Actual Energy Usage Research Articles

Quantum Informative Analysis in Smart Power Distribution

Advancements in the Internet of Things (IoT) paradigm have greatly improved the quality of services in the electricity industry through the integration of smart energy distribution and dependable electric devices. Conspicuously, the current research introduces a method for managing electricity consumption in smart residences using IoT-Fog technology, focusing on efficient energy allocation and real-time energy needs. The study specifically examines the effectiveness of electricity grid sub-stations in distributing energy using fog computing technology. By utilizing a quantum computing-assisted approach, optimal energy distribution is achieved by calculating a novel Electricity Usage Measure (EUM) based on actual energy usage patterns of smart homes. Furthermore, the Quantumized Neural Network (QiM-NN) technique is developed to forecast the electricity distribution over grid substations. For performance assessment, 4-month data are collected using four smart houses. Comparative analysis with existing data assessment techniques illustrates the effectiveness in terms of Temporal Delay (6.33 ms), Optimization Performance (Specificity (93.00%), Sensitivity (90.86%), Precision (96.66%), Coverage (96.66 %), Reliability (93.76%), and Stability (71%).

Network structure analysis based on embodied energy of the Australian economy

Energy and economic growth are closely linked and have negative impacts on the environment. Both environmental protection and economic development are significant global focal points of concern. Australian economic growth has slowed but energy consumption has increased. The relationship between economic growth and energy consumption has changed significantly. However, existing methods for accounting energy transfers between industries overlook the role of embodied energy, making them insufficient to fully capture the actual energy usage in both domestic and international trade. This study investigates the structural changes in embodied energy in the Australian economy. The paper integrates sectors as the section nodes for a network and constructs a two-layer network model to analyze energy flows both between and within nodes. The results show that the Australian embodied energy network exhibited significant variations in efficiency and interconnectedness over time, with a trend toward shorter, more interconnected paths from 2015 to 2019, enhancing overall network efficiency. The Australian embodied energy network currently faces significant funding constraints. The findings show that the Australian economic sectors have increased energy consumption in production without contributing to economic growth due to the concentration of resources within the network.

Low-energy differential target multiplexed SCS derivative reduces pain and improves quality of life through 12 months in patients with chronic back and/or leg pain.

Energy-reducing spinal cord stimulation (SCS) approaches have the potential to impact patient experience with rechargeable and non-rechargeable SCS devices through reducing device recharge time or enhancing device longevity. This prospective, multi-center study evaluated the safety, effectiveness, and actual energy usage of differential target multiplexed (DTM) endurance therapy, a reduced energy DTM SCS derivative. Subjects who reported an overall pain visual analog score (VAS) of ≥6/10 cm and an Oswestry Disability Index score of 21-80 out of 100 at baseline with moderate to severe chronic, intractable back and/or leg pain were eligible. Evaluation visits occurred at 1, 3, 6, and 12 months post-device activation. The primary objective was to characterize change in overall pain intensity, as measured by VAS, from baseline to 3-month visit. Fifty-seven subjects enrolled at 12 US sites from November 2020 through June 2021, 35 were implanted with a rechargeable SCS device, and 27 completed the 12-month visit. Subjects experienced a 50.4% mean reduction in overall pain from baseline at the 3-month follow-up that was sustained through 12 months. Additional outcomes including changes in overall, back, and leg pain intensity, quality of life, disability, therapy satisfaction, safety, and current battery usage are shown through 12-month follow-up. The use of DTM endurance SCS therapy in this study resulted in reductions in pain relief through 12 months, demonstrating that energy-reducing stimulation patterns can provide clinical benefit. Clinically effective, reduced energy SCS derivatives have the potential to impact patient experience through either reduced recharge requirements or increased device longevity.

