Energy Management Technologies for Smart Home Applications
This paper reviews previous and recent trends in energy managementsystems (EMS) and energy information communication technologies (EICT) forsmart home applications. Relevant EMS and EICT publications on smart homesare reviewed. This paper first analyzes different energy management approachesfor smart home applications, including fuzzy logic, neural networks, heuristicmethods, and evolution-based approaches. Then, various EICT approaches aresurveyed to evaluate the feasibility of smart home applications by discussinghistorical developments and introducing advanced EICT methods. Importantly,this paper contributes to efforts to further advanced energy management tech-nologies for smart home applications.
Content
Chapter 82
Energy Management Technologies
for Smart Home Applications
Huo-Ching Sun, Yann-Chang Huang, Chao-Ming Huang
and Chien-Chin Tung
Abstract This paper reviews previous and recent trends in energy management
systems (EMS) and energy information communication technologies (EICT) for
smart home applications. Relevant EMS and EICT publications on smart homes
are reviewed. This paper first analyzes different energy management approaches
for smart home applications, including fuzzy logic, neural networks, heuristic
methods, and evolution-based approaches. Then, various EICT approaches are
surveyed to evaluate the feasibility of smart home applications by discussing
historical developments and introducing advanced EICT methods. Importantly,
this paper contributes to efforts to further advanced energy management technologies for smart home applications.
Keywords Energy management systems
technologies Smart home applications
Energy information communication
82.1 Introduction
Smart grid integrates advanced information and communications technologies,
automation, sensing and metering technologies, and energy management techniques to incorporate intelligence and bidirectional flows of information and
electricity throughout a power grid. The smart grid is a modern power grid
infrastructure for better efficiency, reliability, with possible integration of
H.-C. Sun Y.-C. Huang (&) C.-C. Tung
Department of Electrical Engineering, Cheng Shiu University, Kaohsiung,
Taiwan, Republic of China
e-mail: [email protected]
C.-M. Huang
Department of Electrical Engineering, Kun Shan University, Tainan,
Taiwan, Republic of China
J. Juang et al. (eds.), Proceedings of the 2nd International Conference on Intelligent
Technologies and Engineering Systems (ICITES2013), Lecture Notes in Electrical Engineering 293,
DOI: 10.1007/978-3-319-04573-3_82, Springer International Publishing Switzerland 2014
659
660
H.-C. Sun et al.
renewable and alternative energy sources. Smart grid technologies can schedule
loads at the consumer level to conserve energy, reduce electricity costs, and
facilitate grid operations.
Figure 82.1 shows the smart grid conceptual model [1]. The smart grid enables
the provision of real-time pricing information and other services to consumers,
using smart meters, home automation networks, and advanced metering infrastructure (AMI). However, expecting a consumer to create an optimal schedule
from many possibilities is unrealistic. Recently, millions of smart meters, sensors,
and automatic control devices have been deployed in residential and commercial
buildings via two-way communication networks. Furthermore, the on/off, cycling,
or mode switching of appliances can be controlled and monitored wirelessly with a
home energy management system by developing smart appliances and deploying
home area networks (HANs).
Therefore, a smart home energy management system (SHEMS) must be
developed, which requires little consumer attention to set up and allows consumers
to compare costs/benefits with different load schedules. The SHEMS motivates
consumers to actively participate in managing their energy consumption for their
own benefit as well as for the efficient, reliable, and economical operations of a
power grid.
82.2 Energy Management Systems
Several hardware and software platforms have been developed to realize a smart
home from the perspective of energy conservation and management [2]. These
systems allow end users to monitor and control key equipment remotely within
their homes and also implement rule-based decision-making about their operations. Some systems also incorporate location-management frameworks that can
either learn and predict occupant location and routes or learn and recognize
occupant activities [3].
An information fusion-based smart home control system [4] was presented to
integrate information from multiple sources to control home appliances. This
system combined information acquisition and fusion, wireless/wired communication modes, central intelligent control algorithms, and user-friendly interfaces of
the central control unit. The fuzzy logic and fuzzy neural network approaches were
applied and both output acceptable lead alarm-time estimations, using information
from physical sensors and open sources.
