Showing papers by "Chung-Ang University published in 2022"

Federated Reinforcement Learning for Energy Management of Multiple Smart Homes With Distributed Energy Resources

Abstract: This article proposesa novel federated reinforcement learning (FRL) approach for the energy management of multiple smart homes with home appliances, a solar photovoltaic system, and an energy storage system. The novelty of the proposed FRL approach lies in the development of a distributed deep reinforcement learning (DRL) model that consists of local home energy management systems (LHEMSs) and a global server (GS). Using energy consumption data, DRL agents for LHEMSs construct and upload their local models to the GS. Then, the GS aggregates the local models to update a global model for LHEMSs and broadcasts it to the DRL agents. Finally, the DRL agents replace the previous local models with the global model and iteratively reconstruct their local models. Simulation results obtained under heterogeneous home environments indicate the advantage of the proposed approach in terms of convergence speed, appliance energy consumption, and number of agents.

Cellulose nanofiber grafting and aluminum nitride deposition on the surface of expanded graphite to improve the thermal conductivity and mechanical properties of phase change material composites

Abstract: Phase change material (PCM) composites have attracted much attention as thermal energy storage devices for thermal management because of their high latent heat. However, the intrinsically low thermal conductivity of PCMs hinders the efficient thermal management of these devices. In this study, novel cellulose nanofibers (CNFs) grafting onto an expanded graphite (EG) and aluminum nitride (AlN) covering were carried out to prepare novel thermally conductive PCM composites, analyzed in detail using Fourier transform infrared spectroscopy (FT-IR), X-ray photoelectron spectroscopy (XPS), Raman spectra, X-ray diffraction (XRD) patterns, field-emission scanning electron microscopy (FE–SEM), differential scanning calorimetry (DSC), and thermogravimetric analysis (TGA). The composites exhibited ultra-high through-plane thermal conductivity of 3.39 W/mK and latent heat of 136 J/g, and the tensile strength increased by 402% compared with pure erythritol. The resulting erythritol/EG–CNF/AlN composites enable efficient thermal management because they save and dissipate heat due to the high latent heat and thermal conductivity. Moreover, the composite was insulated by nano-size AlN covered on the surface and pores of the EG structure. The proposed PCM composites are promising candidates for developing superior thermally conductive PCM composites and advanced electronic packaging.

Cellulose nanofiber grafting and aluminum nitride deposition on the surface of expanded graphite to improve the thermal conductivity and mechanical properties of phase change material composites

Abstract: Phase change material (PCM) composites have attracted much attention as thermal energy storage devices for thermal management because of their high latent heat. However, the intrinsically low thermal conductivity of PCMs hinders the efficient thermal management of these devices. In this study, novel cellulose nanofibers (CNFs) grafting onto an expanded graphite (EG) and aluminum nitride (AlN) covering were carried out to prepare novel thermally conductive PCM composites, analyzed in detail using Fourier transform infrared spectroscopy (FT-IR), X-ray photoelectron spectroscopy (XPS), Raman spectra, X-ray diffraction (XRD) patterns, field-emission scanning electron microscopy (FE–SEM), differential scanning calorimetry (DSC), and thermogravimetric analysis (TGA). The composites exhibited ultra-high through-plane thermal conductivity of 3.39 W/mK and latent heat of 136 J/g, and the tensile strength increased by 402% compared with pure erythritol. The resulting erythritol/EG–CNF/AlN composites enable efficient thermal management because they save and dissipate heat due to the high latent heat and thermal conductivity. Moreover, the composite was insulated by nano-size AlN covered on the surface and pores of the EG structure. The proposed PCM composites are promising candidates for developing superior thermally conductive PCM composites and advanced electronic packaging.

Deep Neural Network-based Optimization Framework for Safety Evacuation Route during Toxic Gas Leak Incidents

Abstract: Evacuation planning is important for reducing casualties in toxic gas leak incidents. However, most evacuation plans are too qualitative to be applied to unexpected practical situations. Here, we suggest an evacuation route proposal system based on a quantitative risk evaluation that provides the safest route for individual evacuees by predicting dynamic gas dispersion with a high accuracy and short calculation time. Detailed evacuation scenarios, including weather conditions, leak intensity, and evacuee information, were considered. The proposed system evaluates the quantitative risk in the affected area using a deep neural network surrogate model to determine optimal evacuation routes by integer programming. The surrogate model was trained using data from computational fluid dynamics simulations. A variational autoencoder was applied to extract the geometric features of the affected area. The predicted risk was combined with linearized integer programming to determine the optimal path in a predefined road network. A leak scenario of an ammonia gas pipeline in a petrochemical complex was used for the case study. The results show that the developed model offers the safest route within a few seconds with minimum risk. The developed model was applied to a sensitivity analysis to determine variable influences and safe shelter locations.

