Improving Net Energy Metering (NEM) Actual Load Prediction Accuracy using an Adaptive Learning Rate LSTM Model for Residential Use Case
As an effort to promote renewable energy-based power generation, one of Malaysia's initiatives is the net-energy metering (NEM) scheme. One of the shortcomings of residential Photovoltaic (PV) systems under the NEM scheme is that it operates with smart meters only whereby the actual load profil...
Saved in:
| Main Authors: | , , , |
|---|---|
| Other Authors: | |
| Format: | Conference Paper |
| Published: |
EDP Sciences
2024
|
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| id |
my.uniten.dspace-34039 |
|---|---|
| record_format |
dspace |
| spelling |
my.uniten.dspace-340392024-10-14T11:17:44Z Improving Net Energy Metering (NEM) Actual Load Prediction Accuracy using an Adaptive Learning Rate LSTM Model for Residential Use Case Kunalan D. Krishnan P.S. Ramasamy A.K. Permal N. 56395450700 36053261400 16023154400 56781496300 As an effort to promote renewable energy-based power generation, one of Malaysia's initiatives is the net-energy metering (NEM) scheme. One of the shortcomings of residential Photovoltaic (PV) systems under the NEM scheme is that it operates with smart meters only whereby the actual load profiles by the residential consumers remain unknown. Accurate load prediction for NEM consumers is crucial for optimizing energy consumption and effectively managing net metering credits. This study proposes a new model that incorporates an adaptive learning rate and Long Short-Term Memory (LSTM) to predict the solar output power that subsequently predicts the actual load used by the NEM residential consumers. The proposed model is trained and tested using historical time series data of projected PV power and weather conditions, considering the GPS location of the PV system. The outcome of the proposed model is then compared with other state-of-the-art models like ARIMA and regression methods. It is shown that the proposed model outperforms the traditional forecasting models with a Root Mean Square Error (RMSE) value of 0.1942. � 2023 The Authors, published by EDP Sciences. Final 2024-10-14T03:17:44Z 2024-10-14T03:17:44Z 2023 Conference Paper 10.1051/e3sconf/202343302003 2-s2.0-85175477129 https://www.scopus.com/inward/record.uri?eid=2-s2.0-85175477129&doi=10.1051%2fe3sconf%2f202343302003&partnerID=40&md5=cb087a49ca4a959cae23c61cf5857bfa https://irepository.uniten.edu.my/handle/123456789/34039 433 2003 All Open Access Gold Open Access Green Open Access EDP Sciences Scopus |
| institution |
Universiti Tenaga Nasional |
| building |
UNITEN Library |
| collection |
Institutional Repository |
| continent |
Asia |
| country |
Malaysia |
| content_provider |
Universiti Tenaga Nasional |
| content_source |
UNITEN Institutional Repository |
| url_provider |
http://dspace.uniten.edu.my/ |
| description |
As an effort to promote renewable energy-based power generation, one of Malaysia's initiatives is the net-energy metering (NEM) scheme. One of the shortcomings of residential Photovoltaic (PV) systems under the NEM scheme is that it operates with smart meters only whereby the actual load profiles by the residential consumers remain unknown. Accurate load prediction for NEM consumers is crucial for optimizing energy consumption and effectively managing net metering credits. This study proposes a new model that incorporates an adaptive learning rate and Long Short-Term Memory (LSTM) to predict the solar output power that subsequently predicts the actual load used by the NEM residential consumers. The proposed model is trained and tested using historical time series data of projected PV power and weather conditions, considering the GPS location of the PV system. The outcome of the proposed model is then compared with other state-of-the-art models like ARIMA and regression methods. It is shown that the proposed model outperforms the traditional forecasting models with a Root Mean Square Error (RMSE) value of 0.1942. � 2023 The Authors, published by EDP Sciences. |
| author2 |
56395450700 |
| author_facet |
56395450700 Kunalan D. Krishnan P.S. Ramasamy A.K. Permal N. |
| format |
Conference Paper |
| author |
Kunalan D. Krishnan P.S. Ramasamy A.K. Permal N. |
| spellingShingle |
Kunalan D. Krishnan P.S. Ramasamy A.K. Permal N. Improving Net Energy Metering (NEM) Actual Load Prediction Accuracy using an Adaptive Learning Rate LSTM Model for Residential Use Case |
| author_sort |
Kunalan D. |
| title |
Improving Net Energy Metering (NEM) Actual Load Prediction Accuracy using an Adaptive Learning Rate LSTM Model for Residential Use Case |
| title_short |
Improving Net Energy Metering (NEM) Actual Load Prediction Accuracy using an Adaptive Learning Rate LSTM Model for Residential Use Case |
| title_full |
Improving Net Energy Metering (NEM) Actual Load Prediction Accuracy using an Adaptive Learning Rate LSTM Model for Residential Use Case |
| title_fullStr |
Improving Net Energy Metering (NEM) Actual Load Prediction Accuracy using an Adaptive Learning Rate LSTM Model for Residential Use Case |
| title_full_unstemmed |
Improving Net Energy Metering (NEM) Actual Load Prediction Accuracy using an Adaptive Learning Rate LSTM Model for Residential Use Case |
| title_sort |
improving net energy metering (nem) actual load prediction accuracy using an adaptive learning rate lstm model for residential use case |
| publisher |
EDP Sciences |
| publishDate |
2024 |
| _version_ |
1814061038375534592 |
| score |
13.223943 |