energies-logo

Journal Browser

Journal Browser

Advanced Machine Learning and Big Data Technologies for Smart Cities and Grids

A special issue of Energies (ISSN 1996-1073). This special issue belongs to the section "A1: Smart Grids and Microgrids".

Deadline for manuscript submissions: closed (25 February 2025) | Viewed by 13936

Special Issue Editors


E-Mail Website
Guest Editor
Department of Energy, Politecnico di Milano, Via La Masa 34, 20156 Milan, Italy
Interests: machine learning; smart cities; renewable energy; smart mobility; e-mobility
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Industrial Engineering and Mathematical Sciences Department, Università Politecnica delle Merche, Via Brecce Bianche 12, 60131 Ancona, Italy
Interests: energy management; artificial intelligence; intelligent control; cyber physical systems
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Smart city design emphasizes the efficient management of challenges arising from urbanization, energy consumption, environmental conservation, and economic development while simultaneously enhancing the quality of life for citizens through the adoption of contemporary information and communication technology (ICT). These cities rely on a network of interconnected devices, sensors, and systems that collect and process real-time data to optimize the infrastructure and services of the city. By integrating advanced technologies and citizen engagement, smart cities aim to create sustainable, efficient, and livable urban environments. Machine learning algorithms can be used to analyze large amounts of data from sensors, cameras, and other sources in real time, and to gain insights into the traffic flow, energy consumption patterns, cybersecurity, safety, intelligent transportation systems (ITSs), and other vital metrics.

This Special Issue aims to present and disperse the most recent advances related to applications of machine learning and big data technologies in smart cities.

Topics of interest for publication include, but are not limited to:

  • Energy management: machine learning algorithms can be utilized to optimize energy consumption, forecast energy demand, and identify areas for energy conservation in buildings and smart grids.
  • Intelligent transportation systems: machine learning and big data algorithms can be used to analyze real-time data from traffic sensors, cameras, and other sources to optimize traffic flow, reduce congestion, and improve road safety.
  • Electrification of the transportation system: machine learning algorithms can be used to optimize the electrification of transportation systems by enabling predictive maintenance, battery management, charging infrastructure optimization, and route optimization, as well as by improving vehicle performance and efficiency.
  • Energy-efficient utilization of smart grids: machine learning algorithms can be used to predict energy demand; optimize energy generation and distribution; detect and predict faults in the grid, load forecasting, and energy theft detection; and facilitate demand response programs.
  • Climate change: machine learning can help improve the integration and efficiency of renewable energy sources, such as wind and solar power, by predicting their availability and optimizing their use.
  • Review papers covering the state of the art of the literature on advances in machine learning and big data technologies applications for smart cities and grids.

Dr. Seyed Mahdi Miraftabzadeh
Dr. Michela Longo
Dr. Lucio Ciabattoni
Guest Editors

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. Energies 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

  • machine learning
  • deep learning
  • big data
  • smart cities
  • smart grids

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue policies can be found here.

Related Special Issue

Published Papers (7 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Jump to: Review