Random vector functional link neural network based ensemble deep learning for short-term load forecasting

Abstract: Electricity load forecasting is crucial for the power systems' planning and maintenance. However, its un-stationary and non-linear characteristics impose significant difficulties in anticipating future demand. This paper proposes a novel ensemble deep Random Vector Functional Link (edRVFL) network for electricity load forecasting. The weights of hidden layers are randomly initialized and kept fixed during the training process. The hidden layers are stacked to enforce deep representation learning. Then, the model generates the forecasts by ensembling the outputs of each layer. Moreover, we also propose to augment the random enhancement features by empirical wavelet transformation (EWT). The raw load data is decomposed by EWT in a walk-forward fashion, not introducing future data leakage problems in the decomposition process. Finally, all the sub-series generated by the EWT, including raw data, are fed into the edRVFL for forecasting purposes. The proposed model is evaluated on twenty publicly available time series from the Australian Energy Market Operator of the year 2020. The simulation results demonstrate the proposed model's superior performance over eleven forecasting methods in three error metrics and statistical tests on electricity load forecasting tasks.

Large-scale overseas transportation of hydrogen: Comparative techno-economic and environmental investigation

Abstract: Overseas hydrogen transport via ships is crucial to meet the global energy supply as we shift from the carbon-based fuel era. In this study, the hydrogen supply chain, which includes chemical and physical storage processes as well as sea and land transport and terminals, was economically and environmentally investigated. Five different storage technologies (i.e., liquid hydrogen, ammonia, toluene-methylcyclohexane [TOL-MCH], dibenzyltoluene-perhydro-dibenzyltoluene (H0DBT-H18DBT), and methanol) were applied to a defined intercontinental hydrogen supply chain that carries 300,000 t of hydrogen per year via ships. The five hydrogen storage technologies were evaluated and compared based on their economic and environmental performance. To achieve a higher energy efficiency, the models were upgraded by integrating liquid natural gas (LNG) to achieve hydrogen liquefaction and utilizing the waste heat of solid oxide fuel cells (SOFCs). Additionally, assuming that renewable energy capacity will be dominant in the future, renewable electricity and green hydrogen usage were investigated. The results showed that the TOL-MCH supply chain is the most cost-effective and environmentally friendly technology with 5.8 $/kgH2 levelized cost and 18.5 kgCO2-eq/kgH2 carbon intensity, followed by the ammonia supply chain, due to its suitable operating conditions. In the case of renewable electricity and green hydrogen dominance, the ammonia supply chain generates the lowest carbon emissions (i.e., 2.23 kgCO2-eq/kgH2) with a cost of 4.92 $/kgH2, and the TOL-MCH chain is the most cost-effective technology (i.e., 4.57 $/kgH2). Therefore, a decrease in process energy consumption and the use of renewable energy sources are essential for efficient and sustainable hydrogen seaborne transport.

Escalating Ferromagnetic Order via Se‐Vacancies Near Vanadium in WSe₂ Monolayers

Abstract: Magnetic order has been proposed to arise from a variety of defects, including vacancies, antisites, and grain boundaries, which are relevant in numerous electronics and spintronics applications. Nevertheless, its magnetism remains controversial due to the lack of structural analysis. The escalation of ferromagnetism in vanadium-doped WSe2 monolayer is herein demonstrated by tailoring complex configurations of Se vacancies (SeVac ) via post heat-treatment. Structural analysis of atomic defects is systematically performed using transmission electron microscopy (TEM), enabled by the monolayer nature. Temperature-dependent magnetoresistance hysteresis ensures enhanced magnetic order after high-temperature heat-treatment, consistent with magnetic domain analysis from magnetic force microscopy (MFM). The vanadium-Se vacancy pairing is a key to promoting ferromagnetism via spin-flip by electron transfer, predicted from density-functional-theory (DFT) calculations. The approach toward nanodefect engineering paves a way to overcome weak magnetic order in diluted magnetic semiconductors (DMSs) for renovating semiconductor spintronics.