Performance gap analysis for Korean building energy efficiency certification

Performance gap between predicted and measured building energy use can be caused by simplifications and assumptions introduced in the building energy modeling process, uncertainties in building operation such as heating and cooling setpoint temperature, operational hours, occupant behavior, heat generated from lights and equipment, etc. In South Korea, the building energy efficiency certification system (BEEC) evaluates annual energy use intensity (EUI, kWh/m2/yr) and assigns ten certificate levels using ECO2, a EUI calculation tool developed by the Korean government that is based on ISO 52016 and DIN V 18599. Firstly, we collected information on 158 non-residential BEEC-certified buildings and their actual energy usage data. Subsequently, we analyzed the performance gap between predicted and measured EUI for 158 non-residential buildings in terms of building types, heating and cooling degree days, chiller types, gross floor area, window-wall ratio, and envelope U-value. The study reveals that the performance gap is significant, showing mean absolute error ranging from 21.3 to 417.4 kWh/m2/yr, mean biased error from −3.2 to 73.4 %, and the coefficient of variance of the root mean squared error from 57.0 to 304.9 %, respectively. It is also noteworthy that even individual building’s annual consumption during eight years (2014–2021) is annually fluctuating, indicating that even the performance gap is a moving target. This study reassures that building energy certification in the design stage should be understood as a rating, not for a prediction because of many unpredictable and stochastic behavior of building energy systems and occupants.

Adept Domestic Energy Load Profile Development Using Computational Intelligence‐Based Modelling

Most studies undertaken on energy usage in buildings have shown that energy utilization is widely influenced by occupancy presence and occupants’ activities relative to the indoor environment, which may be widely dependent on weather conditions and user behaviors. However, the core drawback that has negated the proficient estimation of energy is the modelling of occupant behavior relative to energy use. Occupants’ behavior is a complex phenomenon and has a dynamic nature influenced by numerous internal, individual, and circumstantial factors. This research proposes a computational intelligence‐based model for household electricity usage profile development as impacted by core input variables—household activities, household financial status, and occupancy presence. The incorporation of these variables and their adaptiveness is expected to address and resolve unpredictability or nonlinearity concerns, thus allowing for adept energy usage estimation. The model addresses issues unresolved in many other studies, such as occupancy determination (deduction) and the impact on energy consumption. The performance precision of this approach has been demonstrated by trend series analysis, demand analysis, and correlation analysis. Based on the performance indicators including mean absolute percentage error (MAPE), mean square error (MSE), and root mean square error (RMSE), the model has shown proficient predictive output with respect to the metered (actual) energy usage data. The proposed model, compared to actual data, showed that average MAPE values for the respective day standard, morning peak, and night peak demand period (TOUs) are 2.8%, 1.88%, and 0.31% for all income groups, respectively. The aptitude to improve on energy prediction and evaluation accuracy, especially in these periods, makes it a highly suited tool for demand‐side management, power generation, and distribution planning activity. This will translate into power system reliability, reduce operation cost (lowest cost), and reduce greenhouse emissions (environmental pollution), thereby cumulating into sustainable cities.

A novel and lean data-based method to calculate the actual HVAC zone energy consumption and cooling load in sustainable smart cities using a single temperature sensor

Sustainability and energy savings are two intertwined research aims for humanity’s long-term survival, aligned with the Paris Agreement and the Egyptian vision of 2030. The purpose of this research is to minimize the cost needed to measure the HVAC energy consumption in educational and commercial buildings to save energy for energy efficiency strategies to serve the future smart and sustainable cities. These facilities are among the most energy-consuming loads, and this research proposes a technique to determine real HVAC energy consumption and cooling load using a single-sensor method. Calculating the as-built HVAC energy usage and real cooling load, especially in complex HVAC systems like VRV, which are some of the most challenging gaps, is achieved through a revolutionary and cost-effective approach. The proposed approach computes the actual HVAC energy consumption of each specific zone in the building using data from a single temperature sensor. Furthermore, the real and instantaneous cooling load of each zone was calculated, and the results show a promising agreement between the proposed techniques and the real measured consumption of the HVAC system. This approach can be integrated into the BMS building management system to determine the actual HVAC energy usage and cooling load for each zone individually in real time, enabling significant energy reduction decisions with optimal cost efficiency. Furthermore, it can be used by the BMS system as a real-time On-Board Diagnostic of the HVAC system.

Using Real Building Energy Use Data to Explain the Energy Performance Gap of Energy-Efficient Residential Buildings: A Case Study from the Hot Summer and Cold Winter Zone in China

The International Energy Agency (IEA) emphasizes that using real building energy use data (RBEUD) to reflect the actual condition of buildings and inform policy-making is the most effective way to reduce buildings’ carbon emissions. However, based on IEA’s evaluation, regional and national building stock data are limited and lacking. Especially for China, the lack of RBEUD in buildings has limited our ability to address the energy performance gap (EPG). In this research, EPG refers to the difference between regulated energy consumption by design standards and actual energy usage. EPG makes it difficult to develop buildings that are energy-efficient. Therefore, this study aims to gather and analyze RBEUD in order to understand the role of occupants’ behavior in explaining the EPG of energy-efficient residential buildings in China. The results suggest that the actual consumption of residential buildings is less than 1/5–1/3 of the theoretical limits. The heat pump and air conditioner’s actual schedules and setpoint settings are the significant drivers that explain the EPG. In addition, the presentation of a database of 1128 households provides actual usage behavior parameters for policy-makers to improve the accuracy of building energy forecasting models.

