Energy Consumption Information Research Articles

WITHDRAWN: Visual System Development for Construction Project Management by Using Machine Learning Algorithm

Building management involves multiple data sources related to the whole building, so the visualization system can display relevant data information intuitively and improve the overall management level. Based on this, with the help of machine learning algorithm, this paper designs a visualization system of building management, which effectively improves the efficiency of building management. Firstly, this paper uses graph neural network algorithm to extract and transform the data of buildings. Through the continuous iterative process of summing the hidden vectors of adjacent nodes, more information about the building drawing is obtained, and the loss function of graph neural network is defined. In the early stage of building management, especially in the management of new buildings, there are few data available in the system model. Therefore, this paper adopts deep learning algorithm, which can effectively realize the feature analysis and data domain mapping of the original data by generating confrontation network. Finally, a data set with similar distribution features is generated to make up for the shortage of the original data. In the visualization research of construction project management, the analysis of building energy consumption is one of the main functions. Because of the high complexity of building energy consumption data and the variety of data, the recognition accuracy of general machine learning algorithms is low, visualization system is feasible in the construction project management, and more intuitively shows the building energy consumption and other related information, thereby assisting the building managers to improve the safety of the building system.

Data-Driven Based Prediction of the Energy Consumption of Residential Buildings in Oshawa

Buildings consume about 40% of the global energy. Building energy consumption is affected by multiple factors, including building physical properties, performance of the mechanical system, and occupants’ activities. The prediction of building energy consumption is very complicated in actual practice. Accurate and fast prediction of the building energy consumption is very important in building design optimization and sustainable energy development. This paper evaluates 24 energy consumption models for 83 houses in Oshawa, Canada. The energy consumption, social and demographic information of the occupants, and the physical properties of the houses were collected through smart metering, a phone survey, and an energy audit. A total of 63 variables were determined, and based on the variable importance, three groups with different numbers of variables were selected, i.e., 26, 12, and 6 for electricity consumption; and 26, 13, and 6 for gas consumption. A total of eight data-driven algorithms, namely Multiple Linear Regression (MLR), Stepwise Regression (SR), Support Vector Machine (SVM), Backpropagation Neural Network (BPNN), Radial Basis Function Neural Network (RBFN), Classification and Regression Tree (CART), Chi-Square Automatic Interaction Detector (CHAID), and Exhaustive CHAID (ECHAID), were used to develop energy prediction models. The results show that the BPNN model has the best accuracies in predicting both the annual electricity consumption and gas consumption, with mean absolute percentage errors (MAPEs) of 0.94% and 0.94% for training and validation data for electricity consumption, and 2.63% and 0.16% for gas consumption, respectively.

Spike-Based Approximate Backpropagation Algorithm of Brain-Inspired Deep SNN for Sonar Target Classification.

With the development of neuromorphic computing, more and more attention has been paid to a brain-inspired spiking neural network (SNN) because of its ultralow energy consumption and high-performance spatiotemporal information processing. Due to the discontinuity of the spiking neuronal activation function, it is still a difficult problem to train brain-inspired deep SNN directly, so SNN has not yet shown performance comparable to that of an artificial neural network. For this reason, the spike-based approximate backpropagation (SABP) algorithm and a general brain-inspired SNN framework are proposed in this paper. The combination of the two can be used for end-to-end direct training of brain-inspired deep SNN. Experiments show that compared with other spike-based methods of directly training SNN, the classification accuracy of this method is close to the best results on MNIST and CIFAR-10 datasets and achieves the best classification accuracy on sonar image target classification (SITC) of small sample datasets. Further analysis shows that compared with artificial neural networks, our brain-inspired SNN has great advantages in computational complexity and energy consumption in sonar target classification.

