Home > Research > Publications & Outputs > Neural network learns from mock-up operation ex...

Electronic data

  • 2019Chih-Hsiangmres

    Final published version, 9.72 MB, PDF document

    Available under license: CC BY-NC-ND: Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License

Text available via DOI:

View graph of relations

Neural network learns from mock-up operation experience: implementing on a solar energy community distribution

Research output: ThesisMaster's Thesis

Published

Standard

Neural network learns from mock-up operation experience: implementing on a solar energy community distribution. / Lee, Chih-Hsiang.
Lancaster University, 2019. 84 p.

Research output: ThesisMaster's Thesis

Harvard

APA

Vancouver

Lee C-H. Neural network learns from mock-up operation experience: implementing on a solar energy community distribution. Lancaster University, 2019. 84 p. doi: 10.17635/lancaster/thesis/583

Author

Bibtex

@mastersthesis{ad7f18f9ff7a4e01bf6fce1819cd2504,
title = "Neural network learns from mock-up operation experience: implementing on a solar energy community distribution",
abstract = "Inspired by Imitation Learning, this paper trained a LSTM network by a mock-up operation experience of a solar energy community distribution system. Unlike the conventional method that implements LSTM only to predict features for the control programme to calculate an operation action according to a strategy, the LSTM of the proposed model integrates the strategy into its structure and thus can outputs actions directly. To examine whether the proposed model outperforms the conventional model, this paper first describes an operation strategy, adopted by both models, that aims to decrease total operation cost. Since the strategy needs accurate predictions to work effectively, an expert who can perfectly predict the future is created by historical data. The behaviours of the expert that follows the strategy are used as the training data of the LSTM in the proposed model. During simulation, the proposed model has better performance and computation efficiency than the conventional LSTM model by 25% higher and 75 times faster. Many researches have proposed control models for different systems and implemented LSTM only to predict key uncertainty in those models. To these researches, this paper demonstrates a promising result that the performance of a control model can be improved by integrating the strategy of that model into a neural network with mock-up operation experience.",
keywords = "LSTM, Energy storage applications, Imitation learning, solar energy, Microgrid",
author = "Chih-Hsiang Lee",
year = "2019",
doi = "10.17635/lancaster/thesis/583",
language = "English",
publisher = "Lancaster University",
school = "Lancaster University",

}

RIS

TY - GEN

T1 - Neural network learns from mock-up operation experience

T2 - implementing on a solar energy community distribution

AU - Lee, Chih-Hsiang

PY - 2019

Y1 - 2019

N2 - Inspired by Imitation Learning, this paper trained a LSTM network by a mock-up operation experience of a solar energy community distribution system. Unlike the conventional method that implements LSTM only to predict features for the control programme to calculate an operation action according to a strategy, the LSTM of the proposed model integrates the strategy into its structure and thus can outputs actions directly. To examine whether the proposed model outperforms the conventional model, this paper first describes an operation strategy, adopted by both models, that aims to decrease total operation cost. Since the strategy needs accurate predictions to work effectively, an expert who can perfectly predict the future is created by historical data. The behaviours of the expert that follows the strategy are used as the training data of the LSTM in the proposed model. During simulation, the proposed model has better performance and computation efficiency than the conventional LSTM model by 25% higher and 75 times faster. Many researches have proposed control models for different systems and implemented LSTM only to predict key uncertainty in those models. To these researches, this paper demonstrates a promising result that the performance of a control model can be improved by integrating the strategy of that model into a neural network with mock-up operation experience.

AB - Inspired by Imitation Learning, this paper trained a LSTM network by a mock-up operation experience of a solar energy community distribution system. Unlike the conventional method that implements LSTM only to predict features for the control programme to calculate an operation action according to a strategy, the LSTM of the proposed model integrates the strategy into its structure and thus can outputs actions directly. To examine whether the proposed model outperforms the conventional model, this paper first describes an operation strategy, adopted by both models, that aims to decrease total operation cost. Since the strategy needs accurate predictions to work effectively, an expert who can perfectly predict the future is created by historical data. The behaviours of the expert that follows the strategy are used as the training data of the LSTM in the proposed model. During simulation, the proposed model has better performance and computation efficiency than the conventional LSTM model by 25% higher and 75 times faster. Many researches have proposed control models for different systems and implemented LSTM only to predict key uncertainty in those models. To these researches, this paper demonstrates a promising result that the performance of a control model can be improved by integrating the strategy of that model into a neural network with mock-up operation experience.

KW - LSTM

KW - Energy storage applications

KW - Imitation learning

KW - solar energy

KW - Microgrid

U2 - 10.17635/lancaster/thesis/583

DO - 10.17635/lancaster/thesis/583

M3 - Master's Thesis

PB - Lancaster University

ER -