Identifying occupancy patterns and profiles in higher education institution buildings with high occupancy density – A case study

ABSTRACT Building occupancy patterns are an important factor in considering the energy efficiency of buildings and a key input for building performance modelling. More specifically, the energy consumption associated with heating, cooling, lighting, and plug load usage depends on the number of occupants in a building. Identifying occupancy patterns and profiles in buildings is a key factor for the optimisation of building operating systems and can potentially reduce the performance gap between the planning stage and the actual energy usage. This study aims to identify the patterns and profiles of the occupants in a selected case study building in England. In this study, occupancy data were collected over 12 months at five minutes intervals. A sensor was used to obtain high accuracy occupancy data compared to previous studies that encountered uncertainties in data collection. A set of clustering analyses was carried out to identify occupancy patterns and profiles in the building. The results of this study identified three different occupancy patterns and profiles as well as four drivers that influenced the occupants in the case study building: the beginning of the academic term, the examination period, the weekday/weekends, and the vacation driver.

Reducing the Operating Energy of Buildings in Arid Climates through an Adaptive Approach

Due to its excessive energy consumption, the building sector contributes significantly to greenhouse gas (GHG) emissions. The type of thermal comfort models used to maintain the comfort of occupants has a direct influence on forecasting heating and cooling demands and plays a critical role in reducing actual energy usage in the buildings. In this research, a typical residential building was simulated to compare the heating and cooling loads in four different Jordanian climates when using an adaptive thermal model versus the constant setting of temperature limits for air-conditioning systems (19–24 °C). The air-conditioning system with constant temperature settings worked to sustain thermal comfort inside the building, resulting in a significantly increased cooling and heating load. By contrast, significant energy savings were achieved using the temperature limits of an adaptive thermal model. These energy savings equated to 1533, 6276, 3951, and 3353 kWh, which represented 29.3%, 80.5%, 48.5%, and 67.5% of the total energy used for heating and cooling for zones one, two, three, and four, respectively.

인공지능 기반 콜드체인 배송차량 에너지 소비량 예측

Purpose : This study proposes a framework for a cold-chain logistics control system, and presents a method for extracting and utilizing data collected in real-time. Besides, an AI-based data learning used to predict energy consumed by cold-chain delivery vehicles is described with a case study. Research design, data and methodology : In this paper, the energy consumption of cold-chain delivery was predicted using Long Short-Term Memory (LSTM) to enhance competitiveness and efficient operations in a cold-chain logistics environment. Data on dairy product delivery were used in a case study. In total, 539 sets of data were acquired by collecting data every five minutes from five vehicles within 2,695 minutes. Results : The LSTM model seemed to fit actual energy usage data as the epochs of the model increased. Hence, the model is expected to be more effective in predicting energy consumption at epoch settings of 1,000 or more. The validation losses for each 100, 1,000, and 10,000 epochs were 0.72802, 0.01571, and 0.00546, respectively. Conclusions : In this study, the framework of an integrated management system for smart logistics centers was proposed. In addition, a method for extracting and utilizing data collected in real-time was presented. In particular, this study contributes to maintaining temperature and enhancing energy efficiency by predicting the energy consumption of cold-chain delivery vehicles through AI-based data learning.

Better understanding on impact of microclimate information on building energy modelling performance for urban resilience

Building Energy Modelling (BEM) plays a significant role in projecting future building energy demands and predicting urban climate resilience in the context of climate change and urbanization. Accurate weather data are important components in BEM. In this study, we investigate how the BEM performance is affected by weather datasets, including 1) the typical meteorological year (TMY) data, 2) data measured at the suburban ground, and 3) three microclimate datasets, i.e., data measured at a high-rise rooftop near the site, data measured at the near-ground open space close to the site, and developed microclimate data within the urban canopy layer at the site. The new microclimate data are developed by integrating near-ground measured data and microclimate modelling results using a practical GIS model. Compared with the actual energy usage, the predictions of BEM using the developed microclimate data show the least mean bias error of 6%, while the error is 12% when TMY data are used. We further utilize this method to develop microclimate datasets and predict residential energy consumptions under the short-term coronavirus pandemic and long-term climate change scenarios. The findings provide scientific support for the decision-making in future energy planning to improve urban climate resilience.

