Machine learning-based utilization of renewable power curtailments under uncertainty by planning of hydrogen systems and battery storages

Shams, Mohammad H.; Niaz, Haider; Na, Jonggeol; Anvari‐Moghaddam, Amjad; Liu, J. Jay

doi:10.1016/j.est.2021.103010

Cited by 39 publications

(9 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In terms of the forecast of the output power of RES, it was performed in the literature [12][13][14][15]. Rodríguez et al [12] established an ANN model to forecast the short-term wind power density in the next 10 minutes to realize the optimization of microgrid control.…”

Section: Output Power Prediction Of Renewable Energy Systemsmentioning

confidence: 99%

“…Mellit et al [14] developed a deep learning neural network (DLNN) to achieve accurate short-term prediction of photovoltaic power output power, HEET-2021 Journal of Physics: Conference Series 2208 (2022) 012013 which was of great significance for the control and design of micro-grid intelligent energy management systems. Shams et al [15] used deep learning (DL) algorithm to forecast wind and solar power curtailment. Based on it, an original planning model was developed to minimize the waste of wind and solar power by utilizing the battery and hydrogen storage systems.…”

Section: Output Power Prediction Of Renewable Energy Systemsmentioning

confidence: 99%

See 1 more Smart Citation

Artificial intelligence for hydrogen-based hybrid renewable energy systems: A review with case study

Yan

Agbossou

et al. 2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

In recent years, with the progress of computer technology, artificial intelligence has been rapidly developed and begun to be applied in industry, economy and other aspects. Besides, with the pursuit of green hydrogen, hydrogen-based hybrid renewable energy systems have become the focus of the development of the hydrogen industry. This paper compares different artificial intelligence applications in hydrogen-based hybrid renewable energy systems and carries out a case study in a typical area. Firstly, this paper summarizes important works in literature, which use artificial intelligence methods to predict the supply chain of the renewable energy system, including the prediction of renewable energy system resources, output power, load demand and terminal electricity price. Secondly, main articles about artificial intelligence optimization algorithms used in renewable energy systems are also summarized, including swarm and non-swarm biological heuristics, physical or chemical heuristics and hybrid optimization algorithms. Finally, a case study is carried out in Tikanlik, Xinjiang, China. Tikanlik’s weather and load data train the artificial neural network to predict system output power. It shows that 99.32% of the relative error of the test set is less than 3%, which proves that this model can achieve good prediction results.

show abstract

Section: Output Power Prediction Of Renewable Energy Systemsmentioning

confidence: 99%

Section: Output Power Prediction Of Renewable Energy Systemsmentioning

confidence: 99%

Artificial intelligence for hydrogen-based hybrid renewable energy systems: A review with case study

Yan

Agbossou

et al. 2022

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…In the current era of the escalating climate change and global energy demand, strict environmental regulations and the urgent need for renewable energy systems are imperative to sustainably mitigate the detrimental effects of fossil fuels on the environment. , A report by the US Department of Energy estimates that by 2050, wind and solar energy will entirely replace fossil fuels in supporting technologies, such as electric vehicles and green hydrogen production . Despite such a promising potential, the electricity production from PV systems and windmills and its efficiency are major bottlenecks that significantly depend on the availability of solar irradiance profiles and wind speed, which considerably vary based on the geographical location. − Considering this, electricity conversion plants for solar PV and windmills must be installed in the regions where the solar irradiance profiles and wind speed are optimal. The intermittency of solar and wind power is a big challenge as it results in the overproduction of electricity at times or in less production than needed at other times.…”

Section: Introductionmentioning

confidence: 99%

Life Cycle Assessment of Inland Green Hydrogen Supply Chain Networks with Current Challenges and Future Prospects

Akhtar

Dickson

Liu

2021

ACS Sustainable Chem. Eng.

