
Analysis of energy and control efficiencies of fuzzy logic and artificial
neural network technologies in the heating energy supply system
responding to the changes of user demands
Jonghoon Ahn
a
, Soolyeon Cho
a
, Dae Hun Chung
b,
⇑
a
North Carolina State University, Raleigh, NC 27695, USA
b
Korea Institute of Energy Research, Daejeon, South Korea
highlights
Advanced controllers are proposed to reduce control errors and energy consumption increases.
The FIS and ANN models are utilized to compare conventional thermostat on/off controller.
To provide appropriate thermal energy, the models control the amount of air and its temperature simultaneously.
Control errors, heat gains, and output signals are compared to define models’ effectiveness.
The ANN model shows the best result for space heating responding to intermittent thermal changes.
article info
Article history:
Received 17 August 2016
Received in revised form 28 December 2016
Accepted 28 December 2016
Keywords:
Energy efficiency
Control accuracy
User thermal demand changes
Fuzzy inference system
Artificial neural network
abstract
This paper presents hybrid control approaches for heating air supply in response to changes in demand
by using the Fuzzy Inference System (FIS) and Artificial Neural Network (ANN) fitting models.
Since early 2000’s, some advanced computing and statistical tools were introduced to replace conven-
tional control models in improving control and energy efficiency. Among the tools, the FIS and ANN algo-
rithms were used to define complex interactions between inputs and outputs, and were able to facilitate
control models to predict or evaluate precise thermal performance.
This paper introduces the FIS and ANN control schemes for simultaneously controlling the amount of
supply air and its temperature. Input and output data derived from the FIS results generate and validate
the ANN model, and both models are compared to the typical thermostat on/off baseline control to eval-
uate conditions of supply air for a heating season. The differences between the set-point and actual room
temperature and their sums indicate control efficiency, and the heat gains into a room and their sums
define the energy consumption level. This paper concludes that the simultaneous control of mass and
temperature maintains the desired room temperature in a highly efficient manner. Sensitive controls
may have a disadvantage in terms of energy consumption, but the ANN controller can minimize energy
consumption in comparison with simple thermostat on/off controller. The results also confirm the effec-
tiveness of simultaneous control of mass and temperature using an ANN algorithm corresponding to
intermittent or unpredicted changes in thermal demands.
Ó 2017 Elsevier Ltd. All rights reserved.
1. Introduction
In order to maintain the desired temperature in thermal zones,
there is much focus on improving Heating, Ventilating, and Air-
Conditioning (HVAC) systems. To address these issues, the Propor
tional-Integral-Derivative (PID) algorithm has been used to
improve control technologies to meet various conditions in the
HVAC models. However, most technologies used in developing
the PID algorithm focus on controls for optimizing fuel usage and
fan motor speed. These models are useful for large-scaled HVAC
system, plants, and buildings, but they have many disadvantages
when applied to small, sensitive thermal models requiring imme-
diate response. Recent computing and statistical technologies have
been rapidly developed; such technologies propose effective
approaches and solutions to make controllers more sensitive and
able to immediately respond to various thermal demands.
http://dx.doi.org/10.1016/j.apenergy.2016.12.155
0306-2619/Ó 2017 Elsevier Ltd. All rights reserved.
⇑
Corresponding author.
E-mail addresses: cdh@kier.re.kr, cdh950502@gmail.com (D.H. Chung).
Applied Energy 190 (2017) 222–231
Contents lists available at ScienceDirect
Applied Energy
journal homepage: www.elsevier.com/locate/apenergy