Modeling Solution Research Articles

3D model-based scan planning for space frame structures considering site conditions

The acquisition of point cloud data from a space frame using terrestrial laser scanning is usually affected by many occluding components and site conditions and therefore needs to achieve optimal priori planning, which is handled as the planning for scanning (P4S) problem. This paper describes a three-dimensional model-based P4S approach for space frame structures, where a space modeling solution is employed to simulate the scanning target and environment. The P4S problem modeling is used to define the visibility analysis and constraints. Lastly, a two-phase optimization is proposed to solve the P4S problem and compared with a weighted greedy algorithm. Experiments were conducted on a full-scale space frame to validate the proposed approach.

An Evolutionary Field Theorem: Evolutionary Field Optimization in Training of Power-Weighted Multiplicative Neurons for Nitrogen Oxides-Sensitive Electronic Nose Applications.

Neuroevolutionary machine learning is an emerging topic in the evolutionary computation field and enables practical modeling solutions for data-driven engineering applications. Contributions of this study to the neuroevolutionary machine learning area are twofold: firstly, this study presents an evolutionary field theorem of search agents and suggests an algorithm for Evolutionary Field Optimization with Geometric Strategies (EFO-GS) on the basis of the evolutionary field theorem. The proposed EFO-GS algorithm benefits from a field-adapted differential crossover mechanism, a field-aware metamutation process to improve the evolutionary search quality. Secondly, the multiplicative neuron model is modified to develop Power-Weighted Multiplicative (PWM) neural models. The modified PWM neuron model involves the power-weighted multiplicative units similar to dendritic branches of biological neurons, and this neuron model can better represent polynomial nonlinearity and they can operate in the real-valued neuron mode, complex-valued neuron mode, and the mixed-mode. In this study, the EFO-GS algorithm is used for the training of the PWM neuron models to perform an efficient neuroevolutionary computation. Authors implement the proposed PWM neural processing with the EFO-GS in an electronic nose application to accurately estimate Nitrogen Oxides (NOx) pollutant concentrations from low-cost multi-sensor array measurements and demonstrate improvements in estimation performance.

Is the Hénon map able to predict the interaction dynamics between the knee and hip joints emerged during sit-to-stand movement?

In this study, the performance of a two-dimensional Hénon map in predicting the interactive dynamics of the knee and hip joints emerging during a normative sit-to-stand movement was evaluated. The instantaneous values of the knee and hip joints were the model inputs, and the next values of the knee and hip joints were predicted by the Hénon map. The map predicted the desired relative behavior of the joints, showing synergetic coordination between the joints. The experimental data were recorded from four healthy participants and used to identify the Hénon map via a genetic algorithm. Model performance was quantitatively assessed by computing the calculated prediction error and analyzing the behavioral dynamics of the state spaces reconstructed via the captured kinematic data. According to the results, there was an obvious similarity between the dynamics of the state space trajectories of the identified model and those of the recorded data, not only in terms of stretching and folding dynamics, but also concerning generalized synchrony. The acceptable performance of the proposed modeling solution can also be demonstrated through these results.

A building information modeling‐fire dynamics simulation integrated framework for the simulation of passive fire protection in a mid‐scale cross‐laminated timber compartment: Numerical implementation and benchmarking

AbstractConstruction fires are a big threat to worker safety and property safety. Mass timber buildings under construction are largely unprotected as they are not yet equipped with active fire protection systems. With the addition of Types IVA, B, and C, the 2021 International Building Code adopted stricter requirements for mass timber buildings that are under construction. Cross‐laminated timber (CLT) is used as the primary structural element for high‐rise mass timber buildings. However, to date, limited number of research studies investigated the impact of passive fire protection for CLT buildings that are under construction. To facilitate a better understanding of construction fires and their consequences, it is necessary to develop a numerical modeling solution for the early phases of a CLT construction project, which can be achieved by using building information models together with fire dynamics simulation (FDS). However, the numerical modeling technique must be benchmarked against experimental data first to then extrapolate the modeling technique to explore other parameters and conduct FDS analysis. Therefore, this paper develops and benchmarks a numerical modeling solution against a mid‐scale CLT compartment fire test by applying the FDS tool to simulate the fire behavior within the CLT compartment. The FDS analysis results are expected to validate the practicality of simulating the fire behavior in CLT structures using the numerical model proposed in this study. The overarching goal of this study is therefore to develop a comprehensive numerical modeling solution to simulate and assess passive fire protection sequencing in CLT buildings that are under construction.