Biomimicry in the built environment: energy-saving assessment of a novel biomimetic window system

PurposeThe purpose of this study is to examine the energy savings in the indoor environment, using strategies that adopt the characteristics of nature, called biomimetic solutions. This research designed a biomimetic window system to bring daylight into interior spaces in educational buildings where daylight cannot be reached. Specifically, this study assessed how the daylight that was achieved via a biomimetic window system would affect energy savings using an energy simulation method.Design/methodology/approachThis study explored how biomimetic methods would affect the building environment and which biomimetic method would involve the building's energy saving with daylight. The research intended to develop a novel biomimetic window system that can bring daylight to the basement floor of an existing building on a university campus to find out how much the biomimetic window system would affect the energy savings of the building. Referring to the existing building's layout and structure, energy simulation models were developed, and the energy consumptions were estimated.FindingsSimulation models proved that the biomimetic window system has sufficient performance to bring more daylight to the basement floor of the building. Furthermore, it was confirmed that the use of the biomimetic window system for the building could reduce energy usage compared to the actual energy usage of the current building without biomimetic windows.Research limitations/implicationsFirst, this study was adopted as a computer-designed simulation method instead of using a real-world system. Although this study designed the biomimetic window system based on previous studies, it should be considered the possibility of other problems when the system is actually built in. Second, it is necessary to predict how much an initial budget is required when the system is built. It means that this study did not calculate the lifecycle cost of the biomimetic window system. It will also be necessary to compare energy consumption to the required initial budget. Lastly, this study was simulated based on weather data in cold regions, and it did not compare/analyze different climate regions. Different results may be predicted if the biomimetic window system is built in different climatic regions.Originality/valueThis research showed new practical ways to capture and transmit solar heat and light using a biomimetic solution. Furthermore, using the proposed novel biomimetic window system, the amount of energy reduction can be calculated, and this method could be applied in the interior non-window spaces of academic and related types of buildings.

Oversized Electrical Appliance Impacts on Condominium Energy Efficiency and Cost-Effectiveness Management: Experts’ Perspectives

A direct use approach incorporating a cost approach assumed that replacing oversized electrical appliances with those better fit to actual energy consumption can reduce energy consumption, optimizing capacities of the new appliances to the maximum while reducing electricity costs. This study aimed to verify the assumption that the size of appliances has impacts on energy consumption and cost effectiveness. A mixed-method approach included these instruments for data elicitations (i.e., a questionnaire, data records of 485 transformers, two assessments of condominium technical caretakers, and two in-depth interviews of electrical engineering experts). The findings revealed that most condominiums installed electric appliances that are too large for their actual energy usage, which lies between 5.4% and 7.1% of the capacity. This study therefore proposed a total cost reduction of 54% by downsizing these appliances (i.e., MV Switchgear 2 sets, dry type transformer 2 sets 80,000, LV Cable 10 m. (XLPE), main distribution board, Busduct (MDB-DB), generator (20% of Tr.), and generator installation). Even though this analysis is limited to Bangkok, Thailand, this case may contribute decision-making on electrical appliance selection at early stage of investment or to downsize the currently installed appliances for the more energy efficient and cost-effective management of condominiums around the world.

Building envelopes toward energy‐efficient buildings: A balanced multi‐approach decision making

The worldwide environmentally friendly trend has focused the last decade on emphasizing the value of energy conservation and reducing the carbon footprint in buildings, achieving zero energy buildings. Presently, viable building techniques, in developing countries, are insufficient to achieve zero energy buildings. Thus, authorities should implement policies mandating new developments and renovations to establish “energy-efficient buildings”; nevertheless, design solutions should be properly evaluated and assessed preceding execution. The conservation of energy without jeopardizing human comfortability is a huge challenge for any designer. Occupants are less interested in making a major investment to save some expenses over the next two decades, especially nowadays that energy is still affordable. Therefore, improved indoor environmental conditions are perhaps another important parameter toward energy-efficient buildings. Through dynamic simulations, this study examines the energy efficiency and thermal comfort achieved by integrating retrofitting strategies in an institutional building in three different American Society of Heating, Refrigerating and Air-Conditioning Engineers (ASHRAE) hot climate zones represented by three cities of Egypt (Aswan, Cairo, and Alexandria). The built-up baseline model is validated using actual energy usage data. The validated baseline model is then subjected to local sensitivity analysis to determine the driving parameters influencing the building's energy demand. The study at hand focuses on a broader perspective on sustainability. With a multiapproach decision-making methodology based on the most recent measures, the study highlights the outcomes through an environmental–economic assessment and indoor thermal comfort depending on experts' weighting, responses, and recommendations. The outcomes postulate that the implementation of reflective paints solutions would achieve the highest percentages of whole-building energy savings with 21%, 19%, and 17% for Aswan, Cairo, and Alexandria, respectively, improving indoor thermal comfort levels.

