A hybrid agent⁃based machine learning method for human⁃centred energy consumption prediction

Occupant behaviour has significant impacts on the performance of machine learning algorithms when predicting building energy consumption.Due to a variety of reasons(e.g.,underperforming building energy management systems or restrictions due to privacy policies),the availability of occupational data has long been an obstacle that hinders the performance of machine learning algorithms in predicting building energy consumption.Therefore,this study proposed an agent⁃based machine learning model whereby agent⁃based modelling was employed to generate simulated occupational data as input features for machine learning algorithms for building energy consumption prediction.Boruta feature selection was also introduced in this study to select all relevant features.The results indicated that the performances of machine learning algorithms in predicting building energy consumption were significantly improved when using simulated occupational data,with even greater improvements after conducting Boruta feature selection.

Energy Consumption Prediction of a CNC Machining Process With Incomplete Data

Energy consumption prediction of a CNC machining process is important for energy efficiency optimization strategies.To improve the generalization abilities,more and more parameters are acquired for energy prediction modeling.While the data collected from workshops may be incomplete because of misoperation,unstable network connections,and frequent transfers,etc.This work proposes a framework for energy modeling based on incomplete data to address this issue.First,some necessary preliminary operations are used for incomplete data sets.Then,missing values are estimated to generate a new complete data set based on generative adversarial imputation nets(GAIN).Next,the gene expression programming(GEP)algorithm is utilized to train the energy model based on the generated data sets.Finally,we test the predictive accuracy of the obtained model.Computational experiments are designed to investigate the performance of the proposed framework with different rates of missing data.Experimental results demonstrate that even when the missing data rate increases to 30%,the proposed framework can still make efficient predictions,with the corresponding RMSE and MAE 0.903 k J and 0.739 k J,respectively.

Energy consumption prediction model of typical buildings in hot summer and cold winter zone of China

To overcome the shortcomings of the energyconsumption prediction models in the application during thedesign stage, a quick prediction model for energy consumptionis proposed based on the decoupling method. Taking typicalresidential and office buildings in hot summer and cold winterzones as research objects, the influence factors on buildingenergy consumption are classified into intrinsic factors andoperational factors on the basis of the heat transfer principle.Then, using the intrinsic factors as the fundamental variablesand operational factors as the modified variables, the quickprediction model for the buildings in typical cold and hot zonesis proposed based on the decoupling method and the accuracyof the proposed model is verified. The results show thatcompared to the simulation results of EnergyPlus, the relativeerror of the prediction model is less than 1.5% ; comparedwith the real operating data of the building, the relative erroris 13.14% in 2011 and 8.56% in 2012 due to the fact that thecoincidence factor becomes larger than the design value about16% in 2011 and 13% in 2012. The finding reveals that theproposed model has the advantages of rapid calculationcompared with EnergyPlus and Design Builder when predictingbuilding energy consumption in building designs. The energyconsumption prediction model is of great practical value inoptimal operation and building designs.

Research on Prediction Methods of Energy Consumption Data

This paper analyzes the energy consumption situation in Beijing,based on the comparison of common energy consumption prediction methods.Here we use multiple linear regression analysis,grey prediction,BP neural net-work prediction,grey BP neural network prediction combined method,LSTM long-term and short-term memory network model prediction method.Firstly,before constructing the model,the whole model is explained theoretically.The advantages and disadvantages of each model are analyzed before the modeling,and the corresponding advantages and disadvantages of these models are pointed out.Finally,these models are used to construct the Beijing energy forecasting model,and some years are selected as test samples to test the prediction accuracy.Finally,all models were used to predict the development trend of Beijing's total energy consumption from 2018 to 2019,and the relevant energy-saving opinions were given.

Simplified prediction model for lighting energy consumption in office building scheme design

At the scheme design stage,the potential of daylighting is significant due to the saving for electric lighting use. There are few simple tools for architects to optimize the daylighting design. Therefore,it is useful to develop a design guideline related to the evaluation of lighting energy saving potential and sunlight design strategies. This paper analyzes the impacts of different artificial lighting control methods and design parameters on daylighting. A direct correlation between lighting energy consumption and parameters such as orientations,window to wall ratio (WWR) and perimeter depth is established. A simplified prediction model is proposed to estimate lighting energy consumption with the given perimeter depth,WWR,and window transparency. Validation of the model is carried out compared with detailed lighting simulation software for an office building. After the variation analysis for these parameters,design advises for the daylighting design at scheme design phase are summarized.

