Fig 6 - uploaded by Patrizia Aversa
Content may be subject to copyright.
shows the thermal transmittance trend calculated in accordance with equation (2); it is evident that, in all the cases investigated, after several hours of measurement the thermal transmittance tends to a constant value. In particular, the amplitude of oscillations was calculated in the last 24 hours, according to equation:
Source publication
Although the designed theoretical value of U can be derived from the thermal parameters of layers composing an opaque element, according to ISO 6946:2007, measurements are necessary to confirm the expected behaviour. Currently, the measurements of thermal transmittance based on Heat Flow Meter method (HFM) and according to standard ISO 9869-1:2014...
Citations
... The construction industry is responsible for around 40% of global energy consumption [2]. Moreover, rapid population growth has increased the energy demand for buildings [3]. Hence, buildings need to be energy efficient and one effective way to realize this goal is predictive analytics of buildings' energy consumption [4]. ...
The prediction of building energy consumption is beneficial to utility companies, users, and facility managers to reduce energy waste. However, due to various drawbacks of prediction algorithms, such as, non-transparent output, ad hoc explanation by post hoc tools, low accuracy, and the inability to deal with data uncertainties, such prediction has limited applicability in this domain. As a result, domain knowledge-based explainability with high accuracy is critical for making energy predictions trustworthy. Motivated by this, we propose an advanced explainable Belief Rule-Based Expert System (eBRBES) with domain knowledge-based explanations for the accurate prediction of energy consumption. We optimize BRBES’s parameters and structure to improve prediction accuracy while dealing with data uncertainties using its inference engine. To predict energy consumption, we take into account floor area, daylight, indoor occupancy, and building heating method. We also describe how a counterfactual output on energy consumption could have been achieved. Furthermore, we propose a novel Belief Rule-Based adaptive Balance Determination (BRBaBD) algorithm for determining the optimal balance between explainability and accuracy. To validate the proposed eBRBES framework, a case study based on Skellefteå, Sweden, is used. BRBaBD results show that our proposed eBRBES framework outperforms state-of-the-art machine learning algorithms in terms of optimal balance between explainability and accuracy by 85.08%.
... Hence, there is no consensus on the best tools for certain conditions [29]. Several data-driven tools possess to the capacity produce optimal performance in different conditions based on their related strengths; for example, Artificial Neural Network (ANN) is recognized for its production of optimal performance following the availability of a large dataset to train the model [30], and similarly, Support Vector Machine (SVM) using a small dataset [31]. However, ANN has been applied in small data conditions, and vice versa. ...
... This paper conducted a systematic review of data-driven tools and their performance in various conditions. The arbitrary selection of tools for building energy prediction engendered few tools that produced good performance (i.e., ANN [30], SVM) [31]. However, to reduce the time-consuming comparative analysis and achieve optimum performance, developers need to gain a better comprehension of the selection of the appropriate tool for a specific condition (for example, the type of building considered, data properties, required In the past decade, several data-driven tools have been applied for energy prediction, to such an extent that it is essentially unviable to comprehensively review all tools in a single study. ...
... However, ANN and other fairly common data-driven tools (i.e., RF, LR) have been utilized and compared in various studies using a small data sizes [71,73,116]. More recently, SVM has emerged as one of the most utilized data-driven tools based on its capacity to produce good outcomes regardless of the data size [31,33,117]. However, a drawback of SVM is its large requirements and low computational efficiency [118]. ...