A proactive, autonomous, context-aware, unobtrusive lighting system [5] for a
lab-based smart home environment was implemented using pattern recognition,
continuous control, and online adaptation approaches. A data mining-based
approach was presented to accurately estimate the prediction interval of the
electricity price series [6]. A novel energy service simulation platform was presented to improve services delivery using maximizing net benefit derived from
energy services [7]. The simulation platform maximized the value of required
82
Energy Management Technologies for Smart Home Applications
661
meter data, home appliance
data & control, distributed
generation & storage data
AMI, EMS, demand response,
demand side management
smart grid applications layer
local area
network
(LAN)
wide area
network
(WAN)
network
gateway
field area
network
(FAN)
smart
meter
home area
network
(HAN)
communications layer
Fig. 82.1 The smart grid conceptual model
services while minimizing the cost of energy consumption by proposing a strategy,
or a schedule for how available distributed energy resources (DERs) should be
operated. To solve this optimization problem and generate effective strategies,
particle swarm optimization (PSO) was applied because this algorithm can be
implemented easily and has global search ability within reasonable computing
times.
Designing smart home device descriptions and standard practices for demand
response and load management applications was presented in [8]. The paper
proposed smart home interfaces and device definitions to allow interoperability
among ZigBee devices produced by various manufacturers of electrical equipment, meters, and smart energy enabling products. The control application
domains include sensing device control, pricing and demand response and load
control applications.
A decision-support system was applied to optimize energy provisions by
allowing end users to first assign values to desired energy services, and then
schedule their available DERs to maximize net benefits [9]. The PSO method was
used to solve the optimization problem, and the basic formulation of cooperative
PSO was enhanced by stochastic repulsion among particles, which adds additional
randomness to particle trajectories during initial iterations and prevents premature
convergence.
Linear programming-based energy consumption scheduling framework [10]
was presented to achieve a desirable trade-off between minimizing electricity
payment and minimizing wait time for operation of each appliance. Test results
suggested that the proposed scheduling design and the price predictor filter
combined significantly reduced user payments and the resulting peak-to-average
ratio in load demand under various load scenarios. Moreover, the proposed optimal
scheduling schemes are beneficial for both end customers and utilities.
To minimize payment or maximize user comfort preferences, two-step linear
and sequential optimization-based algorithm [11] was applied to solve the appliance commitment problem, using price and consumption forecasts. The thermal
dynamics of heating and coasting of the water heater load was modeled by
662
H.-C. Sun et al.
physical models; random hot water consumption was modeled using statistical
methods. Moreover, user comfort settings were regarded as a set of linear
constraints. Test results confirm that the solution may achieves an optimal balance
between energy cost and user comfort level.
A hybrid forecasting framework [12] was presented to deal with dynamics for
predicting electricity price and demand. The proposed framework integrated a
multi-input multi-output forecasting engine for joint price and demand prediction
with data association mining algorithms. A hybrid approach combing PSO and
fuzzy inference for smart home one-step-ahead load forecasting was presented
[13]. The PSO algorithm firstly determined the locations of fuzzy membership
functions. Then, the fuzzy inference approach was adopted to develop the onestep-ahead load forecasting. Test results confirmed that the proposed approach
possessed better forecasting accuracy than existing methods.
82.3 Energy Information Communication Technologies
A smart grid provides consumers with greater control over their individual energy
costs, using technology that allows for monitoring of electricity consumption.
Smart grid technologies can schedule loads at the consumer level to conserve
energy, reduce electricity costs, and facilitate grid operations. The smart meter
delivers real-time electricity prices to homes, allowing customers to leverage data
via an in-home energy management controller (EMC). The EMC uses prices and
user-defined preferences to control power use across a household. Demand
response controls electricity consumption using varying the price of electricity
over a 24-h day period to reduce peak demand.
Using a suite of hardware devices and software programs, SHEMS facilitates
the demand response imperatives of the smart grid while empowering consumers
with information and increasing the control functions automatically or manually.
The SHEMS can be characterized as an electronic information display, allowing
consumers to visualize their energy use, thus facilitating response to dynamic price
signals. To supply real-time feedback on energy consumption, in-home displays
(IHDs) enable residents to lower energy consumption by providing information on
the cost of the energy consumed. In addition to displaying basic information (e.g.,
real-time power use and planed hourly electricity cost and consumption data),
IHDs also allow customers to determine how behavioral changes alter energy
expenditures and consumption. While many IHDs are commercially available,
most are portable, wireless, or plug-in. IHD illustrates the power drawn from an
electric meter using a clip-on device transformer to measure the electric current.
