Accelerating the low-carbon transition: Technological advancements and challenges for the sustainable development of energy, water, and environment systems

Energy Reports, Год журнала: 2024, Номер 11, С. 4676 - 4687

Опубликована: Апрель 26, 2024

This editorial explores the contributions of papers collected in virtual special issue Energy Reports dedicated to series Conferences on Sustainable Development Energy, Water and Environment Systems held Paphos (Cyprus), São Paulo (Brazil), Vlorë (Albania) 2022. Within this article collections, 13 accepted address key research topics aligned with focus SDEWES conferences, such as energy, water, environmental systems, thereby fulfilling aim scope Reports. Since 2002, Water, (SDEWES) serve a platform for fostering inter-sectoral collaborations among scientists worldwide individuals keen delving into sustainable development showcase advancements engage discussions regarding current trends, future trajectories development. In 2022, conference brought together approximately about 800 scientists, researchers, experts from more than 55 Countries. Based published 2022 – 5th SEE SDEWES, 3rd LA 17th is organized several sections covering VSI primary that encompass innovative renewable energy technologies, design solutions buildings communities, simulation tools green fuels, based technologies. Detailed latest technological challenges accelerate transitions are here presented.

Язык: Английский

---

The difference between energy management systems and environmental management systems on the implementation of cross-sectional technologies in enterprises

Energy Reports, Год журнала: 2025, Номер 13, С. 1691 - 1704

Опубликована: Янв. 22, 2025

Язык: Английский

---

Fostering renewable energy use through smart city construction: The role of National Innovation Systems

Energy Strategy Reviews, Год журнала: 2025, Номер 58, С. 101690 - 101690

Опубликована: Март 1, 2025

Язык: Английский

---

Artificial Intelligence Integrated Energy Education Framework. A Holistic Approach

Опубликована: Май 10, 2024

This scientific article outlines the Artificial Intelligence Integrated Energy Education Framework (AI-IEEF), a transformative model designed to revolutionize energy education and management practices. The framework is organized into five distinct layers: Organizational (AI-enhanced administration systems), Financial (dynamic AI financial models), Technology (advanced simulation modeling), Methodology (AI in curriculum development personalized learning), Social for community engagement impact). An expert panel used fuzzy Delphi method achieve consensus on twenty key factors within these layers, establishing solid foundation analysis. Following this, Fuzzy Analytic Hierarchy Process (AHP) was employed calculate precise weights each layer their respective factors, providing quantitative assessment of relative importance. These weight calculations are crucial, as they guide resource allocation strategic decision-making ensure optimized evolving needs management. Furthermore, introduces tailored variants AI-IEEF, addressing specific aspects offering comprehensive approach navigating challenges field. include Smart Campus Education, Global Policy Analysis, Renewable Research Development, Workforce Community Engagement Outreach variants. Each provides education, from transforming campuses living labs hands-on learning fostering international collaborations that explore global implications policy. emphasize practical skills, policy analysis, community-focused solutions, ensuring students well-prepared contribute effectively sector.

Язык: Английский

---

Advancing Electric Load Forecasting: Leveraging Federated Learning for Distributed, Non-Stationary, and Discontinuous Time Series

Smart Cities, Год журнала: 2024, Номер 7(4), С. 2065 - 2093

Опубликована: Июль 28, 2024

In line with several European directives, residents are strongly encouraged to invest in renewable power plants and flexible consumption systems, enabling them share energy within their Renewable Energy Community at lower procurement costs. This, along the ability for switch between such communities on a daily basis, leads dynamic portfolios, resulting non-stationary discontinuous electrical load time series. Given poor predictability as well insufficient examination of characteristics, critical importance forecasting management we propose novel framework using Federated Learning leverage information from multiple distributed communities, learning domain-invariant features. To achieve this, initially utilize synthetic series district level aggregate profiles Communities portfolios. Subsequently, develop model that accounts composition Community, adapt data pre-processing accordance process, detail federated algorithm incorporates weight averaging sharing. Following training various experimental setups, evaluate effectiveness by applying different tests white noise forecast error signal. The findings suggest our proposed is capable effectively series, extract features, applicable new, unseen through integration knowledge sources.

Язык: Английский

---

Energy classification of urban districts to map buildings and prioritize energy retrofit interventions: A novel fast tool

Applied Energy, Год журнала: 2024, Номер 377, С. 124664 - 124664

Опубликована: Окт. 30, 2024

Язык: Английский

---

Advancing Electric Load Forecasting: Leveraging Federated Learning for Distributed, Non-Stationary, and Discontinuous Time Series

Опубликована: Май 17, 2024

This paper addresses the evolving landscape of electricity markets in Europe, with a focus on integration Renewable Energy Communities as introduced by Directive 2018/2001. Residents within postal code area are highly incentivized to join community, which enables them exchange energy among themselves at lower procurement costs. Thereby, management systems optimize operation respective systems, electrical load forecasting playing key role. Given that prosumers may switch between communities daily basis, demands these groups will vary, leading data is non-stationary, discontinuous well non-identical and independently distributed. To encounter this issue, we propose sophisticated model applies federated learning, using informations from various distributed learn domain-invariant features. achieve this, initially utilize synthetic time series district level aggregate profiles dynamic portfolios. Subsequently, develop accounts for composition residents Community, adapt pre-processing accordance process, detail learning algorithm incorporates weight averaging sharing. Following training experimental setups, ultimately evaluate their effectiveness. The findings suggest our proposed framework capable effectively forecast non-stationary it can be applied new, unseen through knowledge multiple sources.

Язык: Английский

---

A Digital Platform for Real-Time Multi-Energy Management in Districts Using Opc Ua: Conceptualization, Modeling, Software Implementation, and Laboratory Validation

Опубликована: Янв. 1, 2024

Язык: Английский

---