A novel cluster-specific analysis framework for demand-side management and net metering using smart meter data

Demand-side management (DSM) and net metering (NM) plays a critical role in managing the energy imbalance by supervising the customer behavioural patterns. The availability of fine-grained energy consumption information from the smart meter empowers the energy policy-makers to design realistic DSM and NM plans with a detailed analysis of usage patterns, dynamics, and characteristics. This paper presents a novel cluster-specific analysis framework to examine trends in residential electricity consumption to understand their potential for participating in energy efficiency, demand response, and net metering programs. In this process, the proposed framework utilises the Hierarchical clustering on energy usage patterns of residential consumers of Kolkata, India to obtain the representative profiles. Further, six different load shape characteristics are proposed to semantically analyse the clustered profiles for understanding the underlying diversity in consumption behaviour. Moreover, a novel statistical approach is incorporated into the proposed framework to evaluate the electricity consumption of every customer based on the number of peaks in a day, solar size required, and consumption during solar generation hours. The findings emphasise the critical nature of examining consumption habits in order to execute rational and productive decisions for the residential sector The scalability experiment demonstrates the effectiveness of the proposed framework. The cluster-specific analysis thus recommends power utilities in categorising the groups to participate in the demand-side management, net metering, and hybrid programs based on their respective potential. This would also help utilities in better planning for future electricity needs with an increase in renewable energy sources. • A framework for determining the potential of customers for DSM & NM is proposed. • Practical analysis of load profiles using distinct characteristics is presented. • The number of peaks per day & usage during PV generation hours are key parameters. • The implications for DSM & NM are presented for customer recruitment process.

Impacts of Building Energy Consumption Information on Energy-Saving Intention of College Students

As college students bear little energy cost of public buildings on campus, information intervention is more feasible than economic intervention to augment the energy-saving intention of college students. College students are sensitive to environmental information; thus, building energy consumption information, which reflects the energy consumption levels of the environment where students live, may be effective to promote the energy-saving intention of college students. However, the changeable cognitive structure of college students makes it difficult to predict the cognitive results of building energy consumption information. Based on social cognitive theory and theory of planned behavior, this paper reveals the impacts of building energy consumption information on energy-saving intentions of college students from the perspective of perceived value and personal norms. The conclusions are: (1) The impacts are positive and indirect; (2) the impacts are realized through the path “perceived benefit—perceived value—intention” and “perceived benefit & risk—personal norm—intention”; (3) the perceived value and personal norm independently affect energy-saving intention; and (4) the effect of perceived benefits is the most obvious. Based on the above results, we put forward a series of policy suggestions, with the aim to enhance the positive effect of building energy consumption information on college students.

Predicting Energy Consumption Using LSTM, Multi-Layer GRU and Drop-GRU Neural Networks.

With the steep rise in the development of smart grids and the current advancement in developing measuring infrastructure, short term power consumption forecasting has recently gained increasing attention. In fact, the prediction of future power loads turns out to be a key issue to avoid energy wastage and to build effective power management strategies. Furthermore, energy consumption information can be considered historical time series data that are required to extract all meaningful knowledge and then forecast the future consumption. In this work, we aim to model and to compare three different machine learning algorithms in making a time series power forecast. The proposed models are the Long Short-Term Memory (LSTM), the Gated Recurrent Unit (GRU) and the Drop-GRU. We are going to use the power consumption data as our time series dataset and make predictions accordingly. The LSTM neural network has been favored in this work to predict the future load consumption and prevent consumption peaks. To provide a comprehensive evaluation of this method, we have performed several experiments using real data power consumption in some French cities. Experimental results on various time horizons show that the LSTM model produces a better result than the GRU and the Drop-GRU forecasting methods. There are fewer prediction errors and its precision is finer. Therefore, these predictions based on the LSTM method will allow us to make decisions in advance and trigger load shedding in cases where consumption exceeds the authorized threshold. This will have a significant impact on planning the power quality and the maintenance of power equipment.

Prediction of Building Energy Consumption Based on BP Neural Network

In order to solve the energy consumption hypothesis of large buildings, the energy consumption hypothesis based on the BP neural network is proposed. First, to study the system of statistical index of building energy consumption and the system of statistical reporting of energy consumption of civil construction. In addition, to establish reliable consumer authority control to ensure the security and management of the database. Second, based on an analysis of the mechanism by which the BP neural network operates, this article optimizes it and describes the structure of the neural network, which includes the number of network layers, the number of neurons in each layer, and the number of latent neuron layers. hidden neuron layers and hidden neurons. The maximum value method is used to normalize the input sample data; finally, the learning and training process of neural network is determined. Based on BP neural network theory, the energy consumption statistics platform and prediction system are established by using Delphi 6.0. These include functional modules such as basic building information management, building energy consumption information management, building energy consumption summary, energy presampling information management, and building energy consumption forecast; the collection of building energy consumption data is mainly completed by intelligent energy consumption monitoring sensor network system. Finally, the city’s building energy consumption information system conducts construction energy audits and analyzes the potential for energy savings. The results show that the hypothesis model determined by the BP neural network algorithm has an average error of 10.6% in predicting the construction energy consumption data, which is better than Matlab’s predicted result and the mean error is 12.6%. From this, it can be seen that the BP neural network algorithm can provide better predictions of building energy consumption.