The measured values are communicated to IHD via PLC or wireless radio
frequencies.
AMI is an interactive system that includes smart meters, a wired or wireless
communications network, computer hardware, and meter data management
82
Energy Management Technologies for Smart Home Applications
663
software. AMI enables meters to measure and record customer electricity use and
then transmits this data over the communications network to a central collection
point, either a utility or a third-party aggregator. Progress in AMI has led to the
development of demand-side management (DSM) programs. DSM is the implementation of policies and integrates various appliances with a smart controller,
capable of bi-directional communication with the utility to control, regulate, and
lower energy consumption.
HANs connect home appliances and devices into an integrated communicative
system that links TVs, lights, appliances, computers, SHEMS, and security systems, among other home systems. All devices are connected to a central access
point (i.e. a hub, node, or router) by wired or wireless networks. Complex HANs
are constructed around a smart meter and a network of smart appliances and
thermostats. HANs integrate multiple appliances and devices into a single cohesive wired or wireless communications command and control network that enables
complete home automation and energy management. All HANs comprise the
following elements: hub, gateway, operating system, network management software, information display, and smart appliances.
Two-way communications networks among utilities, grid operators, and
consumers will lay the foundation for deploying SHEMS. The networks must be
reliable and secure when transmitting enormous volumes of data. Their faulttolerant design resists security breaches and repairs itself during extreme power
demand conditions. Networks that incorporate advanced digital switches and
ubiquitous sensing and response devices allow for the interconnection of many
smart appliances. Several communications platforms are tested for this demanding
and flexible networking system. The most common communications platforms
are power line communications (PLC), broadband over power lines (BPL),
ZigBee, Wi-Fi, Z-wave, and Worldwide interoperability for microwave access
(WiMAX).
While various PLC and BPL-based communications are technically feasible,
no current technologies and protocols are technically mature and cost competitive to represent a viable solution. Although BPL installations are currently
limited in number, significant growth is expected as utilities attempt to improve
communications for a smart grid. ZigBee and Wi-Fi network are integrated via a
common home gateway that provides network interoperability and remote access
to the system. ZigBee is designed for use in applications that require low data
rate, low-cost, low power consumption, and two way wireless communications;
Wi-Fi is designed to provide relatively high data rate communications. Z-Wave
uses a low-power RF radio embedded or retrofitted into home electronics
devices and systems; the Z-Wave wireless protocol is optimized for reliable,
low-latency communication of small data packets. WiMAX is a 4G communication technology that attempts to satisfy the requirements of smart grid-minded
utilities; WiMAX is a standards-based technology that allows for delivery of last
mile wireless broadband access as an alternative to cable and digital subscriber
line.
664
H.-C. Sun et al.
82.4 Conclusions
This paper aims to review different energy management approaches for smart
home applications, including fuzzy logic, neural networks, heuristic methods, and
evolution-based approaches. The fuzzy logic was used to combine heterogeneous
sources of information and execute an inference mechanism using IF–THEN rules.
However, the heuristic nature of membership functions and fuzzy rules defined by
expert experience, limit fuzzy logic system performances in real-world applications. Artificial intelligence can be used to implement relatively more powerful,
complex control, decision, and management systems. A hybrid intelligent system
is a good solution when the environment model is so complex that a mathematical
model would be markedly nonlinear or impossible to develop. Therefore, hybrid
intelligent systems for generating control rules derived by learning from examples
should be studied further.
The underlying EICT that enables SHEMS benefits consumers, and the utility is
the availability of an AMI and HAN communication system. For efficacy and easy
deployment, the HAN communication network must be based on a network
technology that utilizes open data architecture, is cheap, consumes a minimum
amount of energy, and does not require extensive new infrastructure. We conclude
that PLC, ZigBee, and Wi-Fi optimally satisfy the requirements for smart home
applications.
Acknowledgments Financial supports from the National Science Council, Taiwan, R.O.C.
under the Grant No. NSC 102-3113-P-006-015 and NSC 101-2632-E-230-001-MY3 are
acknowledged.
References
1. Leeds, D. J. (2009). The smart grid in 2010: market segments, applications and industry
players. Greentech Media Inc.
