Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
6.8
3.9
Journals
Sensors
Special Issues
Smart Energy City with AI, IoT and Big Data
sensors-logo
Submit to Sensors Review for Sensors Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Smart Energy City with AI, IoT and Big Data

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Internet of Things".

Deadline for manuscript submissions: closed (30 June 2020) | Viewed by 18871

Special Issue Editor

Prof. Dr. Sehyun Park

E-Mail Website
Guest Editor
Department of Intelligent Energy and Industry, Chung-Ang University, Seoul 06974, Republic of Korea
Interests: smart energy; carbon neutrality; digital platform; AI-based data; digital twins; smart buildings and cities
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Currently, AI technology has been applied in various fields to create a smart and intelligent environment to make life better for users. In particular, many challenges are being made to build a sustainable city by integrating AI technology into the energy fields of the city for realizing a more economical, convenient, and safe society. In order to build a sustainable smart city, many companies are integrating its existing energy infrastructure with the latest AI, IoT and Big Data technologies to create smarter and more intelligent environments, and develop up-to-date technologies for reducing energy and greenhouse gas emissions.

The most important technologies for smart energy city are intelligent energy data collection, analysis and optimization technology for the large amounts of data collected in various city environments. Current IoT system architectures in the smart city are facing significant challenges to handle millions of devices and the transmission and processing of large volume of data, etc. The growing diversity of IoT services and complexity of mobile network architectures has made monitoring and managing a multitude of IoT elements extremely difficult in the city environment. In order to build an adaptive system that can be applied to various environments such as technical, cultural, economic and social environments within a city, it is important to apply the latest advanced technologies such as AI, IoT and Big Data based energy data collection and analysis technology, instead of applying the existing general technology. Deep Reinforcement Learning (DRL) and Neural Network (NN) technologies are getting the limelight technologies in artificial intelligence for energy data collection and analysis technology. This Deep Reinforcement Learning (DRL) will help learn not only basic reinforcement learning algorithms, but also advanced deep reinforcement learning algorithms. Depending on user behaviour, the agent receives a numerical reward, ‘R’ from the environment. Ultimately, the DRL finds the best behaviour and results to increase the numerical rewards. In the smart city, the goal is to learn the behavioural patterns through user behaviors and to find the ‘Optimal Policy’ through interactions between agents and the environment. The goal of AI in smart cities can be represented by maximizing ‘Rewards’ through action-value functions.

AI, IoT and Big Data are three of the most widely used terms in recent years, and it's important to know how these technologies are connected. Various types of IoT collect smart and unstructured data in the smart city and can make accurate and optimized judgments through AI-based big data analysis and processing. AI, IoT and Big Data are complementary to each other as part of the technology chain.

In order to provide more intelligent services through data analysis, an important factor is overcoming the cyclical time lag from sharing data making rewards, and the question of whether it can be deployed effectively at low cost is another important issue. For example, to build a smart city based on AI, IoT and Big Data, it is necessary to build a smart energy city data platform to analyze energy data in the city and provide more intelligent services through it. In order to effectively apply AI technology to Smart cities, it is essential to overcome the cyclical lags from collecting and sharing data to creating rewards. In other words, it is necessary to understand the differential cycle parallax characteristics through characteristic classification of various smart energy systems in the city, and to extract and apply new meanings through data linkage and complementation between systems to overcome them. In addition, the smart energy city data platform should build a cost-effective IoT system that can be effectively linked to existing smart grids by digital twin simulation. From the initial stage of building a smart energy city, a plan for deploying various smart energy systems should be devised and a connected smart energy IoT system should be built on a platform.

Finally, to build a sustainable smart energy city in the future, it is necessary to create a new business model with non-repetitive AI-based Smart Energy City Platform and to expand the research and development of various ideas, prototypes, and core technologies through this platform that can be organically linked. The following list shows the main categories of this special issue. In addition, it should be developed under the condition that user safety and security is maintained, and furthermore, the ethical and moral aspects must be considered in order to create an ideal AI-based Smart Energy City Platform.

The following shows the main categories of this special issue.

