energies-logo

Journal Browser

Journal Browser

Tiny Machine Learning for Energy Applications

A special issue of Energies (ISSN 1996-1073). This special issue belongs to the section "F5: Artificial Intelligence and Smart Energy".

Deadline for manuscript submissions: 31 March 2025 | Viewed by 1360

Special Issue Editors


E-Mail Website1 Website2
Guest Editor
Electrical, Electronics and Telecommunication Engineering and Naval Architecture Department (DITEN), University of Genoa, Via Opera Pia 11/A, 16145 Genova, GE, Italy
Interests: applications of electronic systems; technology-enhanced learning; internet of things; games; electric vehicles charging
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Department of Electrical, Electronic, Telecommunication Engineering and Naval Architecture, University of Genoa, 16126 Genova, GE, Italy
Interests: edge computing; embedded devices; Internet of Things; automated driving; electrical engineering

E-Mail Website
Guest Editor
Department of Industrial Engineering, University of Trento, I-38123 Trento, Italy
Interests: signal processing; embedded electronic systems; Internet of Thing
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

As the demand for energy-efficient solutions continues to rise across various sectors, the integration of efficient Machine Learning algorithms into small and low-power devices has emerged as promising technology to optimize energy usage and enhancing the efficiency of distributed systems. This approach is commonly referred to as Tiny Machine Learning (TinyML). TinyML enables intelligent decision-making and data filtering at the edge of the network, optimizing energy usage, avoiding unnecessary data transmission enabling higher operational efficiency.

This Special Issue seeks original contributions to explore the latest advancements, challenges, and opportunities in deploying TinyML solutions with an emphasis on energy aspects to address the pressing need for sustainable and efficient energy management. Contributions should demonstrate progress, address challenges, and showcase practical applications of TinyML in improving the efficiency, reliability, and sustainability of such systems.

We welcome original high-quality research papers, review articles, case studies, and perspectives that contribute to advancing the field of TinyML for energy efficient applications.

Contributions may cover a wide range of topics, including but not limited to:

  • TinyML Applications: Novel applications across energy efficiency and emerging use cases; Practical implementations of TinyML in energy conservation, efficiency, and sustainability; Application in smart grid technologies for e1ective demand response, load forecasting, and energy distribution optimization; Discussions about real-world use cases; Survey on practical experiences.
  • TinyML Algorithms: Innovative Algorithms and models for energy forecasting, monitoring, and management; Real-time data analytics for energy; ML algorithms optimization and fine-tuning for resources constrained devices; Innovative TinyML architectures; Optimization strategies for energy constrained TinyML deployments.
  • TinyML Architectures: Energy-aware edge computing architectures leveraging TinyML capabilities to enhance operational efficiency. Exploration, evaluation and characterization of hybrid computing approaches (i.e., fog/mist computing); Interdisciplinary approaches combining TinyML with other technologies (e.g., IoT, blockchain, augmented/virtual reality).
  • TinyML Systems: Energy-efficient architectures and hardware for energy applications; performance characterization and power figures of distributed infrastructures; Hardware and Software co-design-based solutions; characterization of tiny real-world embedded systems; in-sensor processing, design, and implementation
  • Battery-Less Design: Integration of TinyML with renewable energy sources for improved efficiency and sustainability; Energy harvesting and power management solutions for TinyML-enabled devices; Transiently powered devices; Batteryless system design; Integration of renewable energy sources using TinyML for optimization and forecasting; Novel hardware architectures and platforms designed to support energy-efficient TinyML inference.
  • TinyML security and privacy: Security and privacy considerations in TinyML deployments; Privacy-preserving Techniques in Edge AI Systems; Secure model deployment; Model encryption, tamper-proofing, and secure boot mechanisms; Robustness techniques such as adversarial training, model distillation, and input sanitization; Transparent governance frameworks for data collection, model training, and inference in TinyML systems.