2. Lien, C. H., Bai, Y. W., & Lin, M. B. (2007). Remote-controllable power outlet system for
home power management. IEEE Transactions on Consumer Electronics, 53, 1634–1641.
3. Roy, A., Das, S., & Basu, K. (2007). A predictive framework for location-aware resource
management in smart homes. IEEE Transaction on Mobile Computer, 6, 1270–1283.
4. Zhang, L., Leung, H., & Chan, K. (2008). Information fusion based smart home control
system and its application. IEEE Transactions on Consumer Electronics, 54, 1157–1165.
5. Vainio, A. M., Valtonen, M., & Vanhala, J. (2008). Proactive fuzzy control and adaptation
methods for smart homes. IEEE Intelligent Systems, 23, 42–49.
6. Zhao, J. H., Dong, Z. Y., Xu, Z., & Wong, K. P. (2008). A statistical approach for interval
forecasting of the electricity price. IEEE Transactions on Power Systems, 23, 267–276.
7. Pedrasa, M. A. Spooner, E. D., & MacGill, I. F. (2009). Improved energy services provision
through the intelligent control of distributed energy resources. In 2009 IEEE Bucharest
Power Tech Conference, pp. 1–8.
8. Han, D., & Lim, J. (2010). Smart home energy management system using IEEE 802.15.4 and
ZigBee. IEEE Transactios on Consumer Electronics, 56, 1403–1410.
82
Energy Management Technologies for Smart Home Applications
665
9. Pedrasa, M. A. A., Spooner, T. D., & MacGill, I. F. (2010). Coordinated scheduling of
residential distributed energy resources to optimize smart home energy services. IEEE
Transactions on Smart Grid, 1, 134–143.
10. Mohsenian-Rad, A. H., & Leon-Garcia, A. (2010). Optimal residential load control with price
prediction in real-time electricity pricing environments. IEEE Transactions on Smart Grid, 1,
120–133.
11. Du, P., & Lu, N. (2011). Appliance commitment for household load scheduling. IEEE
Transactions on Smart Grid, 2, 411–419.
12. Motamedi, A., Zareipour, H., & Rosehart, W. D. (2012). Electricity price and demand
forecasting in smart grids. IEEE Transactions on Smart Grid, 3, 664–674.
13. Huang, C. M., Yang, S. P., Yang, H. T., & Huang, Y. C. (2012). Combined particle swarm
optimization and heuristic fuzzy inference systems for a smart home one-step-ahead load
forecasting. Journal of the Chinese Institute of Engineers, 35, 1–10.
Energy Management Technologies
for Smart Home Applications
Huo-Ching Sun, Yann-Chang Huang, Chao-Ming Huang
and Chien-Chin Tung
Abstract This paper reviews previous and recent trends in energy management
systems (EMS) and energy information communication technologies (EICT) for
smart home applications. Relevant EMS and EICT publications on smart homes
are reviewed. This paper first analyzes different energy management approaches
for smart home applications, including fuzzy logic, neural networks, heuristic
methods, and evolution-based approaches. Then, various EICT approaches are
surveyed to evaluate the feasibility of smart home applications by discussing
historical developments and introducing advanced EICT methods. Importantly,
this paper contributes to efforts to further advanced energy management technologies for smart home applications.
Keywords Energy management systems
technologies Smart home applications
Energy information communication
82.1 Introduction
Smart grid integrates advanced information and communications technologies,
automation, sensing and metering technologies, and energy management techniques to incorporate intelligence and bidirectional flows of information and
electricity throughout a power grid. The smart grid is a modern power grid
infrastructure for better efficiency, reliability, with possible integration of
H.-C. Sun Y.-C. Huang (&) C.-C. Tung
Department of Electrical Engineering, Cheng Shiu University, Kaohsiung,
Taiwan, Republic of China
e-mail: [email protected]
C.-M. Huang
Department of Electrical Engineering, Kun Shan University, Tainan,
Taiwan, Republic of China
J. Juang et al. (eds.), Proceedings of the 2nd International Conference on Intelligent
Technologies and Engineering Systems (ICITES2013), Lecture Notes in Electrical Engineering 293,
DOI: 10.1007/978-3-319-04573-3_82, Springer International Publishing Switzerland 2014
659
660
H.-C. Sun et al.
renewable and alternative energy sources. Smart grid technologies can schedule
loads at the consumer level to conserve energy, reduce electricity costs, and
facilitate grid operations.
