energies

Editorial
The Recent Development of Artificial Intelligence for
Smart and Sustainable Energy Systems
and Applications
Miltiadis D. Lytras 1,2 and Kwok Tai Chui 3, *
1 School of Business, Deree College—The American College of Greece, 153-42 Athens, Greece
2 Effat College of Engineering, Effat University, P.O. Box 34689, Jeddah 21478, Saudi Arabia
3 Department of Technology, School of Science and Technology, The Open University of Hong Kong, Ho Man
Tin, Kowloon, Hong Kong, China
* Correspondence: jktchui@ouhk.edu.hk; Tel.: +852-2768-6883




Received: 5 July 2019; Accepted: 7 August 2019; Published: 13 August 2019


Abstract: Human beings share the same community in which the usage of energy by fossil fuels
leads to deterioration in the environment, typically global warming. When the temperature rises to
the critical point and triggers the continual melting of permafrost, it can wreak havoc on the life of
animals and humans. Solutions could include optimizing existing devices, systems, and platforms,
as well as utilizing green energy as a replacement of non-renewable energy. In this special issue
“Artificial Intelligence for Smart and Sustainable Energy Systems and Applications”, eleven (11)
papers, including one review article, have been published as examples of recent developments. Guest
editors also highlight other hot topics beyond the coverage of the published articles.

Keywords: artificial intelligence; computational intelligence; energy management; machine learning;

optimization algorithms; sensor network; smart city; smart grid; sustainable development

1. Introduction
The world mission is not only improving energy systems to become smart but also progressing
sustainable development. It can be further divided into environmental [1], economic [2], and
socio-cultural [3] perspectives. However, there does not exist a perfect energy source as the solution
for sustainable energy. It requires multidisciplinary techniques and systems to achieve the targets.
The rapid advanced development of computer science and engineering enables the implementation
and adoption of artificial intelligence (AI) into various energy systems and applications. This special
issue aims at consolidating recent developments of AI for smart and sustainable energy systems and
applications. Pilot studies are especially welcome. Topics of interest for the special issue include (but
are not limited to):

• New theories and applications of machine learning algorithms in smart grid;

• Design, development, and application of deep learning in smart grid;
• Artificial intelligence in advanced metering infrastructure;
• Multiobjective optimization algorithms in smart grid;
• Disaggregation techniques in non-intrusive load monitoring;
• Modelling and simulation (or co-simulation) in smart grid;
• Internet of Things and smart grid;
• Data driven analytics (descriptive, diagnostic, predictive, and prescriptive) in smart grid;
• Artificial intelligence techniques for security;

Energies 2019, 12, 3108; doi:10.3390/en12163108 www.mdpi.com/journal/energies

Energies 2019, 12, 3108 2 of 7

• Fraud detection and predictive maintenance;

• Demand response in smart grid;
• Peak load management approach in smart grid;
• Interoperability in smart grid;
• Cloud computing based smart grid;
• Vehicle-to-grid design, development, and application.

This Editorial is organized as follows. Section 2 summarizes the published articles in this special
issue. In addition, editors discuss several hot topics beyond the coverage of the special issue articles in
Section 3. Finally, the conclusion is drawn in Section 4.

2. Special Issue Articles

This section not only discusses each of the published articles in the main text but also summarizes
these in the form of a table (Table 1) as a quick review. It is worth mentioning that the topic of
non-intrusive load monitoring (NILM) has contributed five published papers.

Table 1. Summary of the application and methodology of the special issue articles.

Work Application Methodology

Home energy management and ambient
[4] # Non-intrusive load monitoring techniques
assisted living
Non-intrusive load monitoring for energy Genetic algorithm; support vector machine;
[5]
disaggregation multiple kernel learning
Bacterial foraging optimization; flower
[6] Optimizing residential energy consumption
pollination
Non-intrusive load monitoring for energy
[7] Long short-time memory and decision tree
disaggregation
Energy efficient coverage in wireless sensor
[8] Distributed genetic algorithm
network
Enhanced logistic regression; enhanced
recurrent extreme learning machine;
[9] Estimation of load and price of electric grid
classification and regression tree; relief-F and
recursive feature elimination
Detection of the insulators in power
Improved faster region-convolutional neural
[10] transmission and transformation inspection
network
images
Non-intrusive load monitoring for energy
[11] Concatenate convolutional neural network
disaggregation
Non-intrusive load monitoring for energy
[12] Linear-chain conditional random fields
disaggregation
Prediction of the rheological properties of
[13] Artificial neural network
calcium chloride brine-based mud
Estimation of Static Young’s Modulus for Artificial neural network; self-adaptive
[14]
sandstone formation differential evolution
# Review article.