Energy Consumption Analysis of High-Speed Trains under Real Vehicle Test Conditions

The study collected statistics on the actual operation of national railway electric multiple units (EMUs) and compared the energy consumption of different EMU models at different speed levels. An important method for studying the relationship between speed and energy consumption of EMUs has been constructed based on group method of data handling to reflect how the energy consumption of different EMU models changes with speed. The energy consumption of CRH2 and CRH380A EMUs on flat and sloping lines was compared. Moreover, the start-up energy consumption of CRH2 and CRH380A EMUs was compared. The effect of the number of stops of CRH2 and CRH3 EMUs on energy consumption was analyzed. Furthermore, an idea for improving the general expression and calculation methods of traction energy consumption of EMUs was proposed. Finally, suggestions on the construction of a traction energy consumption information system were provided, and the selection of different high-speed EMU models and the reasonable determination of the operating speed were discussed.

A Novel Niche Quantum Ant Colony-Based Clustering Optimization Approach for Wireless Auto Meter Reading Network

Since the low cost and high flexibility, wireless automatic meter reading network (WAMRN) is widely used by utility companies to realize automatic collection and transmission of remote energy consumption information. Considering that WAMRN is composed of several wireless communication nodes, the lifetime of the network will be affected by factors such as the changeable deployment environment and the limited energy of nodes. Thus, a novel niche quantum ant colony-based WAMRN clustering optimization method is proposed in this paper to address the problem of how to make full use of the limited energy to extend network lifetime and improve data transmission efficiency. In the proposed approach, a clustering model of WAMRN is defined; moreover, an improved Niche Quantum Ant Colony Optimization (NQACO) is proposed to optimize the model therefore to obtain an optimal clustering scheme, which can help WAMRN reduce unnecessary energy loss to achieve the purpose of extending the lifetime of the entire network. To verify the performance of the proposed method, NQACO is compared with some popular clustering methods, i.e., GA and SA, under different scenarios. The results show that under the premise of ensuring network communication, NQACO is superior to the other two methods in reducing the total energy consumption and prolonging the network lifetime.

Adaptive modeling for Non-Intrusive Load Monitoring

Non-Intrusive Load Monitoring (NILM) is an energy-saving technology that has been widely concerned. It can estimate detailed energy consumption information from aggregated power data, eliminating the need to install sub-meters on individual appliances. In addition to the power consumption information from each appliance, traditional load monitoring algorithms often require additional information to help train the model, which incurs extra user interaction during the modeling process, limiting the wide application of NILM. In this paper, we presented a novel model named Adaptive Factorial Hidden Markov Model (Adaptive-FHMM) to characterize the transition between working states of each appliance. In the proposed model an adaptive clustering process is introduced, which could automatically determine the number of hidden states according to the power variation at different working stages. Then the working states information of each appliance is utilized to build a combined model to predict the appliance’s power consumption. Experiments are conducted on two publicly available datasets and one dataset collected from the laboratory, and the results show that the proposed model outperforms five state-of-the-art models in the metrics of energy-based F1, Mean Absolute Error(MAE), and Match Rate. Specifically, the proposed Adaptive FHMM model achieves 26.8% and 52% reduction in MAE compared to the second-best model on the real-world dataset of REDD and AMPds, respectively.

The countermeasures of urban energy risk control oriented to machine learning and data fusion

Urban energy is a very important factor in urban development. How to control its energy risk is the key to this article. This article explores the urban energy risk control countermeasures oriented to machine learning and data fusion. This paper understands the connotation and application of machine learning, and then adds data fusion technology to analyze the data, and finally designs the city’s energy risk control countermeasures through risk control. This article explores the relevant information of domestic energy consumption, and then conducts test experiments and analysis on two regions. It turns out that this strategy has the characteristics of reducing urban energy consumption and reducing urban energy risks. Through the use of machine learning and data fusion design of urban energy risk countermeasures, the extremely high risk areas in the two regions have been reduced from 11.82% and 11.80% to 5.39% and 6.12%. And the extremely low risk area increased from 45.94% and 37.65% to 66.29% and 62.12%, this fully shows that the application of machine learning and data fusion in energy risk can well support the distribution and utilization of energy.