22 pages, 5398 KiB  
Article
Deep Learning Framework Using Transformer Networks for Multi Building Energy Consumption Prediction in Smart Cities
by Samuel Moveh, Emmanuel Alejandro Merchán-Cruz, Maher Abuhussain, Yakubu Aminu Dodo, Saleh Alhumaid and Ali Hussain Alhamami
Energies 2025, 18(6), 1468; https://doi.org/10.3390/en18061468 - 17 Mar 2025
Viewed by 384
Abstract
The increasing complexity of urban building energy systems necessitates advanced prediction methods for efficient energy management. Urban buildings account for approximately 40% of global energy consumption, making accurate prediction crucial for sustainability goals. This research develops a novel transformer-based deep learning framework for [...] Read more.
The increasing complexity of urban building energy systems necessitates advanced prediction methods for efficient energy management. Urban buildings account for approximately 40% of global energy consumption, making accurate prediction crucial for sustainability goals. This research develops a novel transformer-based deep learning framework for multi-building energy consumption forecasting. Despite recent advances in energy prediction techniques, existing models struggle with multi-building scenarios due to limited ability to capture cross-building correlations, inadequate integration of diverse data streams, and poor scalability when deployed at urban scale—gaps this research specifically addresses. The study implemented a modified transformer architecture with hierarchical attention mechanisms, processing data from 100 commercial buildings across three climate zones over three years (2020–2023). The framework incorporated weather parameters, occupancy patterns, and historical energy consumption data through multi-head attention layers, employing a 4000-step warm-up period and adaptive regularization techniques. The evaluation included a comparison with the baseline models (ARIMA, LSTM, GRU) and robustness testing. The framework achieved a 23.7% improvement in prediction accuracy compared to traditional methods, with a mean absolute percentage error of 3.2%. Performance remained stable across building types, with office complexes showing the highest accuracy (MAPE = 2.8%) and healthcare facilities showing acceptable variance (MAPE = 3.5%). The model-maintained prediction stability under severe data perturbations while demonstrating near-linear computational scaling. The transformer-based approach significantly enhances building energy prediction capabilities, enabling more effective demand-side management strategies, though future research should address long-term adaptability. Full article
Show Figures

Figure 1

19 pages, 2947 KiB  
Article
Validating the Smart Grid Architecture Model for Sustainable Energy Community Implementation: Challenges, Solutions, and Lessons Learned
by Valentina Janev, Lazar Berbakov, Nikola Tomašević, Jesús Martin-Borja Sotoca and Sergio Lujan
Energies 2025, 18(3), 641; https://doi.org/10.3390/en18030641 - 30 Jan 2025
Viewed by 1045
Abstract
The integration of renewable energy sources (RESs) and the establishment of energy communities (ECs) are vital steps in achieving global sustainability goals. This paper presents a methodology for developing and validating a Smart Grid Architecture Model (SGAM)-compliant software platform designed to integrate data-driven [...] Read more.
The integration of renewable energy sources (RESs) and the establishment of energy communities (ECs) are vital steps in achieving global sustainability goals. This paper presents a methodology for developing and validating a Smart Grid Architecture Model (SGAM)-compliant software platform designed to integrate data-driven energy services and connect physical energy assets within energy communities. The platform aims to optimize energy dispatch, enhance self-consumption, and facilitate interoperability with smart grid infrastructures. Two case studies—Polígono Industrial Las Cabezas in Spain and the IMP R&D campus in Serbia—are analyzed to highlight real-world challenges, solutions, and lessons learned. The article points to different scenarios relevant for energy community design and implementation. Lessons learned point to challenges related to device integration, production forecasting, user engagement, and regulatory barriers. The results show that the proposed SGAM platform successfully addresses technical and operational complexities, supporting energy efficiency, decarbonization, and scalability. Full article
Show Figures

Figure 1

14 pages, 3592 KiB  
Article
Large-Scale Rooftop Solar Photovoltaic Power Production Potential Assessment: A Case Study for Tehran Metropolitan Area, Iran
by Babak Ranjgar and Alessandro Niccolai
Energies 2023, 16(20), 7111; https://doi.org/10.3390/en16207111 - 16 Oct 2023
Cited by 12 | Viewed by 2546
Abstract
The exponential growth of population and industries has brought about an increase in energy consumption, causing severe climatic and environmental problems. Therefore, the move towards green renewable energy is being ever more intensified. This study aims at estimating the rooftop solar power production [...] Read more.
The exponential growth of population and industries has brought about an increase in energy consumption, causing severe climatic and environmental problems. Therefore, the move towards green renewable energy is being ever more intensified. This study aims at estimating the rooftop solar power production for Tehran, the capital city of Iran, using a Geospatial Information System (GIS) to assess the big data of city building parcels. Tehran is faced with severe air pollution due to its excessive fossil fuel usage, and its electricity demand is increasing. As a result, this paper attempts to provide the quantified solar power potential of city roof tops for policymakers and authorities in order to facilitate decision-making in relation to integrating renewable energies into the power production infrastructure. The results shows that approximately 3000 GWh (more than 14% of the total electric energy consumption) of solar power can be produced by the rooftop PV installations in Tehran. The potential nominal power of rooftop PV installations is estimated to be more than 2000 MW, which is four times the current installed PV capacity of the whole country. The findings of the study suggest that there is great potential hidden on the rooftops of the city, which can be utilized to assist the power systems of the city in the longer run for a more sustainable future. Full article
Show Figures

