Because of their combined effects outstanding mechanical stability, high electrical conductivity, and theoretical capacity, silicon (Si) nanoparticles embedded in carbon are a promising candidate as electrode material for practical utilization Li-ion batteries (LIBs) to replace the conventional graphite. However, because poor ionic diffusion materials, low-grade ultrafast cycling performance at current densities remains considerable challenge. In present study, seeking improve diffusion, we...

We propose a two-stage probabilistic solar power (SP) forecasting algorithm to utilize the irradiation (SI) observations measured from different locations. In first stage, we predict SI based on numerical weather prediction (NWP) after interpolating observations. Since target location is not measured, interpolate it using spatio-temporal Kriging technique observed nearby stations. second forecast SP predictions training and The model trained by observations, but forecasts predictions....

This paper presents a novel contextually supervised optimization-based approach for disaggregating heating, ventilation, and air-conditioning (HVAC) loads using smart meter or Supervisory Control Data Acquisition data. To disaggregate the load into HVAC loads, large infrequently used (LIUL), base we formulate an optimization problem to minimize set of five loss terms, consisting reconstruction errors overall profile, ramp rate losses, three distinct functions linked with load, LIUL,...

This paper introduces an accurate and efficient urban area 5 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">th</sup> Generation millimeter wave path loss model using 3D Convolutional Neural Network (CNN). In this paper, we describe how to create a image that is mainly used as input for 3D-CNN, what are the structures hyperparameters used. The proposed prediction achieved final Root Mean Square Error (RMSE) of 5.84 dBm.

Accurate and efficient path loss prediction in mmWave communication plays an important role large-scale deployment of the mmWave-based 5G mobile systems. Existing methods often present limitations accuracy efficiency fail to fulfill requirements cell planning, especially dense urban environments. In this paper, we propose a novel training method called multi-way local attentive learning, which allows for learning from multiple perspectives on same set samples with attention paid each subset...

Restoring missing data holds paramount importance in power system analysis. Traditional recovery methods typically offer only a singular solution, lacking adaptability and depth. To bridge this gap, we introduce BERT-PIN, pioneering approach harnessing bidirectional encoder representations from transformers for profile inpainting. This innovative technique enables the of multiple segments by leveraging load temperature profiles. Our findings demonstrate that BERT-PIN enhances accuracy 5%–30%...

This paper presents a modified sequence-to-point (S2P) algorithm for disaggregating the heat, ventilation, and air conditioning (HVAC) load from total building electricity consumption. The original S2P model is convolutional neural network (CNN) based, which uses profiles as inputs. We propose three modifications. First, input convolution layer changed 1D to 2D so that normalized temperature are also used inputs model. Second, drop-out added improve adaptability generalizability trained in...

Inspired by the success of Transformer model in natural language processing and computer vision, this paper introduces BERT-PIN, a Bidirectional Encoder Representations from Transformers (BERT) powered Profile Inpainting Network. BERT−PIN recovers multiple missing data segments (MDSs) using load temperature time-series profiles as inputs. To adopt standard structure for profile inpainting, we segment into line segments, treating each word entire sentence. We incorporate top candidates...

Surface-templated evaporation driven (STED) method is a promising to fabricate supraparticles with various sizes, porosities, and shapes by drying colloidal dispersion drops on liquid repellent surfaces. Until now, for the method, only spherical shaped particles have been used as primary colloids. Here, we introduce six different of nano-colloidal dispersions STED method: nanocubics, nanoplates, nanosheets, coffin-shaped nanoparticles (NPs), NPs, aggregates NPs. It confirmed that shape size...

The purpose of this paper is to apply multistage stochastic programming the transmission line expansion planning problem, especially when uncertain demand scenarios exist. Since problem requires an intensive computational load, dual decomposition used decompose into smaller problems. Following this, progressive hedging and proximal bundle methods are restore decomposed solutions original Mixed-integer linear involved in decide where new lines should be constructed or reinforced. However,...

Recently there is a need for QA system to answer not only factoid questions but also descriptive questions. Descriptive are which answers that contain definitional information about the search term or describe some special events. We have proposed new model and presented result of we built defined 10 Answer Type(DAT)s as types discussed how our was applied question with experiments.

The effects of severe plastic deformation on the microstructural evolution, tensile and high cycle fatigue properties warm caliber-rolled hypereutectoid steels were investigated. As reduction in area, associated with amount 0, 38, 57 81%, increased steels, strain accumulation was observed near interfaces between cementite ferrite pearlite structures. Initial structures changed to spheroidized submicron-sized polygonal by dynamic recrystallization according caliber rolling process. initial...

We propose a model predictive control-based optimal offer and operation strategy for photovoltaic (PV) farm consisting of PV panels dual energy storage systems (ESS)s to maximize profits in the regulation markets. Although owner can better respond signals with an ESS, it cannot continuously unidirectional since ESS is limited size. Furthermore, lifespan might be reduced by alternating between charging discharging because that fluctuate often. To improve response, we use ESSs separate...

This paper introduces ViT4LPA, an innovative Vision Transformer (ViT) based approach for Load Profile Analysis (LPA). We transform time-series load profiles into images. allows us to leverage the ViT architecture, originally designed image processing, as a pre-trained encoder uncover latent patterns within data. is using extensive dataset, comprising 1M images derived from smart meter data collected over two-year period 2,000 residential users. The training methodology self-supervised,...

Recently, the semiconductor industry has made much progress since development of first transistor in 1947. As miniaturization technology scaling continues, it is challenging to meet target low loss power delivery network (PDN) specification. Thus, order solve these issues, a new called back-side PDN (BSPDN) been recently introduced and developed apply for advanced node mitigate increasing static IR-drop (SIR) Dynamic Voltage Drop (DvD) risk from conventional PDN, name as Front-side (FSPDN)....