An automated machine learning methodology for the improved prediction of reference evapotranspiration using minimal input parameters

AbstractAn accurate and minimal meteorological parameter‐based reference evapotranspiration (ETo) computational model is highly essential to design a cost‐effective and automated solution for precise water allocation in various agricultural and hydrological applications. Automated machine learning (AutoML), a substantially progressive machine learning (ML) paradigm, expedites the data science applications in these domains by automating and alleviating the tedious tasks of developing ML pipelines, particularly in non‐linear hydrological process modelling. This paper proposes an AutoML solution for daily EToprediction in a limited input parameter scenario, for the first time in EToestimation research. Two AutoML frameworks, AutoGluon‐Tabular (AGT) and H2O AutoML were implemented using daily meteorological data of a humid tropical climatic region of Kerala, India and evaluated its performance with the radiation‐based empirical methods and traditional ML methods. The developed AutoML models imitated the input parameter combinations of radiation‐based empirical models such as Priestley‐Taylor, Makkink, Turc and Ritchie, with the Penman‐Monteith EToserving as the target for modelling process. An improvement of mean absolute error from 0.119 to 0.078 mm/day, mean squared error from 0.035 to 0.017 mm/day, root mean squared error from 0.186 to 0.129 mm/day, root mean squared logarithmic error from 0.078 to 0.026 mm/day, and coefficient of determination (R2) from 0.971 to 0.985 observed in the AutoML model, AGT relative to the empirical model, Turc describes its enhanced performance capability. For demonstrating the superiority of AutoML to traditional ML techniques, another set of AutoML models were also developed based on California Irrigation Management Information System datasets and evaluated them with existing study results in literature. The overall result analysis demonstrated the superiority of AGT model in EToprediction in all the weather stations considered in this study. The results of the study confirm that AutoML techniques can be applied to any hydrological dataset and provide an effective automated solution for hydrological process modelling.

Challenges and Possible Solutions in Aeroelastic Modeling for the Distributed Wind Industry

Aeroelastic modeling (AM) is the primary methodology for structural and performance assessment of any wind turbine; it provides an understanding of the impact of design parameters on turbine loading and power response before witnessing it in the field. Despite these advantages, the use of AM in the distributed wind technology (DWT) sector is limited. This article represents a short summary of an in-depth assessment by the authors of the status of AM and its role within the distributed wind technology design standards. The research gathered input and feedback from a large number of U.S. and international stakeholders, reviewed technical strengths and weaknesses of the current edition of the design standards, analyzed the minutes from recent industry workshops and meetings, collected publicly available AM templates, and provided an evaluation of the existing AM codes. Several goals were achieved including providing strategies for the load assessment categorization of turbines based on rotor swept area and archetype, and guidance for AM verification and validation. Recommendations within this study will advance the value and the ease-of-use of AM, thereby allowing the industry to better capitalize this underutilized tool, resulting in a more efficient design process, an easier path to certification, and overall better and more reliable distributed wind technology products.

Modeling the Impact of Dynamic Fin-Width on the I– V, C– V and RF Characteristics of GaN Fin–HEMTs

In this article, we introduce an engineering approach to model the current and charge characteristics of an AlGaN/GaN Fin–HEMT. The model handles the effective width of the 2DEG channel by considering its depletion due to the presence of gates on the sidewalls of the fin. This width modulation of the 2DEG, and the bias-dependence associated with it, significantly affects the transconductance and the capacitance behavior of the device. In this work, we modify and couple two industry-standard compact models: 1) the advanced SPICE model for GaN HEMTs (ASM-GaN-HEMT) model and 2) the Berkeley short-channel insulated-gate FET model for common multiple gate (BSIM-CMG) model. While the former provides the physics-based calculations for electrostatics and transport in the 2DEG, the latter is incorporated to account for the width-modulation due to the sidewalls. The developed methodology is validated for dc, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${C}$ </tex-math></inline-formula> – <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${V}$ </tex-math></inline-formula> , and RF behavior against experimental data of GaN Fin–HEMTs. To the authors’ knowledge, this is the first compact model that provides an end-to-end dc–radio frequencies (RF) modeling solution for the state-of-the-art GaN Fin–HEMTs and therefore could play a role in the evolution of the GaN Fin–HEMT technology.