Figure 1

19 pages, 4459 KiB  
Article
Adaptive Energy Management of Big Data Analytics in Smart Grids
by Rohit Gupta and Krishna Teerth Chaturvedi
Energies 2023, 16(16), 6016; https://doi.org/10.3390/en16166016 - 17 Aug 2023
Cited by 10 | Viewed by 4022
Abstract
The smart grid (SG) ensures the flow of electricity and data between suppliers and consumers. The reliability and security of data also play an important role in the overall management. This can be achieved with the help of adaptive energy management (AEM). This [...] Read more.
The smart grid (SG) ensures the flow of electricity and data between suppliers and consumers. The reliability and security of data also play an important role in the overall management. This can be achieved with the help of adaptive energy management (AEM). This research aims to highlight the big data issues and challenges faced by AEM employed in SG networks. In this paper, we will discuss the most commonly used data processing methods and will give a detailed comparison between the outputs of some of these methods. We consider a dataset of 50,000 instances from consumer smart meters and 10,000 attributes from previous fault data and 12 attributes. The comparison will tell us about the reliability, stability, and accuracy of the system by comparing the output of the various graphical plots of these methods. The accuracy percentage of the linear regression method is 98%; for the logistic regression method, it is 96%; and for K-Nearest Neighbors, it is 92%. The results show that the linear regression method applied gives the highest accuracy compared to logistic regression and K-Nearest Neighbors methods for prediction analysis of big data in SGs. This will ensure their use in future research in this field. Full article
Show Figures

Figure 1

Review

Jump to: Research

19 pages, 953 KiB  
Review
A Review of Smart Grid Evolution and Reinforcement Learning: Applications, Challenges and Future Directions
by Na Xu, Zhuo Tang, Chenyi Si, Jinshan Bian and Chaoxu Mu
Energies 2025, 18(7), 1837; https://doi.org/10.3390/en18071837 - 5 Apr 2025
Viewed by 660
Abstract
In the face of the rapid development of smart grid technologies, it is increasingly difficult for traditional power system management methods to support the increasingly complex operation of modern power grids. This study systematically reviews new challenges and research trends in the field [...] Read more.
In the face of the rapid development of smart grid technologies, it is increasingly difficult for traditional power system management methods to support the increasingly complex operation of modern power grids. This study systematically reviews new challenges and research trends in the field of smart grid optimization, focusing on key issues such as power flow optimization, load scheduling, and reactive power compensation. By analyzing the application of reinforcement learning in the smart grid, the impact of distributed new energy’s high penetration on the stability of the system is thoroughly discussed, and the advantages and disadvantages of the existing control strategies are systematically reviewed. This study compares the applicability, advantages, and limitations of different reinforcement learning algorithms in practical scenarios, and reveals core challenges such as state space complexity, learning stability, and computational efficiency. On this basis, a multi-agent cooperation optimization direction based on the two-layer reinforcement learning framework is proposed to improve the dynamic coordination ability of the power grid. This study provides a theoretical reference for smart grid optimization through multi-dimensional analysis and research, advancing the application of deep reinforcement learning technology in this field. Full article
Show Figures