AI Intelligence in City system with IoT and Big Data

  • Deep Reinforcement Learning (DRL) architecture in large scale IoT system with AI, IoT and Big Data
  • Deep Reinforcement Learning (DRL) driven user behaviour theory and social information network analysis in Smart Energy City environments
  • Advanced Deep Reinforcement Learning (DRL) algorithm with minimum Reward cycle for energy-efficiency in city
  • Advanced Neural Network (NN) based energy-efficient modelling for sustainable smart energy city

AI Intelligence in Energy

  • Experiential energy management technics with Hybrid-Deep Reinforcement Learning (DRL) and Neural Network (NN) in large scale IoT system
  • Experiential energy management services and applications with Hybrid-Deep Reinforcement Learning (DRL) and Neural Network (NN) in large scale IoT system
  • Energy life cycle tracking and management technology
  • Advanced intelligent IoT connection for energy efficiency
  • Advanced intelligent integrated platform for linking smart energy infrastructure

AI platform for Smart Energy City Sustainability

  • Connectivity, Interoperability and Standardization of Smart Energy City with AI
  • Smart Energy City Platform for Energy Sustainability with AI
  • Hybrid DRL platform-based optimal operation (energy production, conversion, storage) technology of heterogeneous energy through analysis of connectivity with IoT and big data
  • Optimization and modelling for minimum reward life-cycle and low cost IoT system with DRL platform
  • IoT enabled Smart Energy Economic Analysis (ROI: Return on Investment)

AI Business Model in Smart Energy City

  • Deep Reinforcement Learning (DRL) for IoT enabled variable applications in Smart Energy City
  • Deep Neural Network (DNN) modelling and analysis guideline in Smart Energy City
  • Advanced Energy Prosumer, Demand Response (DR), IoT and wearable robot for Smart Energy City intelligence
  • Computer Vision Applications for Smart Energy City energy integration
  • Blockchain and Digital-twin based AI Business Models for Energy Efficiency

Security, Safety and Privacy in AI Smart Energy City

  • Deep Reinforcement Learning (DRL) for security and privacy in city
  • Deep Reinforcement Learning (DRL) for industrial security
  • Ethic Aspects of AI Smart Energy City

Prof. Dr. Sehyun Park
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Smart Energy City
  • AI (Artificial Intelligence)
  • Deep Learning (DL)
  • Deep Reinforcement Learning (DRL)
  • Neural Network IoT (Internet of Thing)
  • Big Data
  • Computer Vision
  • AR/VR (Augmented Reality/Vitual Reality)
  • Energy Data Analytics
  • Energy Optimization
  • Sustainability

Published Papers (4 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

35 pages, 15994 KiB  
Article
Reinforcement Learning-Based BEMS Architecture for Energy Usage Optimization
by Sanguk Park, Sangmin Park, Myeong-in Choi, Sanghoon Lee, Tacklim Lee, Seunghwan Kim, Keonhee Cho and Sehyun Park
Sensors 2020, 20(17), 4918; https://doi.org/10.3390/s20174918 - 31 Aug 2020
Cited by 15 | Viewed by 3976
Abstract
Currently, many intelligent building energy management systems (BEMSs) are emerging for saving energy in new and existing buildings and realizing a sustainable society worldwide. However, installing an intelligent BEMS in existing buildings does not realize an innovative and advanced society because it only [...] Read more.
Currently, many intelligent building energy management systems (BEMSs) are emerging for saving energy in new and existing buildings and realizing a sustainable society worldwide. However, installing an intelligent BEMS in existing buildings does not realize an innovative and advanced society because it only involves simple equipment replacement (i.e., replacement of old equipment or LED (Light Emitting Diode) lamps) and energy savings based on a stand-alone system. Therefore, artificial intelligence (AI) is applied to a BEMS to implement intelligent energy optimization based on the latest ICT (Information and Communications Technologies) technology. AI can analyze energy usage data, predict future energy requirements, and establish an appropriate energy saving policy. In this paper, we present a dynamic heating, ventilation, and air conditioning (HVAC) scheduling method that collects, analyzes, and infers energy usage data to intelligently save energy in buildings based on reinforcement learning (RL). In this regard, a hotel is used as the testbed in this study. The proposed method collects, analyzes, and infers IoT data from a building to provide an energy saving policy to realize a futuristic HVAC (heating system) system based on RL. Through this process, a purpose-oriented energy saving methodology to achieve energy saving goals is proposed. Full article
(This article belongs to the Special Issue Smart Energy City with AI, IoT and Big Data)
►▼ Show Figures