Verification of Energy Usage Based on Standard Building Model Development of Low-Rise Residential Buildings in South Korea

The energy consumption of low-rise residential buildings in South Korea exceeds the targets set in national policies and the standards of other countries. Moreover, there are insufficient policies in place to improve the energy performance of existing low-rise residential buildings and no means to investigate the current status. A standard model enables cost-effective and fast load forecasting and can also be used to establish long-term policies through evaluation of energy saving in buildings before and after the application of energy policies. This study developed a standard model for predicting energy consumption by reflecting the characteristics of low-rise residential buildings in Korea. The standard model was developed based on reliable related standards, national statistical data, and national reports, and the energy variables applied were validated through a sensitivity analysis. Surveys and field measurements were conducted to investigate the energy usage of 70 households in low-rise residential buildings in Korea, and the developed model was validated through comparison with the actual energy usage data. Consequently, the total energy consumption error rate was 12.67% (R2 value: 0.8164), with a significance level higher than 80%, which indicated that the developed model was highly efficient and reliable.

Improvement Effect of Green Remodeling and Building Value Assessment Criteria for Aging Public Buildings

The Green Remodeling Project under South Korea’s Green New Deal policy is a government-led project intended to strengthen the performance sector directly correlated with energy performance among various elements of improvement applicable to building remodeling by replacing insulation materials, introducing new and renewable energy, introducing high-efficiency equipment, etc., with public buildings taking the lead in green remodeling in order to induce energy efficiency enhancement in private buildings. However, there is an ongoing policy that involves the application of a fragmentary value judgment criterion, i.e., whether to apply technical elements confined to the enhancement of the energy performance of target buildings and the prediction of improvement effects according thereto, thus resulting in the phenomenon of another important value criterion for green remodeling, i.e., the enhancement of the occupant (user) comfort performance of target buildings as one of its purposes, being neglected instead. In order to accurately grasp the current status of these problems and to promote ‘expansion of the value judgment criteria for green remodeling’ as an alternative, this study collected energy usage data of buildings actually used by public institutions and then conducted a total analysis. After that, the characteristics of energy usage were analyzed for each of the groups of buildings classified by year of completion, thereby carrying out an analysis of the correlation between the non-architectural elements affecting the actual energy usage and the actual energy usage data. The correlation between the improvement performance of each technical element and the actual improvement effect was also analyzed, thereby ascertaining the relationship between the direction of major policy strategies and the actual energy usage. As a result of the relationship analysis, it was confirmed that the actual energy usage is more affected by the operating conditions of the relevant building than the application of individual strategic elements such as the performance of the envelope insulation and the performance of the high-efficiency system. In addition, it was also confirmed that the usage of public buildings does not increase in proportion to their aging. The primary goal of reducing energy usage in target buildings can be achieved if public sector (government)-led green remodeling is pushed ahead with in accordance with biased value judgment criteria, just as in the case of a campaign to refrain from operating cooling facilities in aging public buildings. However, it was possible to grasp through the progress of this study that the remodeling may also result in the deterioration of environmental comfort and stability, such as the numerical value of the indoor thermal environment. The results of this study have the significance of providing basic data for pushing ahead with a green remodeling policy in which the value judgment criteria for aging existing public buildings are more expanded, and it is necessary to continue research in such a direction that the quantitative purpose of green remodeling, which is to reduce energy usage in aging public buildings, and its qualitative purpose, which is to enhance their environmental performance for occupants’ comfort, can be mutually balanced and secured at the same time.