The review article “NILM techniques for intelligent home energy management and ambient
assisted living: A review” authored by A. Ruano, A. Hernandez, J. Ureña, M. Ruano, and J. Garcia
provided a constructive review on home energy management and ambient assisted living [4]. The
focus was on NILM, which aimed at producing a breakdown of the energy profile in equipment level
based on the total energy profile of the apartment. Here, the energy profile could be information
Energies 2019, 12, 3108 3 of 7

related to current, voltage, power, energy, power factor, harmonic distortion, etc. This review article
divided NILM techniques into four parts: data collection, event detection, feature extraction, and load
identification. The authors highlighted that NILM was a highly scalable but less accurate homecare
monitoring system for ambient assisted living, compared to direct and indirect methods via biosensors
and sensors for activity monitoring.
There are ten technical papers that proposed various AI techniques for energy systems and
applications, towards the goal of smart and sustainable development. The first article “Energy
sustainability in smart cities: artificial intelligence, smart monitoring, and optimization of energy
consumption” [5] written by K. T. Chui, M. D. Lytras, and A. Visvizi formulated the NILM algorithm
as a multiobjective optimization problem. Multiple kernel learning was introduced to the support
vector machine classifier to enhance the classification accuracy by integrating valuable characteristics of
kernels. Weighting factors between kernels were added and solved by a genetic algorithm to optimize
the performance.
M. Awais, N. Javaid, K. Aurangzeb, S. Haider, Z. Khan, and D. Mahmood published an
extended article “Towards effective and efficient energy management of single home and a smart
community exploiting heuristic optimization algorithms with critical peak and real-time pricing tariffs
in smart grids” [6] from the conference paper in the 2018 IEEE 32nd International Conference on
Advanced Information Networking and Applications (AINA) [15]. The residential energy consumption
problem was considered as a heuristic multiobjective optimization problem. The bacterial foraging
optimization algorithm and flower pollination algorithm were utilized to minimize the electricity cost
and peak-to-average ratio while maximizing the user comfort. The trade-off solution was recommended
attributable to conflicting objectives.
In [7], T. T. H. Le and H. Kim presented an article “Non-intrusive load monitoring based on novel
transient signal in household appliances with low sampling rate”. Differing from [4], the authors
divided the NILM framework into three parts: data acquisition, feature extraction, and classification
model. The feature vector was constructed by transient signal. Long short-term memory and decision
tree models were applied for the energy disaggregation problem. The performance evaluation of the
proposed method was tested through five appliances: Samsung monitor, LG monitor, hairdryer, fan,
and air purifier, where the accuracy was up to 97%.
Z. J. Wang, Z. H. Zhan, and J. Zhang in their article “Solving the energy efficient coverage
problem in wireless sensor networks: A distributed genetic algorithm approach with hierarchical
fitness evaluation” [8] proposed a distributed genetic algorithm to address the issue of energy efficient
coverage (EEC) in wireless sensor networks. The authors evaluated the fitness using a hierarchical
approach and constructed a two-level fitness function to determine the number of disjoint sets and
its coverage performance. It was demonstrated to be effective in the maximization of the number of
disjoint sets.
Predicting the load and price of the electric grid have been important tasks for utility in lowering
the electricity cost and improving the service quality for end customers. A. Naz, M. U. Javed, N. Javaid,
T. Saba, M. Alhussein, and K. Aurangzeb have addressed these topics via an article “Short-term electric
load and price forecasting using enhanced extreme learning machine optimization in smart grids” [9].
Two-feature extraction approaches were adopted, namely classification and regression tree, relief-F,
and recursive feature elimination. The extracted features were passed to enhanced logistic regression
and enhanced recurrent extreme learning machines for load and price estimation. Results showed that
the proposed two algorithms outperformed existing methods by 5%.
Z. Zhao, Z. Zhen, L. Zhang, Y. Qi, Y. Kong, and K. Zhang have published an article “Insulator
detection method in inspection image based on improved faster R-CNN” [10]. This paper proposed an
improved faster region-convolutional neural network to detect the insulators in power transmission
and transformation inspection images. It yielded a precision of 81.8% with an enhancement of 28%. It
was noted by the authors that the proposed method was customized to the specific type of insulator.
For other insulators, it required further fine-tuning to achieve an optimal performance.
Energies 2019, 12, 3108 4 of 7