Figure 82.1 shows the smart grid conceptual model [1]. The smart grid enables
the provision of real-time pricing information and other services to consumers,
using smart meters, home automation networks, and advanced metering infrastructure (AMI). However, expecting a consumer to create an optimal schedule
from many possibilities is unrealistic. Recently, millions of smart meters, sensors,
and automatic control devices have been deployed in residential and commercial
buildings via two-way communication networks. Furthermore, the on/off, cycling,
or mode switching of appliances can be controlled and monitored wirelessly with a
home energy management system by developing smart appliances and deploying
home area networks (HANs).
Therefore, a smart home energy management system (SHEMS) must be
developed, which requires little consumer attention to set up and allows consumers
to compare costs/benefits with different load schedules. The SHEMS motivates
consumers to actively participate in managing their energy consumption for their
own benefit as well as for the efficient, reliable, and economical operations of a
power grid.
82.2 Energy Management Systems
Several hardware and software platforms have been developed to realize a smart
home from the perspective of energy conservation and management [2]. These
systems allow end users to monitor and control key equipment remotely within
their homes and also implement rule-based decision-making about their operations. Some systems also incorporate location-management frameworks that can
either learn and predict occupant location and routes or learn and recognize
occupant activities [3].
An information fusion-based smart home control system [4] was presented to
integrate information from multiple sources to control home appliances. This
system combined information acquisition and fusion, wireless/wired communication modes, central intelligent control algorithms, and user-friendly interfaces of
the central control unit. The fuzzy logic and fuzzy neural network approaches were
applied and both output acceptable lead alarm-time estimations, using information
from physical sensors and open sources.
A proactive, autonomous, context-aware, unobtrusive lighting system [5] for a
lab-based smart home environment was implemented using pattern recognition,
continuous control, and online adaptation approaches. A data mining-based
approach was presented to accurately estimate the prediction interval of the
electricity price series [6]. A novel energy service simulation platform was presented to improve services delivery using maximizing net benefit derived from
energy services [7]. The simulation platform maximized the value of required
82
Energy Management Technologies for Smart Home Applications
661
meter data, home appliance
data & control, distributed
generation & storage data
AMI, EMS, demand response,
demand side management
smart grid applications layer
local area
network
(LAN)
wide area
network
(WAN)
network
gateway
field area
network
(FAN)
smart
meter
home area
network
(HAN)
communications layer
Fig. 82.1 The smart grid conceptual model
services while minimizing the cost of energy consumption by proposing a strategy,
or a schedule for how available distributed energy resources (DERs) should be
operated. To solve this optimization problem and generate effective strategies,
particle swarm optimization (PSO) was applied because this algorithm can be
implemented easily and has global search ability within reasonable computing
times.
Designing smart home device descriptions and standard practices for demand
response and load management applications was presented in [8]. The paper
proposed smart home interfaces and device definitions to allow interoperability
among ZigBee devices produced by various manufacturers of electrical equipment, meters, and smart energy enabling products. The control application
domains include sensing device control, pricing and demand response and load
control applications.
A decision-support system was applied to optimize energy provisions by
allowing end users to first assign values to desired energy services, and then
schedule their available DERs to maximize net benefits [9]. The PSO method was
used to solve the optimization problem, and the basic formulation of cooperative
PSO was enhanced by stochastic repulsion among particles, which adds additional
randomness to particle trajectories during initial iterations and prevents premature
convergence.
Linear programming-based energy consumption scheduling framework [10]
was presented to achieve a desirable trade-off between minimizing electricity
payment and minimizing wait time for operation of each appliance. Test results
suggested that the proposed scheduling design and the price predictor filter
combined significantly reduced user payments and the resulting peak-to-average
ratio in load demand under various load scenarios. Moreover, the proposed optimal
scheduling schemes are beneficial for both end customers and utilities.
To minimize payment or maximize user comfort preferences, two-step linear
and sequential optimization-based algorithm [11] was applied to solve the appliance commitment problem, using price and consumption forecasts. The thermal
dynamics of heating and coasting of the water heater load was modeled by
662
H.-C. Sun et al.
physical models; random hot water consumption was modeled using statistical
methods. Moreover, user comfort settings were regarded as a set of linear
constraints. Test results confirm that the solution may achieves an optimal balance
between energy cost and user comfort level.