Research on Energy Consumption Evaluation Method and Energy Saving Operation Technology of Cold Storage

There is not yet a recognized unified energy consumption assessment and grading method on cold storage. It is not conducive to cold storage operation energy-saving management. By establishing the heat balance model of the cold storage, the energy consumption composition of the cold storage is analyzed, and then the causal diagram analysis method is used to determine the influencing factors of the energy consumption of the cold storage, and the quantitative indicators to measure the energy consumption of the cold storage are proposed. Based on the classification of energy consumption assessment methods for cold storage, five typical energy consumption assessment methods for cold storage are compared and analyzed from five aspects of quantification, evaluation index, energy efficiency level, application scope and shortcomings. It is found that to establish an energy efficiency level identification evaluation standard for cold storage recognized by the public, two conditions must be met: the appropriate energy consumption assessment method considering the differentiation of cold storage; establishment of a large database of cold storage energy consumption information. Accordingly, the ways and measures for energy saving of cold storage are proposed.

Evaluation of Energy Performance of Main Administrative Office Buildings of Universities in North-Central Nigeria

The adverse effect of increasing energy demand on global climate has made buildings objects of research globally. Generally, in Nigeria, lack of building energy data and specifically energy consumption information related to building facilities in universities has been given less attention where bulk-metering has been the common practice. Consequently, energy demand of individual building remains unknown. Hence, Energy Use Index (EUI) was adopted as energy performance indicator for main administrative office buildings of federal universities in North-Central Nigeria. This study been exploratory in nature adopted a case study technique. Simple energy audit was conducted in the absence of individual monthly energy bills. The end-uses disaggregation shown that cooling load accounted for more than 40% of annual energy consumption. Also, the derived EUI of 197.85KWh/m2/yr was above benchmark for similar buildings globally. This outcome implies that the buildings are energy inefficient and need for sub-metering and regular energy audit.

Does energy efficiency affect appliance prices? Empirical analysis of air conditioners in China based on propensity score matching

With continuous increases in global eenergy consumption, environmental problems are becoming more prominent. Encouraging consumers to purchase and use energy-saving appliances can effectively reduce energy consumption. Do consumers have a different willingness to pay (WTP) or different preferences for appliance attributes when making purchasing decisions? Energy-efficiency labels provide consumers with energy-consumption information. Do such labels have an effect on appliance prices? To answer these questions, this study used the hedonic price model (HPM) to explore consumers' WTP for various attributes of air conditioners (ACs). Sales data for 1459 ACs were obtained from a major e-commerce platform in China. The results indicated that platform attributes had no significant effect on price. While the premium of energy-efficiency labeling was 12.4%, brands had a high premium—up to 59.4%. Meanwhile, propensity score matching (PSM) was used to explore the premiums of energy-efficiency labeling; PSM can solve the problem of selection bias and has advantages over traditional HPM. The results showed that there was a 19.4% premium between energy-efficiency level 1 and level 2 and a 21.5% premium between levels 1 and 3. Based on the results, management suggestions are made to further promote the development of the household appliance market and energy-efficiency labeling.

The Construction of a Smart City Energy Efficiency Management System Oriented to the Mobile Data Aggregation of the Internet of Things

Aiming at the current situation of complicated energy-consuming equipment and large energy consumption in the current enterprise, a reference model scheme of an enterprise energy efficiency management platform based on the Internet of Things is analyzed and the dynamically collected energy consumption information is analyzed using the Internet of Things technology and data mining technology. They provide decision-making support for enterprise energy efficiency management decisions and formulation of energy-saving and emission reduction plans. This article analyzes the current status of energy efficiency management in buildings and points out several pain points in energy efficiency management, including installation difficulties, high software development costs, upgrade difficulties, long debugging cycles, and closed systems, and introduces intelligent power distribution monitoring based on the Internet of Things technology to solve these difficulties. In the system, we analyze the actual value brought by energy efficiency management technology through case studies. It can collect scattered information through the Internet of Things, gather it together to form massive data, and obtain the corresponding information through data analysis and processing. The design is reasonable, the practicality is strong, the use effect is good, and it is easy to promote and use.

