Accurate Energy Prediction Research Articles

Performance comparison on improved data-driven building energy prediction under data shortage scenarios in four perspectives: Data generation, incremental learning, transfer learning, and physics-informed

Accurate building energy predictions (BEPs) are crucial for maintaining a built environment's sustainability and energy systems. Many data-driven BEPs rely heavily on sufficient data. However, circumstances of practical data shortage restrict the application of these data-driven models to information-poor buildings. This study aims to address this research gap by enhancing BEP performance via the consideration of four perspectives: data generation (DG), incremental learning (IL), transfer learning (TL) and physics-informed (PI). Long short-term memory (LSTM) is selected as the baseline model for comparing performance under extreme (target building dataset: 1-week), heavy (4-weeks) and mild (13-weeks) data shortage scenarios with respect to prediction errors, time costs and the Taylor diagram, among others. The implementation algorithms of four LSTM improved models are conditional variational autoencoder (CVAE), crude incremental learning, domain-adversarial neural network and statistics-informed (SI) for DG, IL, TL and PI, respectively. The effectiveness of the four enhanced models was confirmed using the open-source dataset Building Data Genome Project 2. A comprehensive and fair performance comparison recommends CVAE for extreme and heavy data shortage scenarios with average mean absolute per cent error (MAPE) of 12.79 % and 8.63 % as well as performance improvement ratios (PIRs) of 0.45 and 0.57. SI should be recommended for mild data shortage scenarios with MAPE of 8.01 % and PIR of 0.66.

Smooth Dispersion Is Physically Appropriate: Assessing and Amending the D4 Dispersion Model.

The addition of dispersion corrections to density functionals is essential for accurate energy and geometry predictions. Among them, the D4 scheme is popular due to its low computational cost and high accuracy. However, due to its design, the D4 correction can occasionally lead to anomalies, such as unphysical curvature and bumps in the potential energy surface. We find these anomalies are common in the D4 model, although observable consequences are rarer than in the D3 model for reasons we explain. Nevertheless, we uncover instances of unphysical local minima and stationary points with the D4 scheme and propose two solutions that yield smoother dispersion energy as a function of nuclear position. One is trivial to implement, based on a smoother reparametrization of Gaussian weighting (D4S) to find the effective coordination number. The other replaces Gaussian weighting with soft linear interpolation (D4SL). These new approaches usually remove artificial extremum points, while maintaining accuracy.

Prediction of dynamic behaviors of vibrational-powered electromagnetic generators: Synergies between analytical and artificial intelligence modelling

The electric efficiency of vibrational electromagnetic generators is highly dependent on their ability to ensure effective adaptability to uncertain and irregular dynamics of mechanical energy sources. Such adaptive ability demands a planning operation considering future information of the highly nonlinear dynamics of these generators and mechanical excitations patterns. High accurate energy predictions are then mandatory for high energy generation efficiencies. However, on the one hand, high prediction accuracy by analytical modelling from first principles requires high modelling complexity; on the other hand, artificial intelligence models ensuring high prediction accuracy have not yet been explored to enhance the performance of these generators, even though their pre-training holds potential to significantly reduce the energy production costs. We here provide a multifaceted study highlighting the synergies between analytical and artificial intelligence modelling for optimizing the efficiency of vibrational-powered electromagnetic generators. Two main innovations are introduced: (1) development and experimental validation of a time-series forecasting artificial intelligence model based on the deep deterministic policy gradient method; (2) validation of a pre-training scenario by analytical modelling ⟶ artificial intelligence modelling synergy. Both the analytical and artificial intelligence models were able to provide high prediction accuracies to periodic and random 3D motions combining translations and rotations. Moreover, the pre-training scenario, using simulation training data sets, ensures prediction accuracies within the ±20% absolute error surfaces, profiling approximately normal distributions centered at approximately null error. These are impacting results in the scope of vibrational electromagnetic generation, holding potential to be extended to innovative self-adaptive electromagnetic generators, including those with ability to absorb complex 6 DOF external mechanical excitations. Besides, it can support the implementation of high-performance AI modelling⟶analytical modelling synergies, aiming to re-parameterize the high complex analytical models throughout the EMG operation, such that a superior controllability of the adaptive systems can be achieved.