Vestibular Deficits in Deafness: Clinical Presentation, Animal Modeling, and Treatment Solutions.

The inner ear is responsible for both hearing and balance. These functions are dependent on the correct functioning of mechanosensitive hair cells, which convert sound- and motion-induced stimuli into electrical signals conveyed to the brain. During evolution of the inner ear, the major changes occurred in the hearing organ, whereas the structure of the vestibular organs remained constant in all vertebrates over the same period. Vestibular deficits are highly prevalent in humans, due to multiple intersecting causes: genetics, environmental factors, ototoxic drugs, infections and aging. Studies of deafness genes associated with balance deficits and their corresponding animal models have shed light on the development and function of these two sensory systems. Bilateral vestibular deficits often impair individual postural control, gaze stabilization, locomotion and spatial orientation. The resulting dizziness, vertigo, and/or falls (frequent in elderly populations) greatly affect patient quality of life. In the absence of treatment, prosthetic devices, such as vestibular implants, providing information about the direction, amplitude and velocity of body movements, are being developed and have given promising results in animal models and humans. Novel methods and techniques have led to major progress in gene therapies targeting the inner ear (gene supplementation and gene editing), 3D inner ear organoids and reprograming protocols for generating hair cell-like cells. These rapid advances in multiscale approaches covering basic research, clinical diagnostics and therapies are fostering interdisciplinary research to develop personalized treatments for vestibular disorders.

Deep learning for end-to-end subsurface modeling and interpretation: An example from the Groningen gas field

Subsurface interpretation and modeling are crucial to the success of reservoir exploration and production, which often involves integrating multiple types of subsurface data and accomplishing a series of subtasks consecutively and/or in parallel. Those tasks include data processing and conditioning, structural mapping, property modeling, and others. With the emergence of machine learning (ML), each component of the subsurface modeling and interpretation workflow now has elements of ML automation incorporated into individual steps. However, there have been few attempts to generate an integrated end-to-end workflow that incorporates ML at every stage. This paper presents an end-to-end solution for subsurface modeling and interpretation that is powered by multiple convolutional neural networks (CNNs). Its performance is demonstrated on the Groningen gas field. The workflow can be subdivided into four parts, with the initial phase focusing on data preconditioning, particularly log quality control and reconstruction. Phase two focuses on seismic property estimation (i.e., relative geologic time) and structural feature identification and extraction (i.e., fault and salt). Phase three combines seismic feature extraction, log data, derived seismic properties, and interpretations to generate a 3D rock property model containing modeled gamma ray, density, velocity, and porosity properties. The final component is to validate the estimated subsurface properties by CNN-based seismic image simulation. The results demonstrated in the Groningen field show high accuracy, strong lateral consistency, and a good match with the dominant subsurface features documented in this area, including the Zechstein salt, the complex fault system, and the Rotliegend reservoir model. We conclude that this end-to-end workflow can be readily applied to other fields to provide a one-click solution for efficient subsurface modeling and interpretation.

Innovative Educational Communication in the Global Digital Environment: Trans-Disciplinary Models, Tools, and Mechanisms

The objective of the inquiry is on innovative communication in the light of identifying trans-disciplinary aspects of phylogeny, sociogenesis, and technogenesis of educational communities, which determines the identification of this communicative sphere as an integrative structure determined by the internal unity of its micro- and macro-structures, which in the plane of the sign substrate synthesizes the features of existential, cognitive, anthropological and technological substance. Applied trans-disciplinary lens of the phenomenological approach to the study contributes to the solution of holistic modeling of processes and results of updating models and mechanisms of the highly dynamic communication system of education in the digital environment as a whole and its individual formats at the beginning of the XXI century in particular. The object of research is innovative educational communication in the global digital environment. The study focus is on innovative language and technology models, digital tools, and mechanisms of educational communication in the digital realm. The empirical basis of the research is the practices of innovative communication related to different substrates, formats, objects, and phenomena of acquiring new knowledge and education in the digital realm. The study results allow to provide a transdisciplinary synthesis (across communicative theory, information theory, philosophy, education and e-learning studies, semiotics, digital humanities).

