AI agents envisioning the future: Forecast-based operation of renewable energy storage systems using hydrogen with Deep Reinforcement Learning

Dreher, Alexander; Bexten, Thomas; Sieker, Tobias; Lehna, Malte; Schütt, Jonathan; Scholz, Christoph; Wirsum, Manfred

doi:10.1016/j.enconman.2022.115401

Cited by 42 publications

(12 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Only residential EMSs consider user data, namely consumers' preferences and priorities for various applications [53], consumers' comfort levels [23,43,50], and consumers' location [50]. Meteorological data includes outdoor temperature [46,50], solar irradiance [33,69], wind speed [61], and general weather conditions [69]. Most publications in residential and industrial EMSs use financial data, namely electricity prices.…”

Section: Monitoringmentioning

confidence: 99%

“…In the literature analyzed, only industrial EMSs consider DP. Casini et al [59] model the control of an industrial microgrid, including EVs, and Dreher et al [61] use a DP-based unit commitment to finding an upper benchmark for an EMS in the context of CO 2 -neutral hydrogen production and storage for industrial combined heat and power application. As a software tool, MATLAB is used [59], and the time resolution is 1 h [61].…”

mentioning

confidence: 99%

“…In residential EMSs, Lissa et al [29] propose an RL algorithm for indoor and domestic hot water temperature control, and Ul Haq et al [39] present an RL algorithm for monitoring household electric appliances to lower energy consumption. In industrial EMSs, Dreher et al [61] present an RL-based EMS for CO 2 -neutral hydrogen production. All the RL models are simulated via MATLAB and are validated by different use cases with a time resolution of 30 min [29].…”

mentioning

confidence: 99%

See 2 more Smart Citations

A Systematic Literature Review on Data-Driven Residential and Industrial Energy Management Systems

Sievers

Blank

2023

Energies

View full text Add to dashboard Cite

The energy transition and the resulting expansion of renewable energy resources increasingly pose a challenge to the energy system due to their volatile and intermittent nature. In this context, energy management systems are central as they coordinate energy flows and optimize them toward economic, technical, ecological, and social objectives. While numerous scientific publications study the infrastructure, optimization, and implementation of residential energy management systems, only little research exists on industrial energy management systems. However, results are not easily transferable due to differences in complexity, dependency, and load curves. Therefore, we present a systematic literature review on state-of-the-art research for residential and industrial energy management systems to identify trends, challenges, and future research directions. More specifically, we analyze the energy system infrastructure, discuss data-driven monitoring and analysis, and review the decision-making process considering different objectives, scheduling algorithms, and implementations. Thus, based on our insights, we provide numerous recommendations for future research in residential and industrial energy management systems.

show abstract

Section: Monitoringmentioning

confidence: 99%

mentioning

confidence: 99%

mentioning

confidence: 99%

See 1 more Smart Citation

A Systematic Literature Review on Data-Driven Residential and Industrial Energy Management Systems

Sievers

Blank

2023

Energies

View full text Add to dashboard Cite

show abstract

“…In the available works of Anthopoulos and Kazantzi (2022), Dreher et al (2022), Fang et al (2022), Xuan and Ocone (2022), another key technology of Industry 4.0-artificial intelligence (AI) received a positive assessment from the standpoint of energy efficiency. In particular, it was noted that AI has a great potential for use in the energy sector, contributing to its optimization.…”

Section: Introductionmentioning

confidence: 99%

“…, Dreher et al (2022),Fang et al (2022),Xuan and Ocone (2022), it was proven that the use of AI hinders the development of clean and alternative energy. UnlikeCui et al (2022),Ng et al (2021),,Popkova and Sergi (2021),Tabor et al (2018), Taghizadeh-Hesary et al (2022),Zaidan et al (2022), t was justified, that the technologies of industry 4.0, which are becoming widespread in the conditions of the Fourth Industrial Revolution, not only do not support, but also slow down the transition to "clean" energy.UnlikeChen et al (2022),Deng et al (2022),Inshakova et al (2022),Iqbal and Bilal (2021),Liu et al (2022),Nyenno et al (2021), direct state regulation of sustainable energy development is recommended.…”

mentioning

confidence: 99%

Scenarios of the alternative energetics development in the age of the fourth industrial revolution: Clean energy prospects and policy implications

et al. 2022

View full text Add to dashboard Cite

Operation Performance Analysis of a Novel Renewable Energy‐Driven Multienergy Supply System Based on Wind, Photovoltaic, Concentrating Solar Power, Proton Exchange Membrane Electrolyzers, and Proton Exchange Membrane Fuel Cell

Liu

Zhai

et al. 2023

Energy Tech

View full text Add to dashboard Cite

In pursuing clean energy systems and carbon neutrality, the efficient use of renewable energy is key. This research introduces a novel wind–solar–hydrogen multienergy supply (WSH‐MES) system, powered by renewables, designed to stabilize power output through regulated concentrating solar power (CSP) and proton exchange membrane electrolyzers (PEMEs). An active regulation strategy for thermal and hydrogen storage is developed to counterbalance the volatility of wind and photovoltaic power. Key results reveal that the WSH‐MES system surpasses WP–PV and WP–PV–CSP systems in reliability, reducing power supply loss probability to 2.81%. This improvement is largely due to the controlled CSP and PEME, which effectively mitigates the stochastic fluctuations in wind and solar power generation, thereby ensuring more stable and reliable power output. Moreover, the system achieves an 80.97% primary renewable energy rate and a 0.12 power discard rate. In conclusion, this research comprehensively examines the operational characteristics of the WSH‐MES system, elucidates the practical advantages of the WSH‐MES system in terms of reliability, renewable energy utilization, and adaptability under various conditions. The results offer valuable insights into the design and operation of multienergy supply systems, potentially fostering the large‐scale implementation of renewable energy systems and leading toward a sustainable energy future.

show abstract

AI agents envisioning the future: Forecast-based operation of renewable energy storage systems using hydrogen with Deep Reinforcement Learning

Cited by 42 publications

References 38 publications

A Systematic Literature Review on Data-Driven Residential and Industrial Energy Management Systems

A Systematic Literature Review on Data-Driven Residential and Industrial Energy Management Systems

Scenarios of the alternative energetics development in the age of the fourth industrial revolution: Clean energy prospects and policy implications

Operation Performance Analysis of a Novel Renewable Energy‐Driven Multienergy Supply System Based on Wind, Photovoltaic, Concentrating Solar Power, Proton Exchange Membrane Electrolyzers, and Proton Exchange Membrane Fuel Cell

Contact Info

Product

Resources

About