Enhancing solar power forecasting with machine learning using principal component analysis and diverse statistical indicators

_Predicting solar energy is essential for efficient power system planning and the successful integration of renewable energy sources. This study aims to develop a framework for evaluating various machine learning models and feature selection strategies for solar energy prediction. The research applies six machine learning models, i.e., linear regression (LR), random forest (RF), neural networks (NN), K-nearest neighbor (KNN), gradient boosting (GB), and AdaBoost, to datasets from 2019 to 2021 collected at the Abiod Sid Cheikh solar station in southern Algeria. Various statistical indicators, including R2, RMSE, MAE, and Adj-R, were analyzed to assess model performance. The analysis revealed that R2 values ranged from 0.591 to 0.996 kW/m2, RMSE from 0.510 to 1.78 kW/m2, and MAE from 0.357 to 0.856 kW/m2 across different models. KNN and NN models showed significant errors, while GB and RF models demonstrated strong accuracies (RMS = 0.9). AdaBoost and LR excelled in real-time and short-term predictions, exhibiting an RMS of 0.99. This framework offers a comprehensive evaluation method for selecting the most suitable machine learning models and feature selection strategies for solar energy prediction. The findings can assist energy planners and engineers in choosing the appropriate models for accurate solar energy prediction, thereby enhancing the efficiency of power systems. Improved solar energy prediction can contribute to more reliable integration of renewable energy into power grids, supporting the transition to cleaner energy sources and reducing environmental impacts.

Temporal feature decomposition fusion network for building energy multi-step prediction

Accurate building energy prediction methods have become a key factor in achieving energy-saving goals. Traditional methods for building energy multi-step prediction often use recursive or direct strategies to address time series prediction problems, which may neglect the data sequence correlation and result in the cumulative error. To solve the above problem, this paper proposed a Temporal Feature Decomposition Fusion Network (TFDFNet) model for building energy consumption multi-step prediction, with an encoder-decoder architecture. In the encoder, feature fusion layers is employed to consider the influence of different feature sequences on the predicted sequence. Through the decomposition of historical load data sequences, different hierarchical sequence structures are constructed to enhance the interpretability and predictability of the data. In the decoder, a simple and efficient network is constructed using MLP to decode the encoded information and obtain the prediction results. Experimental results show that, the proposed model achieves higher prediction accuracy and more stable convergence than the other five comparable methods, which also indicates the potential of achieving excellent building energy consumption multi-step prediction results with a simple model design.

Predictive energy control for grid-connected industrial PV-battery systems using GEP-ANFIS

Rising energy costs in Uganda's industrial sector have significantly increased manufacturing expenses and led to the closure of potential enterprises, underscoring the urgent need for efficient energy management solutions. The study presents an optimization-based predictive energy control model that integrates Gene Expression Programming (GEP) and Adaptive Network-based Fuzzy Inference Systems (ANFIS) for grid-connected solar PV-battery systems. The hybrid GEP-ANFIS model leverages GEP's strength in complex pattern recognition and ANFIS's adaptive learning capability to manage nonlinear data, resulting in more accurate and reliable energy predictions. The model utilizes historical load patterns, grid data, and solar PV/battery inputs to forecast load demand and solar power generation, optimizing energy usage based on Time of Use (TOU) pricing. The approach addresses the limitations of existing energy management techniques by enhancing predictive accuracy and ensuring seamless integration with industrial applications. The present work demonstrates that the proposed GEP-ANFIS double diode model consistently outperforms its counterparts, achieving a mean absolute percentage error (MAPE) of 7.25 %, a mean absolute deviation (MAD) of 2.95 %, and a root mean square error (RMSE) of 8.42 %. Moreover, the model exhibits superior accuracy in predicting short-term load demand, with a MAPE of 2.24 %, a MAD of 0.13 %, and an RMSE of 0.18 %. Additionally, the model results in an average energy cost reduction of 6.7 % for hybrid grid-connected solar PV/battery configurations, highlighting its economic benefits. The study's key contributions include the creation of a novel hybrid predictive model, significant cost savings, improved load prediction accuracy, and the integration of renewable energy sources into industrial energy management. The model's inferences can effectively address the challenges of rising energy costs, providing a robust framework for sustainable and efficient energy management in industrial settings.