The development of data-driven building energy consumption prediction models has gained more attention in research due to its relevance for energy planning and conservation. However, many studies have conducted the inappropriate application of data-driven tools for energy consumption prediction in the wrong conditions. For example, employing a data-driven tool to develop a model using a small sample size, despite the recognition of the tool for producing good results in large data conditions. This study delivers a review of 63 studies with a precise focus on evaluating the performance of data-driven tools based on certain conditions; i.e., data properties, the type of energy considered, and the type of building explored. This review identifies gaps in research and proposes future directions in the field of data-driven building energy consumption prediction. Based on the studies reviewed, the outcome of the evaluation of the data-driven tools performance shows that Support Vector Machine (SVM) produced better performance than other data-driven tools in the majority of the review studies. SVM, Artificial Neural Network (ANN), and Random Forest (RF) produced better performances in more studies than statistical tools such as Linear Regression (LR) and Autoregressive Integrated Moving Average (ARIMA). However, it is deduced that none of the reviewed tools are predominantly better than the other tools in all conditions. It is clear that data-driven tools have their strengths and weaknesses, and tend to elicit distinctive results in different conditions. Hence, this study provides a proposed guideline for the selection tool based on strengths and weaknesses in different conditions.
... More specifically, it consumes about 21% of the total final energy in the world, which places it among the most energy-intensive sectors 1 [2]. However, inefficient buildings consume more than their energy needs and are therefore cause additional GHG emissions [3]. It has already been repeatedly demonstrated that climate change, thermal pollution and air pollution have disastrous consequences for mankind [4,5]. ...
... If an accurate energy prediction technique for buildings were developed, studies show that it would: i) reduce energy consumption by up to 30% [3,40], by either focusing on insulation [41], choosing the right HVAC system [42], using LED lights [43], or by renovating the building to the relevant ecological standard [44]; ii) reduce GHG emissions [5,45]; and iii) limit the construction of inefficient buildings [46], and consequently financial investments [47]. Energy demand forecasting is therefore at the vanguard of sustainability and high performance building design. ...
... Although 2 this performance is better than that reported in this study (whether on 1816 or 7559 instances), the size of data employed can be questioned. Indeed, many researchers have reported that SVM performs worse when implemented with a large dataset [3,58,75,101]. This was demonstrated when Dong et al. [60] used 507 instances to implement SVM to predict hourly load of buildings. ...
Very little work has been done on the feasibility of Machine Learning (ML) for predicting buildings energy demand right at the design stage. This feasibility, if proven, would help to avoid the construction of inefficient buildings. This paper uses dataset from 7559 buildings, and estimates their energy consumption using nine ML models. Results show that deep neural network (DNN) is the most efficient ML model with MAE, MSD and RMSE of 0.93, 1.12 and 1.06 respectively achieved in less than 7 s despite the huge data size. Its is also the highest (0.96) which means that the DNN approach manages to explain 96% of the energy consumption in buildings and only 4% remains unexplained certainly due to the limitation of independent variables. Also, this result is not affected by building clusters nor by data from a particular climate zone. As an innovation, this study proposes a model that professionals could use in the design phase of a construction project. This model will allow them to take into account all crucial aspects of the design of an energy efficient building. The model will then serve as a decision-making tool to control and optimise the project and to anticipate energy consumption even before the building is constructed.
... The use of Energy Plus [26], DOE-2 [27], and eQuest [28] systems for examining and predicting energy use have nonetheless been examined and produced relatively good results [29]. The use of Machine Learning (ML) algorithms have been used in several studies [30]; [31]; [32]; [33]; [34], since it is recognized as the most contemporary and best method for prediction [35]; [36]; [37]. The low time consumption and high performance of ML algorithms have led to a broader acceptance [38]. ...
... All-water load in the building. According to most studies, ACB systems used in buildings for cooling are more energy efficient than conventional VAV systems [30]. This is since primary air is mostly responsible for ventilating the building, while chilled water is primarily responsible for cooling the most sensible load [21]. ...
The energy performance of the building was estimated using various data mining techniques, in order to predict its consumption in an efficient, faster, and accurate way, these techniques which are machine learning algorithms, including support vector machine (SVM), artificial neural network (ANN), Narrow Neural Network, Optimizable SVM, Rational Quadratic GPR, etc. The prediction models were constructed using 2500 experimental datasets from the literature with 5 input parameters and one output parameter (Electricity consumption). The Rational Quadratic GPR model was the most suitable technique for predicting electricity consumption based on the comparison results. Its Root Mean Square Error (RMSE) was 297.01kW. which is the lowest among other techniques and with a mean absolute percentage error (MAE) of `below 2% and an R-Squared rate of 0.99. This study confirms the suggested approach's efficiency, significance, and accuracy when predicting electricity consumption at the building design stage. The analytical outcomes sustain the feasibility of using the suggested strategies to facilitate the early designs of energy-conserving buildings.
