Microgrids can be tailored per user, regardless standalone or grid tied. Many microcontrollers (PLCs) are used to generate data for feedback and control. The data produced can vary from reading load profile of users, detecting extra load consumption and even used to distribute the energy generated smartly. Except, the way the microcontroller worked is through lots of the algorithms, developed through the years. One of the algorithms implemented is machine learning. Neural Network, a type of machine learning, would be a common usage for engineering related solution. Artificial Neural Network (ANN) can do classification or regression. Classification for classify types of load profile, mainly peak and non-peak load consumption. Regression, to predict trend. Regression can be split to 2 types, linear and non-linear. This paper’s aim is to generate a general ANN model that can be used as a load prediction algorithm. Mainly the algorithm must be simplified, to be utilised by PLC. The results of the model will be benchmark against a MATLAB tool-made model to prove the accuracy of the model. The project will be hand coded with the relevant mathematical equations, using MATLAB as a base, without the tools. Input and Target for the training model will be drawn from EMA’s SES 2020 statistic. The purpose of the paper is a prequel to the Real-Time Microgrid Optimization Algorithm. The results produced by this paper achieve part of the major project. The forecast algorithm will produce a predicted value that will be fed into the optimization algorithm Bachelor of Engineering (Electrical and Electronic Engineering) 2021-05-25T05:33:21Z 2021-05-25T05:33:21Z 2021 Final Year Project (FYP) Khoo, D. Y. (2021). Real-time microgrid optimization algorithm. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/149065 https://hdl.handle.net/10356/149065 en B1195 - 201 application/pdf Nanyang Technological University |
institution |
Nanyang Technological University |
building |
NTU Library |
continent |
Asia |
country |
Singapore Singapore |
content_provider |
NTU Library |
collection |
DR-NTU |
language |
English |
topic |
Engineering::Electrical and electronic engineering::Electric power::Production, transmission and distribution |
spellingShingle |
Engineering::Electrical and electronic engineering::Electric power::Production, transmission and distribution Khoo, Ding Yuan Real-time microgrid optimization algorithm |
description |
Microgrid, a local energy provider, to self-provide and resilient system. Microgrids can be
tailored per user, regardless standalone or grid tied. Many microcontrollers (PLCs) are
used to generate data for feedback and control. The data produced can vary from reading
load profile of users, detecting extra load consumption and even used to distribute the
energy generated smartly. Except, the way the microcontroller worked is through lots of
the algorithms, developed through the years. One of the algorithms implemented is
machine learning. Neural Network, a type of machine learning, would be a common usage
for engineering related solution. Artificial Neural Network (ANN) can do classification or
regression. Classification for classify types of load profile, mainly peak and non-peak load
consumption. Regression, to predict trend. Regression can be split to 2 types, linear and
non-linear.
This paper’s aim is to generate a general ANN model that can be used as a load prediction
algorithm. Mainly the algorithm must be simplified, to be utilised by PLC. The results of
the model will be benchmark against a MATLAB tool-made model to prove the accuracy
of the model. The project will be hand coded with the relevant mathematical equations,
using MATLAB as a base, without the tools. Input and Target for the training model will
be drawn from EMA’s SES 2020 statistic.
The purpose of the paper is a prequel to the Real-Time Microgrid Optimization Algorithm.
The results produced by this paper achieve part of the major project. The forecast
algorithm will produce a predicted value that will be fed into the optimization algorithm |
author2 |
Xu Yan |
author_facet |
Xu Yan Khoo, Ding Yuan |
format |
Final Year Project |
author |
Khoo, Ding Yuan |
author_sort |
Khoo, Ding Yuan |
title |
Real-time microgrid optimization algorithm |
title_short |
Real-time microgrid optimization algorithm |
title_full |
Real-time microgrid optimization algorithm |
title_fullStr |
Real-time microgrid optimization algorithm |
title_full_unstemmed |
Real-time microgrid optimization algorithm |
title_sort |
real-time microgrid optimization algorithm |
publisher |
Nanyang Technological University |
publishDate |
2021 |
url |
https://hdl.handle.net/10356/149065 |
_version_ |
1772825396163641344 |