Two-stage feature selection for machine learning-aided DFT-based surface reactivity study on single-atom alloys

This paper presents a feature-centric strategy for predicting adsorption energies of key CO2 reduction reaction (CO2RR) adsorbates, CO and H species, utilizing density functional theory-based calculations for eight adsorption sites and considering alloying effects of nine transition metals at single-atom concentrations. Here, we explore a class of materials consisting of a majority host metal where individual atoms of a different element are dispersed called single-atom alloys (SAA). A total of eight feature selection methods are assessed within Gradient Boosting Regression and Linear Regression models. This study proposes a practical and effective two-stage approach that narrows down the initial 86 features to subsets of 10 and 7 for CO and H adsorption energy predictions, respectively, with the arithmetic mean of valence electrons (VE-am) feature consistently emerging as highly influential, validated through permutation and Shapley additive explanations-based feature importance analyses. The models exhibit robust performance on unseen data, indicating their generalization capability. The findings emphasize VE-am as a potential key machine learning feature for CO2RR on SAA surfaces and underline the effectiveness of the feature-centric approach in understanding feature impacts in machine learning models for CO2RR on SAA systems. Additionally, while other features based on structural, electronic and elemental properties may not individually impact the model significantly, their collective contribution plays a vital role in achieving more accurate adsorption energy predictions.

Unveiling Genetic Reinforcement Learning (GRLA) and Hybrid Attention-Enhanced Gated Recurrent Unit with Random Forest (HAGRU-RF) for Energy-Efficient Containerized Data Centers Empowered by Solar Energy and AI

The adoption of renewable energy sources has seen a significant rise in recent years across various industrial sectors, with solar energy standing out due to its eco-friendly characteristics. This shift from conventional fossil fuels to solar power is particularly noteworthy in energy-intensive environments such as cloud data centers. These centers, which operate continuously to support active servers via virtual instances, present a critical opportunity for the integration of sustainable energy solutions. In this study, we introduce two innovative approaches that substantially advance data center energy management. Firstly, we introduce the Genetic Reinforcement Learning Algorithm (GRLA) for energy-efficient container placement, representing a pioneering approach in data center management. Secondly, we propose the Hybrid Attention-enhanced GRU with Random Forest (HAGRU-RF) model for accurate solar energy prediction. This model combines GRU neural networks with Random Forest algorithms to forecast solar energy production reliably. Our primary focus is to evaluate the feasibility of solar energy in meeting the energy demands of cloud data centers that utilize containerization for virtualization, thereby promoting green cloud computing. Leveraging a robust German photovoltaic energy dataset, our study demonstrates the effectiveness and adaptability of these techniques across diverse environmental contexts. Furthermore, comparative analysis against traditional methods highlights the superior performance of our models, affirming the potential of solar-powered data centers as a sustainable and environmentally responsible solution.

Relative cooperativity in neutral and charged molecular clusters using QM/MM calculations.

QM/MM methods have been used to study electronic structure properties and chemical reactivity in complex molecular systems where direct electronic structure calculations are not feasible. In our previous work, we showed that non-polarizable force fields, by design, describe intermolecular interactions through pairwise interactions, overlooking many-body interactions involving three or more particles. In contrast, polarizable force fields account partially for many-body effects through polarization, but still handle van der Waals and permanent electrostatic interactions pairwise. We showed that despite those limitations, polarizable and non-polarizable force fields can reproduce relative cooperativity achieved using density functional theory due to error compensation mechanisms. In this contribution, we assess the performance of QM/MM methods in reproducing these phenomena. Our study highlights the significance of the QM region size and force field choice in QM/MM calculations, emphasizing the importance of parameter validation to obtain accurate interaction energy predictions.

Enhancing Microbial Fuel Cell Performance Prediction and IoT Integration Using Machine Learning and Renewable Energy

This study aims to enhance Microbial Fuel Cells (MFCs) reliability for remote environmental monitoring, emphasizing unexplored facets of accurate energy prediction and the integration of renewable energy-powered Internet of Things (IoT) devices. Following comprehensive research, design, and component procurement, an innovative and cost-effective IoT system was developed, leveraging renewable energy from MFCs. Using an Arduino UNO-WiFi, data was collected and showcased on a web page while logged in a Google Firebase database, with an Android app created for intuitive smartphone visualization. Over four months, sensor data was accumulated. An Artificial Intelligence (AI) model, employing Autoregressive Integrated Moving Average (ARIMA), precisely forecasted MFC energy production (RMSE: 0.0119 and 0.0113 for trials 1 and 2). Despite the initial energy production surge, a subsequent decline occurred due to organic matter depletion. This prototype represents an affordable and sustainable solution for cloud-based IoT environmental monitoring with AI-driven energy forecasts, embodying innovation in renewable energy applications and sustainable practices.