A hybrid forecasting framework [12] was presented to deal with dynamics for
predicting electricity price and demand. The proposed framework integrated a
multi-input multi-output forecasting engine for joint price and demand prediction
with data association mining algorithms. A hybrid approach combing PSO and
fuzzy inference for smart home one-step-ahead load forecasting was presented
[13]. The PSO algorithm firstly determined the locations of fuzzy membership
functions. Then, the fuzzy inference approach was adopted to develop the onestep-ahead load forecasting. Test results confirmed that the proposed approach
possessed better forecasting accuracy than existing methods.
82.3 Energy Information Communication Technologies
A smart grid provides consumers with greater control over their individual energy
costs, using technology that allows for monitoring of electricity consumption.
Smart grid technologies can schedule loads at the consumer level to conserve
energy, reduce electricity costs, and facilitate grid operations. The smart meter
delivers real-time electricity prices to homes, allowing customers to leverage data
via an in-home energy management controller (EMC). The EMC uses prices and
user-defined preferences to control power use across a household. Demand
response controls electricity consumption using varying the price of electricity
over a 24-h day period to reduce peak demand.
Using a suite of hardware devices and software programs, SHEMS facilitates
the demand response imperatives of the smart grid while empowering consumers
with information and increasing the control functions automatically or manually.
The SHEMS can be characterized as an electronic information display, allowing
consumers to visualize their energy use, thus facilitating response to dynamic price
signals. To supply real-time feedback on energy consumption, in-home displays
(IHDs) enable residents to lower energy consumption by providing information on
the cost of the energy consumed. In addition to displaying basic information (e.g.,
real-time power use and planed hourly electricity cost and consumption data),
IHDs also allow customers to determine how behavioral changes alter energy
expenditures and consumption. While many IHDs are commercially available,
most are portable, wireless, or plug-in. IHD illustrates the power drawn from an
electric meter using a clip-on device transformer to measure the electric current.
The measured values are communicated to IHD via PLC or wireless radio
frequencies.
AMI is an interactive system that includes smart meters, a wired or wireless
communications network, computer hardware, and meter data management
82
Energy Management Technologies for Smart Home Applications
663
software. AMI enables meters to measure and record customer electricity use and
then transmits this data over the communications network to a central collection
point, either a utility or a third-party aggregator. Progress in AMI has led to the
development of demand-side management (DSM) programs. DSM is the implementation of policies and integrates various appliances with a smart controller,
capable of bi-directional communication with the utility to control, regulate, and
lower energy consumption.
HANs connect home appliances and devices into an integrated communicative
system that links TVs, lights, appliances, computers, SHEMS, and security systems, among other home systems. All devices are connected to a central access
point (i.e. a hub, node, or router) by wired or wireless networks. Complex HANs
are constructed around a smart meter and a network of smart appliances and
thermostats. HANs integrate multiple appliances and devices into a single cohesive wired or wireless communications command and control network that enables
complete home automation and energy management. All HANs comprise the
following elements: hub, gateway, operating system, network management software, information display, and smart appliances.
Two-way communications networks among utilities, grid operators, and
consumers will lay the foundation for deploying SHEMS. The networks must be
reliable and secure when transmitting enormous volumes of data. Their faulttolerant design resists security breaches and repairs itself during extreme power
demand conditions. Networks that incorporate advanced digital switches and
ubiquitous sensing and response devices allow for the interconnection of many
smart appliances. Several communications platforms are tested for this demanding
and flexible networking system. The most common communications platforms
are power line communications (PLC), broadband over power lines (BPL),
ZigBee, Wi-Fi, Z-wave, and Worldwide interoperability for microwave access
(WiMAX).
While various PLC and BPL-based communications are technically feasible,
no current technologies and protocols are technically mature and cost competitive to represent a viable solution. Although BPL installations are currently
limited in number, significant growth is expected as utilities attempt to improve
communications for a smart grid. ZigBee and Wi-Fi network are integrated via a
common home gateway that provides network interoperability and remote access
to the system. ZigBee is designed for use in applications that require low data
rate, low-cost, low power consumption, and two way wireless communications;
Wi-Fi is designed to provide relatively high data rate communications. Z-Wave
uses a low-power RF radio embedded or retrofitted into home electronics
devices and systems; the Z-Wave wireless protocol is optimized for reliable,
low-latency communication of small data packets. WiMAX is a 4G communication technology that attempts to satisfy the requirements of smart grid-minded
utilities; WiMAX is a standards-based technology that allows for delivery of last
mile wireless broadband access as an alternative to cable and digital subscriber
line.