Figure 1

19 pages, 2202 KiB  
Review
Advanced Deep Learning Algorithms for Energy Optimization of Smart Cities
by Izabela Rojek, Dariusz Mikołajewski, Krzysztof Galas and Adrianna Piszcz
Energies 2025, 18(2), 407; https://doi.org/10.3390/en18020407 - 18 Jan 2025
Cited by 2 | Viewed by 2236
Abstract
Advanced deep learning algorithms play a key role in optimizing energy usage in smart cities, leveraging massive datasets to increase efficiency and sustainability. These algorithms analyze real-time data from sensors and IoT devices to predict energy demand, enabling dynamic load balancing and reducing [...] Read more.
Advanced deep learning algorithms play a key role in optimizing energy usage in smart cities, leveraging massive datasets to increase efficiency and sustainability. These algorithms analyze real-time data from sensors and IoT devices to predict energy demand, enabling dynamic load balancing and reducing waste. Reinforcement learning models optimize power distribution by learning from historical patterns and adapting to changes in energy usage in real time. Convolutional neural networks (CNNs) and recurrent neural networks (RNNs) facilitate detailed analysis of spatial and temporal data to better predict energy usage. Generative adversarial networks (GANs) are used to simulate energy usage scenarios, supporting strategic planning and anomaly detection. Federated learning ensures privacy-preserving data sharing in distributed energy systems, promoting collaboration without compromising security. These technologies are driving the transformation towards sustainable and energy-efficient urban environments, meeting the growing demands of modern smart cities. However, there is a view that if the pace of development is maintained with large amounts of data, the computational/energy costs may exceed the benefits. The article aims to conduct a comparative analysis and assess the development potential of this group of technologies, taking into account energy efficiency. Full article
Show Figures

Figure 1

36 pages, 3608 KiB  
Review
A Mini Review of the Impacts of Machine Learning on Mobility Electrifications
by Kimiya Noor ali, Mohammad Hemmati, Seyed Mahdi Miraftabzadeh, Younes Mohammadi and Navid Bayati
Energies 2024, 17(23), 6069; https://doi.org/10.3390/en17236069 - 2 Dec 2024
Cited by 1 | Viewed by 1945
Abstract
Electromobility contributes to decreasing environmental pollution and fossil fuel dependence, as well as increasing the integration of renewable energy resources. The increasing interest in using electric vehicles (EVs), enhanced by machine learning (ML) algorithms for intelligent automation, has reduced the reliance on. This [...] Read more.
Electromobility contributes to decreasing environmental pollution and fossil fuel dependence, as well as increasing the integration of renewable energy resources. The increasing interest in using electric vehicles (EVs), enhanced by machine learning (ML) algorithms for intelligent automation, has reduced the reliance on. This shift has created an interdependence between power, automatically, and transportation networks, adding complexity to their management and scheduling. Moreover, due to complex charging infrastructures, such as variations in power supply, efficiency, driver behaviors, charging demand, and electricity price, advanced techniques should be applied to predict a wide range of variables in EV performance. As the adoption of EVs continues to accelerate, the integration of ML and especially deep learning (DL) algorithms will play a pivotal role in shaping the future of sustainable transportation. This paper provides a mini review of the ML impacts on mobility electrification. The applications of ML are evaluated in various aspects of e-mobility, including battery management, range prediction, charging infrastructure optimization, autonomous driving, energy management, predictive maintenance, traffic management, vehicle-to-grid (V2G), and fleet management. The main advantages and challenges of models in the years 2013–2024 have been represented for all mentioned applications. Also, all new trends for future work and the strengths and weaknesses of ML models in various aspects of mobility transportation are covered. By discussing and reviewing research papers in this field, it is revealed that leveraging ML models can accelerate the transition to electric mobility, leading to cleaner, safer, and more sustainable transportation systems. This paper states that the dependence on big data for training, the high uncertainty of parameters affecting the performance of electric vehicles, and cybersecurity are the main challenges of ML in the e-mobility sector. Full article
Show Figures

Figure 1

Back to TopTop