The article “Concatenate convolutional neural networks for non-intrusive load monitoring across
complex background” was presented by Q. Wu and F. Wang [11]. The concatenate convolutional neural
network was newly proposed as the NILM technique, which was evaluated based on key performance
indicators: accuracy, robustness, and generalization of load recognition. A key observation was
concluded regarding the background load, which is almost stationary in a given short period of time.
This method improved the F1-score, precision, and recall by 12%, 19%, and 4% respectively.
In [12], H. He, Z. Liu, R. Jiao, and G. Yan proposed a novel algorithm named linear-chain conditional
random fields for energy disaggregation in the article “A novel nonintrusive load monitoring approach
based on linear-chain conditional random fields”. This approach has eliminated some obstacles for
performance improvement: (i) they relax the independent assumption of the hidden Markov model,
and (ii) current and real power are included as representative features. As a result, it achieved an
outstanding accuracy of 96–100%.
A. Gowida, S. Elkatatny, E. Ramadan, and A. Abdulraheem wrote an article “Data-driven
framework to predict the rheological properties of CaCl2 brine-based drill-in fluid using artificial
neural network” [13]. Artificial neural network was adopted to forecast the rheological properties of
brine-based drill-in fluid so that it could avoid the loss of circulation, pipe sticking, and hole cleaning.
The correlation coefficient and average absolute percentage error were 0.97 and <6.1%, respectively.
Finally, A. A. Mahmoud, S. Elkatatny, A. Ali, and T. Moussa contributed an article “Estimation of
static Young’s modulus for sandstone formation using artificial neural networks” [14]. The authors
introduced self-adaptive differential evolution on top of artificial neural network to further enhance
the performance of the estimation of static Young’s modulus for sandstone formation. This approach
reduced the average absolute percentage error significantly from 36% to 1%, as well as the perfect
correlation coefficient.

3. Trends and Future Development

Besides the applications in Table 1, there are numerous applications that apply AI for smart and
sustainable energy systems. The guest editors would like to summarize the key topics—renewable
energy, cloud platform, edge computing, fog computing, as well as electric and plug-in hybrid electric
vehicles—in this section. Also, we have attached a few related works as recommended readings in
each field.
Renewable energy (specifically energy harvesting), acting as an alternative of fossil fuels, is one
of the directions to fight against global warming. Typical sources are solar [16,17] and wind [18,19].
Focuses are basically on the reliability and efficiency of energy harvesting. Other emergent topics
include vibration energy [20], water wave energy [21], acoustic energy [22], and waste-to-energy [23].
The cloud platform is not unfamiliar in today’s era, as many smartphone users have linked their
personal information to it. A more advanced technique of the cloud platform possesses not only big
data storage but also massive computation power, which allows complex data analytics for smart grid
data streaming, processing, analyzing, and storage. Readers are encouraged to read the following
articles [24–27].
Edge computing and fog computing are alternatives to cloud computing that offer relatively local
(lower latency) computation. In other words, data processing and loading can be distributed to edge,
fog, and cloud services. For edge computing, it is recommended for readers to read [28,29], and the
readings for fog computing are [30,31].
There is an increasing portion of new buyers purchasing electric or plug-in hybrid electric
vehicles, which can reduce the usage of fuel. Various AI techniques have been applied to plug-in
hybrid electric vehicles, for instance, artificial neural network [32] and integrated model predictive
controller [33]. When it comes to electric vehicles, biased coupling, torque estimation, and cognitive
heuristic techniques were adopted in [34] and deep neural networks in [35].
Energies 2019, 12, 3108 5 of 7

4. Conclusions
This special issue is composed of eleven papers (one review article) with various topics and
methodologies in AI for smart and sustainable energy systems and applications. Contributors have
shared many valuable insights on recent developments and beyond. The guest editors have briefly
summarized the details of each work, as well as highlighted four groups of emergent topics in the
energy industry. The guest editors would like to thank the contributions of all colleagues and reviewers.
We hope to witness a lot of real implementation and adoption of AI techniques in the energy industry
in the near future.

Author Contributions: K.T.C. and M.D.L. contributed equally to the design, implementation, and the delivery of
the special issue. All co-editors contributed equally in all the phases of this intellectual outcome.
Funding: The authors would like to thank Effat University in Jeddah, Saudi Arabia, for funding the research
reported in this paper through the Research and Consultancy Institute.
Conflicts of Interest: The authors declare no conflict of interest.