Dr. Riccardo Berta
Dr. Luca Lazzaroni
Dr. Matteo Nardello
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

  • tiny machine learning (TinyML)
  • energy management
  • sustainable energy
  • edge computing
  • edge intelligence
  • edge applications
  • energy forecasting
  • energy-harvesting technologies
  • batteryless technologies
  • smart grid technologies

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 polices can be found here.

Related Special Issue

Published Papers (2 papers)

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

Research

17 pages, 932 KiB  
Article
Exploring the Preference for Discrete over Continuous Reinforcement Learning in Energy Storage Arbitrage
by Jaeik Jeong, Tai-Yeon Ku and Wan-Ki Park
Energies 2024, 17(23), 5876; https://doi.org/10.3390/en17235876 - 22 Nov 2024
Viewed by 502
Abstract
In recent research addressing energy arbitrage with energy storage systems (ESSs), discrete reinforcement learning (RL) has often been employed, while the underlying reasons for this preference have not been explicitly clarified. This paper aims to elucidate why discrete RL tends to be [...] Read more.
In recent research addressing energy arbitrage with energy storage systems (ESSs), discrete reinforcement learning (RL) has often been employed, while the underlying reasons for this preference have not been explicitly clarified. This paper aims to elucidate why discrete RL tends to be more suitable than continuous RL for energy arbitrage problems. When using continuous RL, the charging and discharging actions determined by the agent often exceed the physical limits of the ESS, necessitating clipping to the boundary values. This introduces a critical issue where the learned actions become stuck at the state of charge (SoC) boundaries, hindering effective learning. Although recent advancements in constrained RL offer potential solutions, their application often results in overly conservative policies, preventing the full utilization of ESS capabilities. In contrast, discrete RL, while lacking in granular control, successfully avoids these two key challenges, as demonstrated by simulation results showing superior performance. Additionally, it was found that, due to its characteristics, discrete RL more easily drives the ESS towards fully charged or fully discharged states, thereby increasing the utilization of the storage system. Our findings provide a solid justification for the prevalent use of discrete RL in recent studies involving energy arbitrage with ESSs, offering new insights into the strategic selection of RL methods in this domain. Looking ahead, improving performance will require further advancements in continuous RL methods. This study provides valuable direction for future research in continuous RL, highlighting the challenges and potential strategies to overcome them to fully exploit ESS capabilities. Full article
(This article belongs to the Special Issue Tiny Machine Learning for Energy Applications)
Show Figures

Figure 1

16 pages, 3855 KiB  
Article
A Regression-Based Method for Monthly Electric Load Forecasting in South Korea
by Geun-Cheol Lee
Energies 2024, 17(23), 5860; https://doi.org/10.3390/en17235860 - 22 Nov 2024
Viewed by 369
Abstract
In this study, we propose a regression-based method for forecasting monthly electricity consumption in South Korea. The regression model incorporates key external variables such as weather conditions, calendar data, and industrial activity to capture the major factors influencing electricity demand. These predictor variables [...] Read more.
In this study, we propose a regression-based method for forecasting monthly electricity consumption in South Korea. The regression model incorporates key external variables such as weather conditions, calendar data, and industrial activity to capture the major factors influencing electricity demand. These predictor variables were identified through comprehensive data analysis. Comparative experiments were conducted with various existing methods, including univariate time series models and machine learning techniques like Holt–Winters, LightGBM, and Long Short-Term Memory (LSTM). Additionally, ensemble methods combining two or more of these existing methods were tested. In the empirical analysis, the proposed model was used to forecast monthly electricity demand for a 24-month period (2022–2023), achieving a mean absolute percentage error (MAPE) of approximately 2%. The results demonstrated that the proposed method consistently outperforms all benchmarks tested in this study. Full article
(This article belongs to the Special Issue Tiny Machine Learning for Energy Applications)
Show Figures

Figure 1

Back to TopTop