A many-to-many pick-up and delivery problem under stochastic battery depletion of electric vehicles

ABSTRACT The study extends the traditional pick-up and delivery problems (PDPs) to address the specific challenges of urban logistics and electric vehicle (EV) adoption. These challenges include the limited range of EVs, energy consumption along the route, and uncertainty in traffic conditions. To overcome the limited range of EVs, the study includes battery swapping stations to ensure sufficient energy to complete delivery routes. Vehicle energy consumption is considered to reduce range anxiety and optimize energy use. The study also considers the unpredictability of traffic conditions that affect energy consumption and delivery schedules. To address these concerns, the study proposes an approximate Quadratic Chance-Constrained Mixed-Integer Programming (QC-MIP) model with a linear approximation, a constructive heuristic and a meta-heuristic. These quantitative models incorporate comprehensive EV energy estimation approaches, enabling more accurate energy predictions. The proposed approaches provide valuable insights and strategies for improving energy efficiency and delivery performance in urban logistics environments.

Formation energy prediction of crystalline compounds using deep convolutional network learning on voxel image representation

Emerging machine-learned models have enabled efficient and accurate prediction of compound formation energy, with the most prevalent models relying on graph structures for representing crystalline materials. Here, we introduce an alternative approach based on sparse voxel images of crystals. By developing a sophisticated network architecture, we showcase the ability to learn the underlying features of structural and chemical arrangements in inorganic compounds from visual image representations, subsequently correlating these features with the compounds’ formation energy. Our model achieves accurate formation energy prediction by utilizing skip connections in a deep convolutional network and incorporating augmentation of rotated crystal samples during training, performing on par with state-of-the-art methods. By adopting visual images as an alternative representation for crystal compounds and harnessing the capabilities of deep convolutional networks, this study extends the frontier of machine learning for accelerated materials discovery and optimization. In a comprehensive evaluation, we analyse the predicted convex hulls for 3115 binary systems and introduce error metrics beyond formation energy error. This evaluation offers valuable insights into the impact of formation energy error on the performance of the predicted convex hulls.

Sequential attention deep learning architecture with unsupervised pre-training for interpretable and accurate building energy prediction with limited data

ABSTRACT Predicting building energy consumption is important for energy efficiency and reducing carbon emissions. However, deep learning (DL) models for energy consumption forecasting often have limited predictive generalization and lack explainability. To address these challenges, this research adopts a sequential attention deep learning architecture (SADLA) that uses attention mechanisms to learn the importance of different features for predicting cooling energy consumption, which helps building occupants and managers to make informed decisions about energy optimization. The model was trained and tested on comprehensive and scarce datasets in terms of recording periods and predictor numbers. The data were derived from a three-month field experiment in a commercial office building in Seoul, Korea. Furthermore, models were constructed with other prevalent algorithms like Long Short-Term Memory, deep neural networks, and Extreme Gradient Boosting for comparative assessment. The results from the one- and two-week datasets and reduced features suggested that the SADLA-based models surpassed others in model generalization (R2 = 0.961, 0.967, and 0.976 respectively). However, all algorithms demonstrated comparable performance with the three-month dataset achieving an average R2 of 0.970. These findings underscore the potential of the adopted model in addressing data scarcity in existing and new buildings for accurate cooling energy prediction.

Upsampling wave temporal resolution: Investigating wave parameters and the influence on WEC power performance