Non-intrusive load transient identification based on multivariate LSTM neural network and time series data augmentation

Getting the specific energy consumption information of each appliance is an effective way to reduce energy wastage and improve energy efficiency. The non-intrusive load monitoring is a promising solution to achieve this goal. In terms of the event-based non-intrusive load monitoring, the load transient identification models have attracted great attention recently. In this study, a hybrid load transient identification model based on multivariate fusion, time series data augmentation, and deep neural network computation is proposed. In the hybrid model, the multivariate LSTM neural network is utilized to extend the traditional template matching methods to the deep learning field, which is beneficial to improve the identification accuracy and the efficiency in the testing stage. A hybrid time series data augmentation framework is designed to handle the class-imbalance and insufficient sample size, which is often the case in non-intrusive load monitoring. The effectiveness of each component, as well as the whole hybrid model, are evaluated based on the BLUED dataset. The comparison results indicate that (a) multivariate LSTM neural network is effective in modeling the characters of the load transient; (b) the proposed hybrid time series data augmentation framework is effective in improving the overall performance of the multivariate LSTM neural network; (c) taking identification accuracy and the application efficiency in testing stage into consideration, the proposed hybrid model performs better than that of the state of the art Dynamic Time Warping (DTW) based models.

Research on Energy Acquisition, Monitoring and Analysis Platform of Integrated Energy System Based on NB-IOT

His paper introduces the energy acquisition and monitoring analysis platform of the integrated energy system based on NB-IOT, the system platform realizes the collection, storage, statistics and monitoring analysis of comprehensive energy consumption information such as electricity / water / gas based on NB-IOT communication technology, and provides effective data support for the promotion and construction of comprehensive energy system.

The Effect of Providing Monetary Information on Energy Savings for Household Appliances: A Field Trial in Spain

Energy labels are one of the most widely used policies in the European Union for increasing the energy efficiency of household appliances. However, their effectiveness in promoting energy-efficient purchases has sometimes been called into question. One of the reasons for this is that consumers may have difficulties in fully understanding the energy consumption information provided on labels (in kilowatt-hour per year). Some authors argue that to avoid this problem energy consumption information should be converted into monetary information. We analyse whether providing monetary information on lifetime energy savings can significantly increase purchases of energy-efficient appliances. To that end, a field experiment was carried out with small retailers in Spain. The experiment involved three types of appliances: washing machines, fridges and dishwashers. The impact of monetary information on actual purchases of appliances was tested in different ways: (i) by including a monetary label to display energy savings during the lifetime of the product; (ii) by the monetary information provided by sales staff; and (iii) by combining (i) and (ii). We find that the effectiveness of providing monetary information depends on the appliance and the specific way in which the information is provided. For washing machines, providing monetary information through a monetary label seems effective in promoting the purchase of highly energy-efficient appliances. However, for fridges, both monetary information provided by staff alone and the combination of the monetary label and information from sales staff seem to be effective in promoting purchases of A+++ fridges. Surprisingly, no effect is found for dishwashers.

The impact of social norms on cross-state energy regime changes

We present a survey study that explores two experimental analysis: first, a cross-country norms effect on petition signing, and second, a cross-state comparison, focusing on clean energy adaptation instead of fossil fuel energy. In the first study, we use energy consumption information from the US, EU, and China. Using the first study as a pilot, we redesigned the second experiment by providing energy utilization for Arizonian and New Mexican to validate our norms by comparing their states' green energy consumption to the pioneer states separately. The results of the research point out that social norms can effectively influence the participants in different angles. The attendants are more likely to sign a petition—by seven percent—in favor of clean energy act when they have been provided with additional information. This research highlights that not only social norms could be compelling individuals’ behavior, but also that they are sensitive to the types of information which are disclosed to them.

Optimization and Control Strategy Technology for User Comprehensive Energy Consumption

This paper studies the application of the exclusive energy controller for comprehensive energy consumption. Users’ various energy consumption data such as water, gas, electricity, heat, cold are collected by controller. Various energy consumption information collection and sharing of park, community, building and other types of users can be realized by using data optimization and data fusion technology. The coupling optimization model is designed and the optimization strategy is studied, so as to realize the comprehensive state perception of energy consumption equipment and intelligent optimization control of comprehensive energy consumption.