Related Experiment Video
Updated: Oct 25, 2025
06:37
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
Published on: December 15, 2023
4.5K
Forecasting Time-Series Energy Data in Buildings Using an Additive Artificial Intelligence Model for Improving Energy
Ngoc-Son Truong1, Ngoc-Tri Ngo1, Anh-Duc Pham1
1Faculty of Project Management, The University of Danang-University of Science and Technology, 54 Nguyen Luong Bang, Danang, Vietnam.
Computational Intelligence and Neuroscience
|August 6, 2021
Summary
This study introduces additive artificial neural networks (AANNs) to predict residential building energy consumption. The AANNs model demonstrated superior accuracy in forecasting energy use, offering a valuable tool for enhancing building energy efficiency.
Area of Science:
- Building Science
- Artificial Intelligence
- Energy Systems
Background:
- Buildings are significant energy consumers, necessitating improved energy efficiency.
- Accurate prediction of building energy consumption is crucial for effective management.
- Existing models may not fully capture the complexities of energy usage in buildings with renewable sources.
Purpose of the Study:
- To propose and evaluate additive artificial neural networks (AANNs) for predicting energy consumption in residential buildings.
- To compare the predictive accuracy of AANNs against Support Vector Regression (SVR) and standard Artificial Neural Networks (ANNs).
- To establish AANNs as an effective tool for improving building energy efficiency.
Main Methods:
- Utilized an hourly resolution dataset from a residential building equipped with a solar photovoltaic system.
- Developed and implemented an additive artificial neural network (AANNs) model.
- Evaluated model performance using Mean Absolute Percentage Error (MAPE) and Mean Absolute Error (MAE).
Main Results:
- The AANNs model achieved a Mean Absolute Percentage Error (MAPE) of 14.04% and a Mean Absolute Error (MAE) of 111.98 Watt-hour.
- AANNs demonstrated a 103.75% improvement in MAPE compared to Support Vector Regression (SVR).
- AANNs showed a 4.6% improvement in MAPE over standard Artificial Neural Networks (ANNs).
Conclusions:
- Additive artificial neural networks (AANNs) are highly effective for forecasting building energy consumption.
- The AANNs model offers significant accuracy improvements over SVR and ANNs.
- This predictive tool can assist building managers in enhancing overall energy efficiency.
Related Concept Videos
02:44Heating and Cooling Curves
24.9K
When a substance—isolated from its environment—is subjected to heat changes, corresponding changes in temperature and phase of the substance is observed; this is graphically represented by heating and cooling curves.
For instance, the addition of heat raises the temperature of a solid; the amount of heat absorbed depends on the heat capacity of the solid (q = mcsolidΔT). According to thermochemistry, the relation between the amount of heat absorbed or released by a substance, q, and its...
For instance, the addition of heat raises the temperature of a solid; the amount of heat absorbed depends on the heat capacity of the solid (q = mcsolidΔT). According to thermochemistry, the relation between the amount of heat absorbed or released by a substance, q, and its...
24.9K
01:17Energy and Power Signals
757
In an electrical system with a resistor, voltage and current signals facilitate the measurement of power and energy across the resistor. For a continuous-time signal, the total energy over a time interval is defined as the integral of the square of the signal's magnitude over that interval. Mathematically, this is expressed as:
757
01:21Energy Losses in Transformers
1.0K
In an ideal transformer, it is assumed that there are no energy losses, and, hence, all the power at the primary winding is transferred to the secondary winding. However, in reality, the transformers always have some energy losses, and, hence, the output power obtained at the secondary winding is less than the input power at the primary winding due to energy losses.
There are four main reasons for energy losses in transformers.
The first cause can be the high resistance of the...
There are four main reasons for energy losses in transformers.
The first cause can be the high resistance of the...
1.0K
01:20Maxwell-Boltzmann Distribution: Problem Solving
1.9K
Individual molecules in a gas move in random directions, but a gas containing numerous molecules has a predictable distribution of molecular speeds, which is known as the Maxwell-Boltzmann distribution, f(v).
This distribution function f(v) is defined by saying that the expected number N (v1,v2) of particles with speeds between v1 and v2 is given by
This distribution function f(v) is defined by saying that the expected number N (v1,v2) of particles with speeds between v1 and v2 is given by
1.9K
01:16Energy Conservation and Bernoulli's Equation
9.9K
Applying the conservation of energy principle or the work-energy theorem to an incompressible, inviscid fluid in laminar, steady, irrotational flow leads to Bernoulli's equation. It states that the sum of the fluid pressure, potential, and kinetic energy per unit volume is constant along a streamline.
All the terms in the equation have the dimension of energy per unit volume. The kinetic energy per unit volume is called the kinetic energy density, and the potential energy per unit volume is...
All the terms in the equation have the dimension of energy per unit volume. The kinetic energy per unit volume is called the kinetic energy density, and the potential energy per unit volume is...
9.9K
01:03Prediction Intervals
2.5K
The interval estimate of any variable is known as the prediction interval. It helps decide if a point estimate is dependable.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
However, the point estimate is most likely not the exact value of the population parameter, but close to it. After calculating point estimates, we construct interval estimates, called confidence intervals or prediction intervals. This prediction interval comprises a range of values unlike the point estimate and is a better predictor of the observed sample value, y.
2.5K