Optimal Operation of a Microgrid with Hydrogen Storage Based on Deep Reinforcement Learning

Zhu, Zhenshan; Weng, Zhimin; Zheng, Hailin

doi:10.3390/electronics11020196

Cited by 12 publications

(5 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recent studies on the optimised control of SENs having multiple ESSs like a hybrid of a BESS and a HESS are proposed in [8,[30][31][32][33]. In [8,30], a DDPG-based algorithm is proposed to minimise building carbon emissions in an SEN that includes a BESS, an HESS, and constant building loads.…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Battery and Hydrogen Energy Storage Control in a Smart Energy Network with Flexible Energy Demand Using Deep Reinforcement Learning

Samende,

Fan,

Cao

et al. 2023

Energies

View full text Add to dashboard Cite

Smart energy networks provide an effective means to accommodate high penetrations of variable renewable energy sources like solar and wind, which are key for the deep decarbonisation of energy production. However, given the variability of the renewables as well as the energy demand, it is imperative to develop effective control and energy storage schemes to manage the variable energy generation and achieve desired system economics and environmental goals. In this paper, we introduce a hybrid energy storage system composed of battery and hydrogen energy storage to handle the uncertainties related to electricity prices, renewable energy production, and consumption. We aim to improve renewable energy utilisation and minimise energy costs and carbon emissions while ensuring energy reliability and stability within the network. To achieve this, we propose a multi-agent deep deterministic policy gradient approach, which is a deep reinforcement learning-based control strategy to optimise the scheduling of the hybrid energy storage system and energy demand in real time. The proposed approach is model-free and does not require explicit knowledge and rigorous mathematical models of the smart energy network environment. Simulation results based on real-world data show that (i) integration and optimised operation of the hybrid energy storage system and energy demand reduce carbon emissions by 78.69%, improve cost savings by 23.5%, and improve renewable energy utilisation by over 13.2% compared to other baseline models; and (ii) the proposed algorithm outperforms the state-of-the-art self-learning algorithms like the deep-Q network.

show abstract

Section: Related Workmentioning

confidence: 99%

“…In [8,30], a DDPG-based algorithm is proposed to minimise building carbon emissions in an SEN that includes a BESS, an HESS, and constant building loads. Similarly, operating costs are minimised in [31] using DDPG and in [32] using DQN. However, these studies use a single control agent to manage the multiple ESSs.…”

Section: Related Workmentioning

confidence: 99%

Battery and Hydrogen Energy Storage Control in a Smart Energy Network with Flexible Energy Demand Using Deep Reinforcement Learning

Samende,

Fan,

Cao

et al. 2023

Energies

View full text Add to dashboard Cite

show abstract

“…Finally, in ref. [23], the authors develop a deep deterministic policy gradient algorithm to reduce the operating costs of a microgrid with hydrogen storage by simulation, compared to traditional algorithms.…”

Section: Introductionmentioning

confidence: 99%

The Economic Impact and Carbon Footprint Dependence of Energy Management Strategies in Hydrogen-Based Microgrids

Rey,

Segura,

Andújar

et al. 2023

Electronics

View full text Add to dashboard Cite

This paper presents an economic impact analysis and carbon footprint study of a hydrogen-based microgrid. The economic impact is evaluated with respect to investment costs, operation and maintenance (O&M) costs, as well as savings, taking into account two different energy management strategies (EMSs): a hydrogen-based priority strategy and a battery-based priority strategy. The research was carried out in a real microgrid located at the University of Huelva, in southwestern Spain. The results (which can be extrapolated to microgrids with a similar architecture) show that, although both strategies have the same initial investment costs (EUR 52,339.78), at the end of the microgrid lifespan, the hydrogen-based strategy requires higher replacement costs (EUR 74,177.4 vs. 17,537.88) and operation and maintenance costs (EUR 35,254.03 vs. 34,877.08), however, it provides better annual savings (EUR 36,753.05 vs. 36,282.58) and a lower carbon footprint (98.15% vs. 95.73% CO2 savings) than the battery-based strategy. Furthermore, in a scenario where CO2 emission prices are increasing, the hydrogen-based strategy will bring even higher annual cost savings in the coming years.

show abstract

“…On the other hand, it can also be found that green hydrogen could be economically competitive with hydrogen produced from steam-methane reformation [14] or a quick and significant reduction in the costs of Li-ion batteries [15]. To make RESs and storage systems economically competitive for self-consumption, there are different proposals that can be classified between the following: (1) Those focused on the energy-management strategy (EMS), such as a mixed-integer linear-programming (MILP) model to minimise the operating cost of a microgrid [16], or the use of a deep deterministic policy-gradient algorithm in order to reduce microgrid operating costs [17]. (2) Those based on the use of low-cost materials and equipment for the microgrid, such as the use of a photoluminescent (PL) absorber of luminescent solar power (LSP) to reduce solar-PV energy costs [18], or the use, in redox flow batteries (RFBs), of low-cost polymeric redox-active materials and porous size-exclusion membranes of commodity polymers instead of more expensive options like inorganic redox-active materials and ion-exchange membranes, respectively [19].…”

Section: Introductionmentioning

confidence: 99%

Profitability of Hydrogen-Based Microgrids: A Novel Economic Analysis in Terms of Electricity Price and Equipment Costs

Rey,

Segura,

Andújar

2023

Electronics

View full text Add to dashboard Cite

The current need to reduce carbon emissions makes hydrogen use essential for self-consumption in microgrids. To make a profitability analysis of a microgrid, the influence of equipment costs and the electricity price must be known. This paper studies the cost-effective electricity price (EUR/kWh) for a microgrid located at ‘’La Rábida Campus’’ (University of Huelva, south of Spain), for two different energy-management systems (EMSs): hydrogen-priority strategy and battery-priority strategy. The profitability analysis is based, on one hand, on the hydrogen-systems’ cost reduction (%) and, on the other hand, considering renewable energy sources (RESs) and energy storage systems (ESSs), on cost reduction (%). Due to technological advances, microgrid-element costs are expected to decrease over time; therefore, future profitable electricity prices will be even lower. Results show a cost-effective electricity price ranging from 0.61 EUR/kWh to 0.16 EUR/kWh for hydrogen-priority EMSs and from 0.4 EUR/kWh to 0.17 EUR/kWh for battery-priority EMSs (0 and 100% hydrogen-system cost reduction, respectively). These figures still decrease sharply if RES and ESS cost reductions are considered. In the current scenario of uncertainty in electricity prices, the microgrid studied may become economically competitive in the near future.

show abstract

Optimal Operation of a Microgrid with Hydrogen Storage Based on Deep Reinforcement Learning

Cited by 12 publications

References 25 publications

Battery and Hydrogen Energy Storage Control in a Smart Energy Network with Flexible Energy Demand Using Deep Reinforcement Learning

Battery and Hydrogen Energy Storage Control in a Smart Energy Network with Flexible Energy Demand Using Deep Reinforcement Learning

The Economic Impact and Carbon Footprint Dependence of Energy Management Strategies in Hydrogen-Based Microgrids

Profitability of Hydrogen-Based Microgrids: A Novel Economic Analysis in Terms of Electricity Price and Equipment Costs

Contact Info

Product

Resources

About