Assessing the cost of the Hazard-Decision simplification in multistage stochastic hydrothermal scheduling

Hydropower is one of the world’s primary renewable energy sources whose usage has profound economic, environmental, and social impacts. We focus on the dispatch of generating units and the storage policy of hydro resources. In this context, an accurate assessment of the water opportunity-cost is crucial for driving the sustainable use of this scarce resource. Nevertheless, traditional computational tools use stochastic dual dynamic programming under the Hazard-Decision (HD) modeling simplification, where dispatch decisions are determined assuming perfect information about the current inflows. In practice, however, some dispatch decisions are made before water inflows are observed, i.e., under a Decision-Hazard (DH) scheme. This inconsistency generates an optimistic assessment of the opportunity cost of the water, inducing a sub-optimal use of energy resources. Thus, our objectives are: (i) to raise awareness of the HD issue bridging research and implementation with a clear recommendation to system operators and regulators; (ii) to incorporate the DH scheme into the long-term hydrothermal scheduling problem; (iii) to assess the economic impacts and other market distortions due to the actual energy usage policy based on the HD simplification. For a representative case-study with realistic data from the Brazilian power system, results show that the HD simplification introduces a regret cost of 12%. Furthermore, we show that incorporating the DH scheme into the hydrothermal planning model, the energy supply cost can be reduced up to 5.3%. We also show that spot-price distortions and expensive thermal generation could be mitigated in the DH scheme.

Forecasting the Energy Consumption of an Actual Air Handling Unit and Absorption Chiller Using ANN Models

Air conditioning in buildings accounts for 60% of the total energy consumption. Therefore, accurate predictions of energy consumption are needed to properly manage the energy consumption of buildings. For this purpose, many studies have been conducted recently on the prediction of energy consumption of buildings using machine learning techniques. The energy consumption of the air handling unit (AHU) and absorption chiller in an actual building’s air conditioning system is predicted in this paper using prediction models that are based on artificial neural networks (ANNs), which simply and accurately allow us to forecast energy consumption with limited variables. Using these ANN models, the energy usage of the AHU and chiller could be predicted by collecting a month’s worth of driving data during the summer cooling period. After the forecast models had been verified, the AHU prediction model showed performance in the ranges of 13.27% to 15.25% and 19.42% to 19.53% for the training period and testing period, respectively, and the mean bias error (MBE) ranges were 4.03% to 4.97% and 3.48% to 4.39% for the training period and testing period, respectively. The chiller prediction model satisfied the energy consumption forecast performance criteria presented by American Society of Heating, Refrigerating and Air-Conditioning Engineers (ASHRAE) guideline 14 (the measurement of energy and demand savings), with a performance of 24.64~25.58% and 7.12~29.39% in the training period and testing period, respectively, and MBE ranges of 2.59~3.40% and 1.35~2.87% in the training period and testing period, respectively. When the training period and testing period were combined for the AHU data, the actual energy usage forecast showed a lower error rate range of 0.22% to 1.11% for the training period and 0.17% to 2.44% for the testing period. For the chiller data, the error rate range was 0.22% to 2.12% for the entire training period, but was somewhat higher at 11.67% to 15.18% for the testing period. The study found that, even if the performance criteria were met, high accuracy results were not obtained, which was due to the poor data set quality. Although the forecast model based on artificial neural network can achieve relatively high-accuracy results with sufficient amounts of data, it is believed that this will require a thorough verification of the data used, as well as improvements in the predictive model to avoid overfitting and underfitting, to achieve such good results.

Machine learning approaches for estimating building energy consumption

Using building data and corresponding weather conditions provided by ASHRAE, a statistical method that carefully measures features and applies both linear regression and gradient boosting machine models to predict and analyse building energy consumption was developed. Comparison of the predicted and actual energy usage indicates our model can predict energy consumption within an acceptable error range. Such statistical model has the potential to be widely used to monitor energy consumption and measure energy savings for various kinds of buildings in the future. If additional data is available, this method will be more widely applicable to other sectors such as industrial facilities.

Prediction of energy consumption in hotel buildings via support vector machines

This paper studies and analyzes the energy consumption of hotel buildings by establishing a support vector machine energy consumption prediction model. The support vector machine model takes the weather parameters and operating parameters of the hotel air-conditioning system as input variables, and determines the critical value of the input parameters by determining the normal-distribution interval, so as to avoid the influence of the outliers on the model prediction stability. The RBF kernel function is selected as the kernel function of the support vector machine, and the accuracy of the model prediction is improved by optimizing the kernel parameters. The MSE value of the final model prediction was 2.22 % and R2 was 0.94. By predicting the results, you can visually assess the actual energy usage of the hotel and suggest timely improvements to the hotel's operations to reduce the hotel's energy consumption.