Dynamic Rolling Horizon Scheduling of Waterborne AGVs for Inter Terminal Transportation: Mathematical Modeling and Heuristic Solution

The demand for transport between terminals within port areas, known as inter terminal transportation (ITT), is increasing. This paper proposes a dynamic rolling horizon scheduling strategy for ITT using a fleet of waterborne Autonomous Guided Vessels (waterborne AGVs). The strategy is dynamic in that it can handle dynamically arriving ITT requests. Every certain period of time, transport schedules are updated according to the current vessel states, dynamic waterway transport network, and ITT requests over a future time horizon. Specifically, the dynamic scheduling problem is mathematically modeled in a rolling horizon fashion considering time windows of ITT requests, capacity limits of waterborne AGVs and load/unload service times at terminals. Considering the computational complexity for possible large scale ITT scenarios, we further propose an efficient solution approach based on improved insertion, tabu search and restart heuristics. Initial routes are first constructed by inserting new ITT requests into the previously computed routes in the rolling horizon framework. Tabu search with two types of neighborhoods are then designed to improve the initial routes. Moreover, a select-remove-insert restart procedure is activated to diversify the search space whenever necessary. A waterborne ITT network in the port of Rotterdam is considered. Comprehensive simulations based on realistic ITT dataset are run to demonstrate the effectiveness of the proposed dynamic scheduling strategy. This work could be readily used to build towards a fully autonomous waterborne ITT system. Insights that support long term strategical decisions, such as the fleet size, could also be gained from the simulations.

A Two-stage Successive Approximation Method of Dynamic Programming for Operations of Cascaded Hydropower Plants with Navigation Demand

The operations of cascaded hydropower plants have always been recognized as a complex system optimization problem. The difficulty of modelling and optimization solution is further aggravated when comprehensive water demands for power generation, navigation and ecology are considered. This study develops an optimization model for operations of cascaded hydropower plants with navigation demands, and proposes a two-stage successive approximation method of dynamic programming. In the model, the navigation demand is considered as a constraint. The first stage is to optimize the operation of cascaded hydropower plants with no consideration of navigation demand. The optimized result is taken as an initial solution of the last stage. Moreover, the navigation constraint is introduced in the solution procedure to obtain a reasonable operation scheme. The method is implemented on operations of a cascaded hydropower plants with navigation task in Southwest China. The results show that the navigation demand can be satisfied by coordination of cascaded hydropower plants. Moreover, this constraint has an effect on the monthly distribution of total energy production during one year. In addition, the computing efficiency and solution accuracy are analysed by using different discrete steps.

A review on water simulation models for the WEF Nexus: development perspective.

The primary impediment to adopting the Water, Energy, and Food (WEF) Nexus is a lack of a comprehensive and user-friendly simulation model. According to our search on Google Scholar and the Scopus databank, WEF Nexus studies can be divided into three broad categories: (1) studies about the nexus concept, (2) studies related to nexus modeling and software development, and (3) case studies. Given that the present study's objective is to review various solutions for WEF Nexus modeling and also to prepare a checklist of available models to find a better model for nexus simulation, we excluded papers and studies which were related to the nexus concept. After that, we split up other papers that talked about nexus and software development into (1) integrated and (2) compiled approaches. Then, it was attempted to identify the shortcomings in each approach. It was shown that the existing integrated WEF Nexus models (such as MUSIASEM, NexSym, CLEW, and ANEMI) had some significant drawbacks compared to compiled alternatives. Several of the major shortcomings of existing integrated models include the following: (1) They did not cover all spatial scales; (2) they included only a limited number of interactions across WEF subsystems; and (3) some of these models were unavailable. Therefore, as a general result of the current study, it was shown that compiled approach is generally preferable compared to available integrated models. In this regard, we tried to find the best water simulation models to implement in the nexus concept. We searched for papers about water simulation models and defined water subsystem requirements in the nexus concept. So, we evaluated each water simulation model based on its ability to cover water subsystem requirements. This work illustrates the capability of a suitable water simulation model to be utilized in the nexus concept and provides a holistic checklist to choose the preferred water simulation model based on the needs of each issue.