References
1. Cuce, E.; Harjunowibowo, D.; Cuce, P.M. Renewable and sustainable energy saving strategies for greenhouse
systems: A comprehensive review. Renew. Sustain. Energy Rev. 2016, 64, 34–59. [CrossRef]
2. Chen, G.Q.; Wu, X.F. Energy overview for globalized world economy: Source, supply chain and sink. Renew.
Sustain. Energy Rev. 2017, 69, 735–749. [CrossRef]
3. Radovanović, M.; Filipović, S.; Pavlović, D. Energy security measurement—A sustainable approach. Renew.
Sustain. Energy Rev. 2017, 68, 1020–1032. [CrossRef]
4. Ruano, A.; Hernandez, A.; Ureña, J.; Ruano, M.; Garcia, J. NILM Techniques for intelligent home energy
management and ambient assisted living: A review. Energies 2019, 12, 2203. [CrossRef]
5. Chui, K.T.; Lytras, M.D.; Visvizi, A. Energy sustainability in smart cities: Artificial intelligence, smart
monitoring, and optimization of energy consumption. Energies 2018, 11, 2869. [CrossRef]
6. Awais, M.; Javaid, N.; Aurangzeb, K.; Haider, S.; Khan, Z.; Mahmood, D. Towards effective and efficient
energy management of single home and a smart community exploiting heuristic optimization algorithms
with critical peak and real-time pricing tariffs in smart grids. Energies 2018, 11, 3125. [CrossRef]
7. Le, T.T.H.; Kim, H. Non-intrusive load monitoring based on novel transient signal in household appliances
with low sampling rate. Energies 2018, 11, 3409. [CrossRef]
8. Wang, Z.J.; Zhan, Z.H.; Zhang, J. Solving the energy efficient coverage problem in wireless sensor networks:
A distributed genetic algorithm approach with hierarchical fitness evaluation. Energies 2018, 11, 3526.
[CrossRef]
9. Naz, A.; Javed, M.U.; Javaid, N.; Saba, T.; Alhussein, M.; Aurangzeb, K. Short-term electric load and price
forecasting using enhanced extreme learning machine optimization in smart grids. Energies 2019, 12, 866.
[CrossRef]
10. Zhao, Z.; Zhen, Z.; Zhang, L.; Qi, Y.; Kong, Y.; Zhang, K. Insulator detection method in inspection image
based on improved faster R-CNN. Energies 2019, 12, 1204. [CrossRef]
11. Wu, Q.; Wang, F. Concatenate convolutional neural networks for non-intrusive load monitoring across
complex background. Energies 2019, 12, 1572. [CrossRef]
12. He, H.; Liu, Z.; Jiao, R.; Yan, G. A novel nonintrusive load monitoring approach based on linear-chain
conditional random fields. Energies 2019, 12, 1797. [CrossRef]
13. Gowida, A.; Elkatatny, S.; Ramadan, E.; Abdulraheem, A. Data-driven framework to predict the rheological
properties of CaCl2 brine-based drill-in fluid using artificial neural network. Energies 2019, 12, 1880.
[CrossRef]
14. Mahmoud, A.A.; Elkatatny, S.; Ali, A.; Moussa, T. Estimation of static young’s modulus for sandstone
formation using artificial neural networks. Energies 2019, 12, 2125. [CrossRef]
Energies 2019, 12, 3108 6 of 7