Figure 1

24 pages, 5063 KiB  
Article
Routing Based Multi-Agent System for Network Reliability in the Smart Microgrid
by Niharika Singh, Irraivan Elamvazuthi, Perumal Nallagownden, Gobbi Ramasamy and Ajay Jangra
Sensors 2020, 20(10), 2992; https://doi.org/10.3390/s20102992 - 25 May 2020
Cited by 13 | Viewed by 3272
Abstract
Microgrids help to achieve power balance and energy allocation optimality for the defined load networks. One of the major challenges associated with microgrids is the design and implementation of a suitable communication-control architecture that can coordinate actions with system operating conditions. In this [...] Read more.
Microgrids help to achieve power balance and energy allocation optimality for the defined load networks. One of the major challenges associated with microgrids is the design and implementation of a suitable communication-control architecture that can coordinate actions with system operating conditions. In this paper, the focus is to enhance the intelligence of microgrid networks using a multi-agent system while validation is carried out using network performance metrics i.e., delay, throughput, jitter, and queuing. Network performance is analyzed for the small, medium and large scale microgrid using Institute of Electrical and Electronics Engineers (IEEE) test systems. In this paper, multi-agent-based Bellman routing (MABR) is proposed where the Bellman–Ford algorithm serves the system operating conditions to command the actions of multiple agents installed over the overlay microgrid network. The proposed agent-based routing focuses on calculating the shortest path to a given destination to improve network quality and communication reliability. The algorithm is defined for the distributed nature of the microgrid for an ideal communication network and for two cases of fault injected to the network. From this model, up to 35%–43.3% improvement was achieved in the network delay performance based on the Constant Bit Rate (CBR) traffic model for microgrids. Full article
(This article belongs to the Special Issue Smart Energy City with AI, IoT and Big Data)
►▼ Show Figures

Figure 1

17 pages, 3057 KiB  
Article
Multiple Electric Energy Consumption Forecasting Using a Cluster-Based Strategy for Transfer Learning in Smart Building
by Tuong Le, Minh Thanh Vo, Tung Kieu, Eenjun Hwang, Seungmin Rho and Sung Wook Baik
Sensors 2020, 20(9), 2668; https://doi.org/10.3390/s20092668 - 07 May 2020
Cited by 54 | Viewed by 5095
Abstract
Electric energy consumption forecasting is an interesting, challenging, and important issue in energy management and equipment efficiency improvement. Existing approaches are predictive models that have the ability to predict for a specific profile, i.e., a time series of a whole building or an [...] Read more.
Electric energy consumption forecasting is an interesting, challenging, and important issue in energy management and equipment efficiency improvement. Existing approaches are predictive models that have the ability to predict for a specific profile, i.e., a time series of a whole building or an individual household in a smart building. In practice, there are many profiles in each smart building, which leads to time-consuming and expensive system resources. Therefore, this study develops a robust framework for the Multiple Electric Energy Consumption forecasting (MEC) of a smart building using Transfer Learning and Long Short-Term Memory (TLL), the so-called MEC-TLL framework. In this framework, we first employ a k-means clustering algorithm to cluster the daily load demand of many profiles in the training set. In this phase, we also perform Silhouette analysis to specify the optimal number of clusters for the experimental datasets. Next, this study develops the MEC training algorithm, which utilizes a cluster-based strategy for transfer learning the Long Short-Term Memory models to reduce the computational time. Finally, extensive experiments are conducted to compare the computational time and different performance metrics for multiple electric energy consumption forecasting on two smart buildings in South Korea. The experimental results indicate that our proposed approach is capable of economical overheads while achieving superior performances. Therefore, the proposed approach can be applied effectively for intelligent energy management in smart buildings. Full article
(This article belongs to the Special Issue Smart Energy City with AI, IoT and Big Data)
►▼ Show Figures

Figure 1

19 pages, 2242 KiB  
Article
From Intelligent Energy Management to Value Economy through a Digital Energy Currency: Bahrain City Case Study
by Vangelis Marinakis, Haris Doukas, Konstantinos Koasidis and Hanan Albuflasa
Sensors 2020, 20(5), 1456; https://doi.org/10.3390/s20051456 - 06 Mar 2020
Cited by 14 | Viewed by 5222
Abstract
The transition of the energy system into a more efficient state requires innovative ideas to finance new schemes and engage people into adjusting their behavioural patterns concerning consumption. Effective energy management combined with Information and Communication Technologies (ICTs) open new opportunities for local [...] Read more.
The transition of the energy system into a more efficient state requires innovative ideas to finance new schemes and engage people into adjusting their behavioural patterns concerning consumption. Effective energy management combined with Information and Communication Technologies (ICTs) open new opportunities for local and regional authorities, but also for energy suppliers, utilities and other obligated parties, or even energy cooperatives, to implement mechanisms that allow people to become more efficient either by producing and trading energy or by reducing their energy consumption. In this paper, a novel framework is proposed connecting energy savings with a digital energy currency. This framework builds reward schemes where the energy end-users could benefit financially from saving energy, by receiving coins according to their real consumption compared to the predicted consumption if no actions were to take place. A pilot appraisal of such a scheme is presented for the case of Bahrain, so as to simulate the behaviour of the proposed framework in order for it to become a viable choice for intelligent energy management in future action plans. Full article
(This article belongs to the Special Issue Smart Energy City with AI, IoT and Big Data)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-4
Back to TopTop