664
H.-C. Sun et al.
82.4 Conclusions
This paper aims to review different energy management approaches for smart
home applications, including fuzzy logic, neural networks, heuristic methods, and
evolution-based approaches. The fuzzy logic was used to combine heterogeneous
sources of information and execute an inference mechanism using IF–THEN rules.
However, the heuristic nature of membership functions and fuzzy rules defined by
expert experience, limit fuzzy logic system performances in real-world applications. Artificial intelligence can be used to implement relatively more powerful,
complex control, decision, and management systems. A hybrid intelligent system
is a good solution when the environment model is so complex that a mathematical
model would be markedly nonlinear or impossible to develop. Therefore, hybrid
intelligent systems for generating control rules derived by learning from examples
should be studied further.
The underlying EICT that enables SHEMS benefits consumers, and the utility is
the availability of an AMI and HAN communication system. For efficacy and easy
deployment, the HAN communication network must be based on a network
technology that utilizes open data architecture, is cheap, consumes a minimum
amount of energy, and does not require extensive new infrastructure. We conclude
that PLC, ZigBee, and Wi-Fi optimally satisfy the requirements for smart home
applications.
Acknowledgments Financial supports from the National Science Council, Taiwan, R.O.C.
under the Grant No. NSC 102-3113-P-006-015 and NSC 101-2632-E-230-001-MY3 are
acknowledged.
References
1. Leeds, D. J. (2009). The smart grid in 2010: market segments, applications and industry
players. Greentech Media Inc.
2. Lien, C. H., Bai, Y. W., & Lin, M. B. (2007). Remote-controllable power outlet system for
home power management. IEEE Transactions on Consumer Electronics, 53, 1634–1641.
3. Roy, A., Das, S., & Basu, K. (2007). A predictive framework for location-aware resource
management in smart homes. IEEE Transaction on Mobile Computer, 6, 1270–1283.
4. Zhang, L., Leung, H., & Chan, K. (2008). Information fusion based smart home control
system and its application. IEEE Transactions on Consumer Electronics, 54, 1157–1165.
5. Vainio, A. M., Valtonen, M., & Vanhala, J. (2008). Proactive fuzzy control and adaptation
methods for smart homes. IEEE Intelligent Systems, 23, 42–49.
6. Zhao, J. H., Dong, Z. Y., Xu, Z., & Wong, K. P. (2008). A statistical approach for interval
forecasting of the electricity price. IEEE Transactions on Power Systems, 23, 267–276.
7. Pedrasa, M. A. Spooner, E. D., & MacGill, I. F. (2009). Improved energy services provision
through the intelligent control of distributed energy resources. In 2009 IEEE Bucharest
Power Tech Conference, pp. 1–8.
8. Han, D., & Lim, J. (2010). Smart home energy management system using IEEE 802.15.4 and
ZigBee. IEEE Transactios on Consumer Electronics, 56, 1403–1410.
82
Energy Management Technologies for Smart Home Applications
665
9. Pedrasa, M. A. A., Spooner, T. D., & MacGill, I. F. (2010). Coordinated scheduling of
residential distributed energy resources to optimize smart home energy services. IEEE
Transactions on Smart Grid, 1, 134–143.
10. Mohsenian-Rad, A. H., & Leon-Garcia, A. (2010). Optimal residential load control with price
prediction in real-time electricity pricing environments. IEEE Transactions on Smart Grid, 1,
120–133.
11. Du, P., & Lu, N. (2011). Appliance commitment for household load scheduling. IEEE
Transactions on Smart Grid, 2, 411–419.
12. Motamedi, A., Zareipour, H., & Rosehart, W. D. (2012). Electricity price and demand
forecasting in smart grids. IEEE Transactions on Smart Grid, 3, 664–674.
13. Huang, C. M., Yang, S. P., Yang, H. T., & Huang, Y. C. (2012). Combined particle swarm
optimization and heuristic fuzzy inference systems for a smart home one-step-ahead load
forecasting. Journal of the Chinese Institute of Engineers, 35, 1–10.