Mathematical Modeling and Analytical Solution of Thermoelastic Stability Problem of Functionally Graded Nanocomposite Cylinders within Different Theories

Revolutionary advances in technology have led to the use of functionally graded nanocomposite structural elements that operate at high temperatures and whose properties depend on position, such as cylindrical shells designed as load-bearing elements. These advances in technology require new mathematical modeling and updated numerical calculations to be performed using improved theories at design time to reliably apply such elements. The main goal of this study is to model, mathematically and within an analytical solution, the thermoelastic stability problem of composite cylinders reinforced by carbon nanotubes (CNTs) under a uniform thermal loading within the shear deformation theory (ST). The influence of transverse shear deformations is considered when forming the fundamental relations of CNT-patterned cylindrical shells and the basic partial differential equations (PDEs) are derived within the modified Donnell-type shell theory. The PDEs are solved by the Galerkin method, and the formula is found for the eigenvalue (critical temperature) of the functionally graded nanocomposite cylindrical shells. The influences of CNT patterns, volume fraction, and geometric parameters on the critical temperature within the ST are estimated by comparing the results within classical theory (CT).

COMMIT: Consideration of metabolite leakage and community composition improves microbial community reconstructions.

Composition and functions of microbial communities affect important traits in diverse hosts, from crops to humans. Yet, mechanistic understanding of how metabolism of individual microbes is affected by the community composition and metabolite leakage is lacking. Here, we first show that the consensus of automatically generated metabolic reconstructions improves the quality of the draft reconstructions, measured by comparison to reference models. We then devise an approach for gap filling, termed COMMIT, that considers metabolites for secretion based on their permeability and the composition of the community. By applying COMMIT with two soil communities from the Arabidopsis thaliana culture collection, we could significantly reduce the gap-filling solution in comparison to filling gaps in individual reconstructions without affecting the genomic support. Inspection of the metabolic interactions in the soil communities allows us to identify microbes with community roles of helpers and beneficiaries. Therefore, COMMIT offers a versatile fully automated solution for large-scale modelling of microbial communities for diverse biotechnological applications.

A predictive solution for fracture modeling of alkali-activated slag and fly ash blended sea sand concrete after exposure to elevated temperature

Because of the heterogeneous and discontinuous properties in concrete, realistic fracture parameters were hardly obtained rationally based on traditional methods. The material heterogeneity and discontinuity may be more significant under the attack of high temperature. Therefore, the intention of this paper is to propose a predictive solution for fracture modeling of AASC (alkali-activated ground granulated blast furnace slag (GGBFS) and fly ash (FA) blended sea sand concrete) after exposure to elevated temperature. First, fracture test was performed on AASC after exposure to four high temperatures plus one room temperature. The fracture process and failure mechanism were analyzed and clarified at both macro- and micro-scales. Subsequently, an analytical model was presented to determine the fracture parameters of AASC by incorporating the material heterogeneity and discontinuity. The realistic tensile strength ft, fracture toughness KIC and fracture energy GF were then explicitly linked to the maximum fracture load Fmax by virtue of boundary effect model. Results show that the load-displacement curve becomes gentler and the failure mode is changed from trans-granular fracture to inter-granular fracture as the temperature increases. Once the Fmax is obtained from the test, the realistic ft, KIC and GF from each specimen can be predicted conveniently. The scatters in the predicted parameters would be clarified assisted by statistical analysis. As the temperature increases, the ft is reduced and the reduction becomes larger. But the GF shows insignificant variation until the temperature attains 400 °C, and apparently decreases as the temperature is further enhanced. Moreover, the predicted fracture parameters of AASC with higher GGBFS/FA mass ratio are larger than those of the other AASC below 400 °C. However, the former has higher strength loss than the latter. The crack resistance of AASC after exposure to high temperature can be well clarified based on the proposed predictive model.

Towards an Interoperable Approach for Modelling and Managing Smart Building Data: The Case of the CESI Smart Building Demonstrator

Buildings have a significant impact on energy consumption and carbon emissions. Smart buildings are deemed to play a crucial role in improving the energy performance of buildings and cities. Managing a smart building requires the modelling of data concerning smart systems and components. While there is a significant amount of research on optimising building energy using the smart building concept, there is a dearth of studies investigating the modelling and management of smart systems’ data, which is the starting point for establishing the necessary digital environment for representing a smart building. This study aimed to develop and test a solution for modelling and managing smart building information using an industry foundation classes (IFCs)-based BIM process. A conceptual model expressed in the SysML language was proposed to define a smart building. Five BIM approaches were identified as potential ‘prototypes’ for representing and exchanging smart building information. The fidelity of each approach is checked through a BIM-based validation process using an open-source visualisation platform. The different prototypes were also assessed using a multi-criteria comparison method to identify the preferred approach for modelling and managing smart building information. The preferred approach was prototyped and tested in a use case focused on building energy consumption monitoring to evaluate its ability to manage and visualise the smart building data. The use case was applied in a real case study using a full-scale demonstrator, namely, the ‘Nanterre 3’ (N3) smart building located at the CESI campus in Paris-Nanterre. The findings demonstrated that an open BIM format in the form of IFCs could achieve adequate modelling of smart building data without information loss. Future extensions of the proposed approach were finally outlined.