15. Awais, M.; Javaid, N.; Mateen, A.; Khan, N.; Mohiuddin, A.; Rehman, M.H.A. Meta heuristic and nature
inspired hybrid approach for home energy management using flower pollination algorithm and bacterial
foraging optimization technique. In Proceedings of the 2018 IEEE 32nd International Conference on Advanced
Information Networking and Applications (AINA), Krakow, Poland, 16–18 May 2018; pp. 882–891.
16. Zhang, J.; Lou, M.; Xiang, L.; Hu, L. Power cognition: Enabling intelligent energy harvesting and resource
allocation for solar-powered UAVs. Future Gener. Comput. Syst. 2019. [CrossRef]
17. Chander, A.H.; Kumar, L. MIC for reliable and efficient harvesting of solar energy. IET Power Electron. 2018,
12, 267–275. [CrossRef]
18. Mitiku, T.; Manshahia, M.S. Modeling of wind energy harvesting system: A systematic review. Int. J. Eng.
Sci. Math. 2018, 7, 444–467.
19. Mahmoud, T.; Dong, Z.Y.; Ma, J. An advanced approach for optimal wind power generation prediction
intervals by using self-adaptive evolutionary extreme learning machine. Renew. Energy 2018, 126, 254–269.
[CrossRef]
20. Nabavi, S.; Zhang, L. Design and optimization of a low-resonant-frequency piezoelectric MEMS energy
harvester based on artificial intelligence. Proceedings 2018, 2, 930. [CrossRef]
21. Liu, W.; Xu, L.; Bu, T.; Yang, H.; Liu, G.; Li, W.; Cheng, T. Torus structured triboelectric nanogenerator array
for water wave energy harvesting. Nano Energy 2019, 58, 499–507. [CrossRef]
22. Chen, F.; Wu, Y.; Ding, Z.; Xia, X.; Li, S.; Zheng, H.; Zi, Y. A novel triboelectric nanogenerator based on
electrospun polyvinylidene fluoride nanofibers for effective acoustic energy harvesting and self-powered
multifunctional sensing. Nano Energy 2019, 56, 241–251. [CrossRef]
23. Nicoletti, J.; Ning, C.; You, F. Incorporating agricultural waste-to-energy pathways into biomass product and
process network through data-driven nonlinear adaptive robust optimization. Energy 2019, 180, 556–571.
[CrossRef]
24. Chekired, D.A.; Khoukhi, L. Smart grid solution for charging and discharging services based on cloud
computing scheduling. IEEE Trans. Ind. Inform. 2017, 13, 3312–3321. [CrossRef]
25. Mehmi, S.; Verma, H.K.; Sangal, A.L. Simulation modeling of cloud computing for smart grid using CloudSim.
J. Electr. Syst. Inform. Technol. 2017, 4, 159–172. [CrossRef]
26. Demir, K.; Ismail, H.; Vateva-Gurova, T.; Suri, N. Securing the cloud-assisted smart grid. Int. J. Crit.
Infrastruct. Prot. 2018, 23, 100–111. [CrossRef]
27. Jegadeesan, S.; Azees, M.; Kumar, P.M.; Manogaran, G.; Chilamkurti, N.; Varatharajan, R.; Hsu, C.H. An
efficient anonymous mutual authentication technique for providing secure communication in mobile cloud
computing for smart city applications. Sustain. Cities Soc. 2019, 49, 101522. [CrossRef]
28. Liu, Y.; Yang, C.; Jiang, L.; Xie, S.; Zhang, Y. Intelligent edge computing for IoT-based energy management in
smart cities. IEEE Netw. 2019, 33, 111–117. [CrossRef]
29. Chen, S.; Wen, H.; Wu, J.; Lei, W.; Hou, W.; Liu, W.; Jiang, Y. Internet of things based smart grids supported
by intelligent edge computing. IEEE Access 2019, 7, 74089–74102. [CrossRef]
30. Barros, E.B.C.; Dionísio Machado Filho, L.; Batista, B.G.; Kuehne, B.T.; Peixoto, M.L.M. Fog computing model
to orchestrate the consumption and production of energy in microgrids. Sensors 2019, 19, 2642. [CrossRef]
31. Maatoug, A.; Belalem, G.; Mahmoudi, S. Fog computing framework for location-based energy management
in smart buildings. Multiagent Grid Syst. 2019, 15, 39–56. [CrossRef]
32. Jahangir, H.; Tayarani, H.; Ahmadian, A.; Golkar, M.A.; Miret, J.; Tayarani, M.; Gao, H.O. Charging demand
of plug-in electric vehicles: Forecasting travel behavior based on a novel Rough Artificial Neural Network
approach. J. Clean. Prod. 2019, 229, 1029–1044. [CrossRef]
33. Xie, S.; Hu, X.; Liu, T.; Qi, S.; Lang, K.; Li, H. Predictive vehicle-following power management for plug-in
hybrid electric vehicles. Energy 2019, 166, 701–714. [CrossRef]
Energies 2019, 12, 3108 7 of 7

34. Xiong, H.; Zhang, M.; Zhang, R.; Zhu, X.; Yang, L.; Guo, X.; Cai, B. A new synchronous control method for
dual motor electric vehicle based on cognitive-inspired and intelligent interaction. Future Gener. Comput.
Syst. 2019, 94, 536–548. [CrossRef]
35. Huang, H.B.; Wu, J.H.; Huang, X.R.; Yang, M.L.; Ding, W.P. The development of a deep neural network and
its application to evaluating the interior sound quality of pure electric vehicles. Mech. Syst. Signal Process.
2019, 120, 98–116. [CrossRef]

© 2019 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access
article distributed under the terms and conditions of the Creative Commons Attribution
(CC BY) license (http://creativecommons.org/licenses/by/4.0/).