Self Cite

View full text Add to dashboard Cite

Large-scale energy storage and mobility infrastructures are imperative for meeting the current global energy demand. With hydrogen increasingly emerging as a potential energy carrier, the development of global hydrogen mobility infrastructures is essential to accelerate the transition to a hydrogen economy. In this work, a comprehensive cradle-to-gate life cycle assessment (LCA) was performed for seven hydrogen delivery pathways: compressed gas via pipeline (CGH2-PL), compressed gas via tube trailer (CGH2-TT), liquid hydrogen (LH2), liquid organic hydrogen carrier with natural gas as a heating source (LOHC), liquid ammonia (LNH3), liquid organic hydrogen carrier with hydrogen as a heating source (LOHC-Own), and the direct utilization of NH3 in direct ammonia fuel cell vehicle (LNH3-DAFCV). The LCA results showed that CGH2-PL is the most sustainable option among all the above mentioned pathways as it showed to have the lowest global warming potential (GWP) (1.57 kgCO2-eq/kgH2). On the contrary, delivery via LOHC had the worst results and would have the highest emissions (3.58 kgCO2-eq/kgH2). However, by partially utilizing the produced hydrogen to fulfill the heating requirements during dehydrogenation (LOHC-Own), approximately 35% of the GWP was reduced to 2.34 kgCO2-eq/kgH2. Likely, delivery via LNH3 also showed significant emissions (3.14 kgCO2-eq/kgH2) and remained the second worst candidate for hydrogen delivery. However, the direct utilization of NH3 in DAFCV showed promising results for GWP (1.62 kgCO2-eq/kgH2), making NH3 a likely candidate for future hydrogen and energy carriers.

show abstract

“…There are generally three levels: the strategic level includes the determination of production technologies and network configurations, and the tactical and operational levels include production-planning processes in the medium term (e.g., monthly) and short term (e.g., weekly or daily), respectively. 13 Furthermore, the supply chain can be divided into three parts: upstream, comprising biomass production through delivery to a production facility; midstream, encompassing all conversion processes; and downstream, comprising the storage and distribution of the produced biofuels to end-users. 14 Many studies have been performed on designing the first and second generation of the biofuel supply chain involving chemicals containing sugars and starches or lignocellulosic biomass.…”

Section: Introductionmentioning

confidence: 99%

Optimal Design of the Biofuel Supply Chain Utilizing Multiple Feedstocks: A Korean Case Study

Zarei

Niaz

Dickson

et al. 2021

ACS Sustainable Chem. Eng.

Self Cite

View full text Add to dashboard Cite

As the global climate crisis worsens and fossil fuels deplete, renewable energy sources have become more appealing. Biofuel is one of the promising sources produced from multiple biomass sources, as long as it does not compromise food security. In this direction, a multiperiod mixed-integer linear programming model incorporating three types of biomass simultaneously is developed to provide a second- and third-generation biofuel supply chain. The proposed model minimizes the total annualized cost by selecting raw materials, locating production facilities, placing storage facilities, and identifying optimal material flows by defining a deference path for each feedstock. A case study addressing bioethanol production in South Korea was then conducted to evaluate the performance of the developed model; the results demonstrated a clear reduction in the total annualized cost by incorporating multiple feedstocks. Using multiple feedstocks allowed for the total ethanol demand of South Korea to be met using harvested biomass, thereby drastically reducing import costs. Refinery costs accounted for the large majority of the remaining costs. A sensitivity analysis was also conducted to assess the effect of uncertainty associated with some economic and production parameters.

show abstract

Machine learning-based utilization of renewable power curtailments under uncertainty by planning of hydrogen systems and battery storages

Cited by 39 publications

References 39 publications

Artificial intelligence for hydrogen-based hybrid renewable energy systems: A review with case study

Artificial intelligence for hydrogen-based hybrid renewable energy systems: A review with case study

Life Cycle Assessment of Inland Green Hydrogen Supply Chain Networks with Current Challenges and Future Prospects

Optimal Design of the Biofuel Supply Chain Utilizing Multiple Feedstocks: A Korean Case Study

Contact Info

Product

Resources

About