Modeling method for grounded coplanar waveguide with vector fitting technique

AbstractIn this article, a semiempirical equivalent circuit model of the grounded coplanar waveguide (GCPW) based on the vector fitting is proposed for the first time, which improves the accuracy in high frequency. It offers an effective solution for the millimeter GCPW modeling. This model takes into account nonideal effects such as skin effect and substrate coupling effect, which realizes the combination of numerical method and physical meaning. The method we propose aims to use sequential quadratic programming algorithm to solve strictly passive problems. Good agreement is obtained between the modeled and measured data up to 40 GHz.

A statistical modelling approach for source attribution meta-analysis of sporadic infection with foodborne pathogens.

Numerous source attribution studies for foodborne pathogens based on epidemiological and microbiological methods are available. These studies provide empirical data for modelling frameworks that synthetize the quantitative evidence at our disposal and reduce reliance on expert elicitations. Here, we develop a statistical model within a Bayesian estimation framework to integrate attribution estimates from expert elicitations with estimates from microbial subtyping and case‐control studies for sporadic infections with four major bacterial zoonotic pathogens in the Netherlands (Campylobacter, Salmonella, Shiga toxin‐producing E. coli [STEC] O157 and Listeria). For each pathogen, we pooled the published fractions of human cases attributable to each animal reservoir from the microbial subtyping studies, accounting for the uncertainty arising from the different typing methods, attribution models, and year(s) of data collection. We then combined the population attributable fractions (PAFs) from the case‐control studies according to five transmission pathways (domestic food, environment, direct animal contact, human–human transmission and travel) and 11 groups within the foodborne pathway (beef/lamb, pork, poultry meat, eggs, dairy, fish/shellfish, fruit/vegetables, beverages, grains, composite foods and food handlers/vermin). The attribution estimates were biologically plausible, allowing the human cases to be attributed in several ways according to reservoirs, transmission pathways and food groups. All pathogens were predominantly foodborne, with Campylobacter being mostly attributable to the chicken reservoir, Salmonella to pigs (albeit closely followed by layers), and Listeria and STEC O157 to cattle. Food‐wise, the attributions reflected those at the reservoir level in terms of ranking. We provided a modelling solution to reach consensus attribution estimates reflecting the empirical evidence in the literature that is particularly useful for policy‐making and is extensible to other pathogens and domains.

A Hybrid Bimodal LSTM Architecture for Cascading Thermal Energy Storage Modelling

Modelling of thermal energy storage (TES) systems is a complex process that requires the development of sophisticated computational tools for numerical simulation and optimization. Until recently, most modelling approaches relied on analytical methods based on equations of the physical processes that govern TES systems’ operations, producing high-accuracy and interpretable results. The present study tackles the problem of modelling the temperature dynamics of a TES plant by exploring the advantages and limitations of an alternative data-driven approach. A hybrid bimodal LSTM (H2M-LSTM) architecture is proposed to model the temperature dynamics of different TES components, by utilizing multiple temperature readings in both forward and bidirectional fashion for fine-tuning the predictions. Initially, a selection of methods was employed to model the temperature dynamics of individual components of the TES system. Subsequently, a novel cascading modelling framework was realised to provide an integrated holistic modelling solution that takes into account the results of the individual modelling components. The cascading framework was built in a hierarchical structure that considers the interrelationships between the integrated energy components leading to seamless modelling of whole operation as a single system. The performance of the proposed H2M-LSTM was compared against a variety of well-known machine learning algorithms through an extensive experimental analysis. The efficacy of the proposed energy framework was demonstrated in comparison to the modelling performance of the individual components, by utilizing three prediction performance indicators. The findings of the present study offer: (i) insights on the low-error performance of tailor-made LSTM architectures fitting the TES modelling problem, (ii) deeper knowledge of the behaviour of integral energy frameworks operating in fine timescales and (iii) an alternative approach that enables the real-time or semi-real time deployment of TES modelling tools facilitating their use in real-world settings.