... According to some recent research [1], buildings utilize roughly forty percent of world's energy, twenty-five percent of water, and forty percent of global resources. Furthermore, this study also states that residential and commercial buildings produce almost one-third of the global greenhouse gas emissions. ...
The concepts of "Collaborative Virtual Power Plant Ecosystem" (CVPP-E) and "Cognitive Household Digital Twin" (CHDT) have been introduced to support sustainability and effective energy performance at the level of households within Renewable Energy Communities (RECs). In this context, a CVPP-E can be viewed as a digital twin representation of a REC. Likewise, CHDTs can also be represented by digital twins of each member household of the CVPP-E. Moreover, the CHDTs may be implemented as software agents with some level of cognitive intelligence, which allows them to perform as autonomous decision-making entities that can assume some "delegated autonomy" on behalf of the owners of the physical households. Their decisions are expected to lead to the promotion of collaborative behaviours that will increase the ecosystem's resilience and sustainability. This work examines the scenario of a CVPP-E with prosumer CHDTs that may directly consume energy from a solar energy generation system installed in the household, from a local battery storage system, from a community battery storage, or from the power grid. The scenario also considers consumer CHDTs whose sole choices for energy consumption are the community storage and the grid. The CHDTs given some "delegation" to make decisions on energy consumption. This "delegated autonomy" is given by their physical twin (owner), which may indicate the owner's contribution to a common objective, hence enabling a collaborative approach towards sustainable energy consumption. The outcomes of the performed analysis, obtained through a multi-method simulation methodology, show the feasibility and potential utility of having CHDTs with complementary decision-making capabilities. The adequacy of the adopted modelling technique is also demonstrated.
... In a recent study [1], it is claimed that buildings consume nearly 40% of global energy, 25% of global water, and 40% of global resources. Residential and commercial buildings, according to this study, were argued to emit about one-third of global greenhouse gases. ...
The notions of Collaborative Virtual Power Plant Ecosystem (CVPP-E) and Cognitive Household Digital Twin (CHDT) are related and complementary concepts that were proposed to help contribute to the efficient organization and management of households within Renewable Energy Communities (RECs). A CVPP-E can be seen as a digital replica of a REC as a whole. Similarly, a CHDT is a digital twin representation of each constituent household of a CVPP-E, focusing on delegated autonomy in decision-making capabilities. CHDTs can be modelled as software agents that possess some intelligent or cognitive attributes that enable them to play complementary roles as autonomous decision-making entities. Their decisions are expected to promote collaborative behaviours that can help increase the survivability and sustainability of the energy ecosystem. In this study, we consider a CVPP-E with prosumer CHDTs who have the option of consuming energy from multiple sources, such as directly from a locally installed photovoltaic system, a local energy storage system, and a community storage, or from the grid. We also consider consumer CHDTs whose options are limited to the grid and community storage only. For all CHDTs, the decision to select/use a particular energy source is based on some "delegated autonomy" assigned to it by the corresponding Physical Twin (PT), which could represent the PT's contribution towards a common goal, thus, enabling sustainable consumption in the ecosystem. Using a multi-method simulation technique, the study's results show that the idea of these proposed CHDTs having complementary decision-making skills is possible and could be useful.
... Against the background of increasing global population and rapid economic development, the energy demand for buildings has increased significantly [1]. According to the World Watch Institute, public buildings account for one-third of global energy consumption and nearly 40% of carbon dioxide emissions each year [2]. ...
