Skip to main navigation
Skip to search
Skip to main content
Heriot-Watt Research Portal Home
Help & FAQ
Link opens in a new tab
Search content at Heriot-Watt Research Portal
Home
Profiles
Research units
Research output
Datasets
Impacts
Equipment
Prizes
Activities
Press/Media
Courses
Short-term forecasting of residential electricity demand using CNN-LSTM
Ashkan Lotfipoor
,
Sandhya Patidar
,
David P. Jenkins
School of Energy, Geoscience, Infrastructure and Society
Institute for Infrastructure & Environment
Institute for Sustainable Building Design
Research output
:
Contribution to conference
›
Paper
›
peer-review
587
Downloads (Pure)
Overview
Fingerprint
Fingerprint
Dive into the research topics of 'Short-term forecasting of residential electricity demand using CNN-LSTM'. Together they form a unique fingerprint.
Sort by
Weight
Alphabetically
INIS
demand
100%
electricity
100%
forecasting
100%
layers
75%
energy demand
75%
prediction
50%
neural networks
50%
data
25%
randomness
25%
planning
25%
comparative evaluations
25%
algorithms
25%
units
25%
energy consumption
25%
learning
25%
efficiency
25%
trains
25%
management
25%
one-dimensional calculations
25%
architecture
25%
policy
25%
households
25%
forests
25%
scotland
25%
energy systems
25%
Engineering
Electricity Demand
100%
Lstm
100%
Convolutional Neural Network
100%
One Dimensional
33%
Moving Average
33%
Convolutional Layer
33%
Random Forest
33%
Energy Consumption Data
33%
Dense Layer
33%
Provide Energy
33%
Energy Systems
33%
Max
33%
Light Gradient Boosting Machine
33%
Long Short-Term Memory
33%
Deep Learning Method
33%
Deep Neural Network
33%