Power production of wave energy converters (WEC) predicted in the time domain utilize wave resource parameters and time-domain hydrodynamic model simulations of the WEC. While the hydrodynamic model provides high temporal resolution of power production (10’s of Hz), the wave resource parameters are often based on frequency-domain calculations with temporal resolution of 30 minutes to an hour. However, real ocean wave conditions vary on much shorter time scales. Relying on frequency-domain calculations will not be sufficient to capture the short-term variability and accurately predict WEC power production for a standardized methodology that follows power system requirements. These requirements need forecasted data with high sampling frequency for accurate energy predictions. Looking specifically at resource characterization, high temporal resolution datasets are not publicly available or do not exist for many coastal locations. Due to data availability, low temporal resolution datasets are being used in a majority of studies to generate representative wave conditions as inputs to numerical simulations. Representative wave conditions are used to generate wave spectrums. The issue with this practice is spectrums are then used to predict the efficiency of systems that will not accurately capture the variability of waves in short timeframes. Creating a standardized methodology to increase the temporal resolution of metaocean conditions to inform model development can provide better forecasting of power production. Random amplitude, Fourier coefficient methods have been suggested for WEC simulations of finite durations to improve the observed variability in wave heights and power production. Variability using this method does increase for finite durations compared to the commonly used deterministic amplitude method. In this paper we will investigate the influence of wave parameters (significant wave height, maximum wave height, and energy period) on the prediction of WEC power production. A better understanding of the influence of these parameters will provide a path towards future standardization methodology for resource inputs for time-domain modeling.

Influence of heating, air conditioning and vehicle automation on the energy and power demand of electromobility

With the increasing number of electric vehicles in the transport sector, the relevance of accurate energy and power demand predictions of electromobility is growing. Thereby, different vehicle functions, especially heating and air conditioning and vehicle automation, have a significant influence. In accordance with the upcoming Euro-7 emissions standard, the energy consumption for heating even has to be contained in the manufacturer’s consumption data in the future. To increase the accuracy of energy and power demand predictions of electromobility, the energy consumption of vehicle functions such as heating and air conditioning as well as the energy savings through vehicle automation must be considered.This paper presents approaches for modeling and simulation the energy consumption of heating, air conditioning and vehicle automation which can be used as an extension of electric vehicles WLTP (Worldwide Harmonized Light-Duty Vehicles Test Procedure) consumption simulation on the level of vehicle classes. The Germany-wide results of the electric vehicles energy demand for heating and air conditioning on the level of NUTS3-areas (Nomenclature of territorial units for statistics) and vehicle classes show regionally different results and confirm the relevance of the research approach. Vehicle automation results are described on the level of the five SAE automation levels (Society of Automotive Engineers automation levels) and the vehicle classes. The approaches and results can be used for single vehicles or assumed vehicle fleets.

SOLAR ENERGY FORECASTING WITH DEEP LEARNING TECHNIQUE

The increasing reliance on renewable energy sources, such as solar power, necessitates accurate forecasting to ensure efficient grid integration and stability. This study explores the application of deep learning techniques, particularly deep neural networks (DNNs), in predicting solar irradiance and power output. By leveraging advanced algorithms and large datasets, this research aims to enhance the precision of solar energy forecasts, thereby optimizing grid management and resource allocation. Deep learning techniques, characterized by their ability to model complex nonlinear relationships, offer significant advantages over traditional statistical methods in forecasting solar energy. This study focuses on the development and evaluation of deep neural networks for predicting solar irradiance, which directly influences the power output of photovoltaic (PV) systems. The models are trained on extensive historical weather data, satellite imagery, and real-time solar output measurements to capture temporal and spatial variations in solar energy. Key components of the research include data preprocessing to handle missing values and noise, feature extraction to identify relevant patterns, and model training using various architectures of DNNs such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs). The study also employs ensemble learning techniques to combine predictions from multiple models, further enhancing forecast accuracy. Results demonstrate that deep neural networks significantly outperform traditional forecasting methods in terms of accuracy and reliability. The improved forecasts enable better scheduling of energy generation and distribution, reducing reliance on fossil fuels and minimizing grid imbalances. Additionally, accurate solar energy predictions support the efficient integration of solar power into the grid, enhancing overall system stability and reducing operational costs. The study also addresses challenges in implementing deep learning models, such as computational requirements and the need for large, high-quality datasets. Solutions include leveraging cloud computing resources and developing standardized data collection protocols to facilitate broader application and scalability of the models. Application of deep learning techniques in solar energy forecasting represents a promising advancement for the renewable energy sector. By improving the accuracy of solar irradiance and power output predictions, deep neural networks contribute to more reliable grid integration and efficient energy management. This research advocates for the continued exploration and adoption of advanced machine learning methods to support the transition to a sustainable energy future. Keywords: Deep Learning Techniques; Solar Energy; Forecasting; Grid Integration; Power Output.