Short-term building energy consumption forecasting is vital for energy conservation and emission reduction. However, it is challenging to achieve accurate short-term forecasting of building energy consumption due to its nonlinear and non-stationary characteristics. This paper proposes a novel hybrid short-term building energy consumption forecasting model, SSA-CNNBiGRU, which is the integration of SSA (singular spectrum analysis), a CNN (convolutional neural network), and a BiGRU (bidirectional gated recurrent unit) neural network. In the proposed SSA-CNNBiGRU model, SSA is used to decompose trend and periodic components from the original building energy consumption data to reconstruct subsequences, the CNN is used to extract deep characteristic information from each subsequence, and the BiGRU network is used to model the dynamic features extracted by the CNN for time series forecasting. The subsequence forecasting results are superimposed to obtain the predicted building energy consumption results. Real-world electricity and natural gas consumption datasets of office buildings in the UK were studied, and the multi-step ahead forecasting was carried out under three different scenarios. The simulation results indicate that the proposed model can improve building energy consumption forecasting accuracy and stability.
... However, these tools are considered inefficient due to the large number of required parameters and its time consumption (Pham et al., 2020). Researchers speculate that such an energy prediction model with high accuracy will save around 30% of total energy use in buildings (Aversa et al., 2016;Colmenar-Santos et al., 2013). This indicates why there have been various studies since the 1990s, that have developed diverse models for predicting building energy consumption (Ahmad et al., 2017;Castelli et al., 2015;Chokwitthaya et al., 2020;Dong et al., 2005;Kim & Suh, 2021;Li et al., 2018;Neto & Fiorelli, 2008;Tardioli et al., 2015;Zhong et al., 2019). ...
... Despite the good properties of data driven method using ML algorithms, past studies (e.g. Aversa et al., 2016;Li et al., 2018;Pham et al., 2020;Robinson et al., 2017) have not been extensively developed for design stage analysis which is where the potential lies for around 30% energy savings (Aversa et al., 2016;Colmenar-Santos et al., 2013). However, data driven methods performance depends on the ML algorithm used for model development (Pham et al., 2020;Runge & Zmeureanu, 2019). ...
... Despite the good properties of data driven method using ML algorithms, past studies (e.g. Aversa et al., 2016;Li et al., 2018;Pham et al., 2020;Robinson et al., 2017) have not been extensively developed for design stage analysis which is where the potential lies for around 30% energy savings (Aversa et al., 2016;Colmenar-Santos et al., 2013). However, data driven methods performance depends on the ML algorithm used for model development (Pham et al., 2020;Runge & Zmeureanu, 2019). ...
The substantial amount of energy consumption in buildings and the associated adverse effects prompts the importance of understanding building energy efficiency. Developing an energy prediction model with high accuracy is considered one of the most effective approach to understanding building energy efficiency. Therefore, various studies have developed diverse models for predicting building energy consumption focused on the current building stock. However, to ensure future buildings are constructed to be more energy efficient, it is essential to consider energy efficiency at the design stage. Machine Learning (ML) algorithms are considered the most contemporary and best method for prediction, and these algorithms (such as Support Vector Machine (SVM) and Decision Tree (DT), among others) have gained much attention in the field of energy prediction. However, no study has explored the application of hyper parameter tuning and feature selection methods in developing a design stage Machine Learning (ML) energy predictive model. In this research, nine machine learning classification-based algorithms were compared for energy performance assessment at the design stage of residential buildings. Additionally, feature selection and hyper parameter tunning were implemented. The result shows that it is possible to develop a high performing ML model for building energy use prediction at the design stage. Furthermore, Gradient Boosting (GB) outperformed the other models with an accuracy of 0.67 for predicting building energy performance.
... The high proportion of energy consumed by buildings leads to major environmental problems causing climate change, air pollution, thermal pollution, among others, which deploys a severe impact on the existence of mankind [2]. In the past decades, the demand for energy in buildings has considerably amplified due to the population increase and prompt urbanization [3]. ...
... In response, data-driven models are based solely on mathematical models and measurements. This model utilizes machine learning algorithms for building energy estimation and it has been proposed in several studies because it does not require a sizeable number detailed inputs about the building [1,3,[10][11][12]. This method is trained on large detailed hourly or sub-hourly readings dataset retrieved from the building management systems and smart meters [13]. ...
... Researchers suggest that the availability of a building energy system with accurate forecasting, is projected to save between 10 and 30% of total energy consumptions in buildings [3,18]. Thus, the continuous effort to enhance building energy prediction is essential for more efficient buildings. ...
The high proportion of energy consumed in buildings has engendered the manifestation of many environmental problems which deploy adverse impacts on the existence of mankind. The prediction of building energy use is essentially proclaimed to be a method for energy conservation and improved decision-making towards decreasing energy usage. Also, the construction of energy efficient buildings will aid the reduction of total energy consumed in newly constructed buildings. Machine Learning (ML) method is recognised as the best suited approach for producing desired outcomes in prediction task. Hence, in several studies, ML has been applied in the field of energy consumption of operational building. However, there are not many studies investigating the suitability of ML methods for forecasting the potential building energy consumption at the early design phase to reduce the construction of more energy inefficient buildings. To address this gap, this paper presents the utili- zation of several machine learning techniques namely Artificial Neural Network (ANN), Gradient Boosting (GB), Deep Neural Network (DNN), Random Forest (RF), Stacking, K Nearest Neighbour (KNN), Support Vector Ma- chine (SVM), Decision tree (DT) and Linear Regression (LR) for predicting annual building energy consumption using a large dataset of residential buildings. This study also examines the effect of the building clusters on the model performance. The novelty of this paper is to develop a model that enables designers input key features of a building design and forecast the annual average energy consumption at the early stages of development. This result reveals DNN as the most efficient predictive model for energy use at the early design phase and this presents a motivation for building designers to utilize it before construction to make informed decision, manage and optimize design.
... However, the are no known exploration towards predicting energy performance based on the energy ratings. One ML recurrent model is called the Support Vector Machine (SVM), it has also been introduced by a number of researchers in this field and recognized due to its generation of good result in small dataset (Li et al., 2009;Qiong Li, Peng Ren, & Qinglin Meng, 2010;Aversa et al., 2016). It is employed for classification which is also referred to as Support Vector Classifier (SVC). ...
... The training of a stable model that excels in all aspects is the main goal of Machine learning . Support Vector Regression (SVR) is utilised in predicting building electricity consumption and cooling load for Heating, ventilation, and air conditioning(HVAC) system (Niu, Wang & Wu, 2010;Aversa et al., 2016). Dong et al. also implemented data driven method using customary machine learning algorithms namely Artificial Neural Network (ANN) and Support Vector regression (SVR) and hybrid techniques such as Least-square support vector machine (LS-SVM), Gaussian process regression (GPR) and Gaussian Mixture Model (GMM) for forecasting future electricity consumption and further established that the hybrid modelling approach performs relatively better for hourly energy predictions (Dong et al., 2016). ...
There are already countless articles on strategies to limit human exposure to particulate matter10 (PM10) pollution because of their disastrous impact on the environment and people's well-being in the United Kingdom (UK) and around the globe. Strategies such as imposing sanctions on places with higher levels of exposure, dissuading non-environmentally friendly vehicles, motivating bicycles for transportation, and encouraging the use of eco-friendly fuels in industries. All these methods are viable options but will take longer to implement. For this, efficient PM10 predictive machine learning is needed with the most impactful features/data identified. The predictive model will offer more strategic avoidance techniques to this lethal air pollutant, in addition to all other current efforts. However, the diversity of the existing data is a challenge. This paper solves this by (1) Bringing together numerous data sources into an Amazon web service big data platform and (2) Investigating which exact feature contributes best to building a high-performance PM10 machine learning predictive model. Examples of such data sources in this research include traffic information, pollution concentration information, geographical/built environment information, and meteorological information. Furthermore, this paper applied random forest in selecting the most impactful features due to its better performance over the decision tree Feature selection and XGBoost feature selection method. As part of the discovery from this research work, it is now clearly discovered that the height of buildings in a geographical area has a role in the dispersion of PM10.