Energy Management of Sowing Unit for Extended-Range Electric Tractor Based on Improved CD-CS Fuzzy Rules

In order to ensure the continuity and endurance mileage requirements during sowing operations, it is necessary to establish accurate modeling for the working condition of the electric tractor sowing unit by adopting a reasonable energy management strategy and realizing accurate energy prediction. The existing electric tractor sowing unit battery energy management strategy is not optimal since it is mostly based on extensive rules. In this paper, according to the requirements of the sowing conditions, a precise model of electric energy consumption in the sowing cycle was established and an energy management strategy of sowing unit of extended-range electric tractor with power CD-CS was proposed. Fuzzy control rules of the dynamic SOC correction factor were established in the battery maintenance stage, and the NSGA-II algorithm was used to optimize the fuzzy control rules to optimize the battery charging and discharging efficiency. A hardware-in-the-loop simulation test platform was built, and the proposed CD-CS strategy was compared with the fuzzy improvement strategy. The simulation results show that the proposed fuzzy improvement strategy extended the battery life of the power consumption stage by 2131.9 s, which is a significant improvement. The field practical results showed that the SOC decreased by 7.21% and the simulation by 4.94% in terms of power consumption in a cycle. The power consumption variance was within a reasonable range, which further verifies the feasibility of the strategy.

Force-field-enhanced neural network interactions: from local equivariant embedding to atom-in-molecule properties and long-range effects.

We introduce FENNIX (Force-Field-Enhanced Neural Network InteraXions), a hybrid approach between machine-learning and force-fields. We leverage state-of-the-art equivariant neural networks to predict local energy contributions and multiple atom-in-molecule properties that are then used as geometry-dependent parameters for physically-motivated energy terms which account for long-range electrostatics and dispersion. Using high-accuracy ab initio data (small organic molecules/dimers), we trained a first version of the model. Exhibiting accurate gas-phase energy predictions, FENNIX is transferable to the condensed phase. It is able to produce stable Molecular Dynamics simulations, including nuclear quantum effects, for water predicting accurate liquid properties. The extrapolating power of the hybrid physically-driven machine learning FENNIX approach is exemplified by computing: (i) the solvated alanine dipeptide free energy landscape; (ii) the reactive dissociation of small molecules.

Building Energy Consumption Forecast under Different Anticipations on a Green Computation Perspective

Electrical buildings are composed by smart grids technologies intended on improving the energy efficiency. Nowadays, forecasting algorithms are crucial to formulate advance decisions resulting in lower energy costs. This paper uses two forecasting algorithms known as artificial neural networks and k-nearest neighbors to obtain accurate energy predictions in a target week with the support of an annual historic with energy and auxiliary sensors devices data. Green computing is also addressed in this paper to value the environmental sustainability of computing devices. This is possible by reducing the computational effort of the GPU device dedicated on forecasting activities. Therefore, the historic and predictions of this paper are contextualized in five minutes periods and hour schedules with energy activity behaviors.

Monte Carlo energy spectrum matching method for SiPM-based EJ254 plastic scintillator detector calibration

Accurate energy measurement is the precondition for the application of plastic scintillator-based spectrometers in space exploration missions, and appropriate energy calibration methods are very important for plastic scintillators. At the same time, the energy resolution is a key factor in evaluating the performance of spectrometers. In this paper, an energy calibration method that can be used for plastic scintillators is proposed, and the energy resolution calibration results were also obtained in the process. The key of the method is to focus on the accurate energy prediction of the reference points in the Compton Continuum by using the Monte Carlo energy spectrum matching method. In the calibration process, the experimental measurements and Monte Carlo simulations of 22Na and 137Cs were carried out, and the shapes of the obtained spectra were matched by a certain energy resolution model. By shape matching, the Monte Carlo simulations provided energies of reference points, and the experiments provided their corresponding channel numbers. Then the parameters of the energy calibration model were obtained by fitting with multiple reference points’ paired data. Moreover, the backscattering experiments with 131I, 137Cs, and 232Th sources were executed to equivalently provide monoenergetic electrons to verify the energy calibration and energy resolution model parameters obtained for the EJ254 spectrometer. The accuracy was high in the energy range of 341∼2381.6 keV, the maximum bias of the energy was −4.7 keV (@2381.6 keV), and the maximum bias of the energy resolution model was 4.7% (@341 keV).