Generating Synthetic Data to Reduce Prediction Error of Energy Consumption

Renewable and nonrenewable energy sources are widely incorporated for solar and wind energy that produces electricity without increasing carbon dioxide emissions.Energy industries worldwide are trying hard to predict future energy consumption that could eliminate over or under contracting energy resources and unnecessary financing.Machine learning techniques for predicting energy are the trending solution to overcome the challenges faced by energy companies.The basic need for machine learning algorithms to be trained for accurate prediction requires a considerable amount of data.Another critical factor is balancing the data for enhanced prediction.Data Augmentation is a technique used for increasing the data available for training.Synthetic data are the generation of new data which can be trained to improve the accuracy of prediction models.In this paper,we propose a model that takes time series energy consumption data as input,pre-processes the data,and then uses multiple augmentation techniques and generative adversarial networks to generate synthetic data which when combined with the original data,reduces energy consumption prediction error.We propose TGAN-skip-Improved-WGAN-GP to generate synthetic energy consumption time series tabular data.We modify TGANwith skip connections,then improveWGANGPby defining a consistency term,and finally use the architecture of improved WGAN-GP for training TGAN-skip.We used various evaluation metrics and visual representation to compare the performance of our proposed model.We also measured prediction accuracy along with mean and maximum error generated while predicting with different variations of augmented and synthetic data with original data.The mode collapse problemcould be handled by TGAN-skip-Improved-WGAN-GP model and it also converged faster than existing GAN models for synthetic data generation.The experiment result shows that our proposed technique of combining synthetic data with original data could significantly reduce the prediction error rate and increase the prediction accuracy of energy consumption.

Multi-Time Scale Optimal Scheduling of a Photovoltaic Energy Storage Building System Based on Model Predictive Control

Building emission reduction is an important way to achieve China’s carbon peaking and carbon neutrality goals.Aiming at the problem of low carbon economic operation of a photovoltaic energy storage building system,a multi-time scale optimal scheduling strategy based on model predictive control(MPC)is proposed under the consideration of load optimization.First,load optimization is achieved by controlling the charging time of electric vehicles as well as adjusting the air conditioning operation temperature,and the photovoltaic energy storage building system model is constructed to propose a day-ahead scheduling strategy with the lowest daily operation cost.Second,considering inter-day to intra-day source-load prediction error,an intraday rolling optimal scheduling strategy based on MPC is proposed that dynamically corrects the day-ahead dispatch results to stabilize system power fluctuations and promote photovoltaic consumption.Finally,taking an office building on a summer work day as an example,the effectiveness of the proposed scheduling strategy is verified.The results of the example show that the strategy reduces the total operating cost of the photovoltaic energy storage building system by 17.11%,improves the carbon emission reduction by 7.99%,and the photovoltaic consumption rate reaches 98.57%,improving the system’s low-carbon and economic performance.

Intelligent Energy Consumption For Smart Homes Using Fused Machine-Learning Technique

Energy is essential to practically all exercises and is imperative for the development of personal satisfaction.So,valuable energy has been in great demand for many years,especially for using smart homes and structures,as individuals quickly improve their way of life depending on current innovations.However,there is a shortage of energy,as the energy required is higher than that produced.Many new plans are being designed to meet the consumer’s energy requirements.In many regions,energy utilization in the housing area is 30%–40%.The growth of smart homes has raised the requirement for intelligence in applications such as asset management,energy-efficient automation,security,and healthcare monitoring to learn about residents’actions and forecast their future demands.To overcome the challenges of energy consumption optimization,in this study,we apply an energy management technique.Data fusion has recently attracted much energy efficiency in buildings,where numerous types of information are processed.The proposed research developed a data fusion model to predict energy consumption for accuracy and miss rate.The results of the proposed approach are compared with those of the previously published techniques and found that the prediction accuracy of the proposed method is 92%,which is higher than the previously published approaches.

Forecasting Energy Consumption Using a Novel Hybrid Dipper Throated Optimization and Stochastic Fractal Search Algorithm

The accurate prediction of energy consumption has effective role in decision making and risk management for individuals and governments.Meanwhile,the accurate prediction can be realized using the recent advances in machine learning and predictive models.This research proposes a novel approach for energy consumption forecasting based on a new optimization algorithm and a new forecasting model consisting of a set of long short-term memory(LSTM)units.The proposed optimization algorithm is used to optimize the parameters of the LSTM-based model to boost its forecasting accuracy.This optimization algorithm is based on the recently emerged dipper-throated optimization(DTO)and stochastic fractal search(SFS)algo-rithm and is referred to as dynamic DTOSFS.To prove the effectiveness and superiority of the proposed approach,five standard benchmark algorithms,namely,stochastic fractal search(SFS),dipper throated optimization(DTO),whale optimization algorithm(WOA),particle swarm optimization(PSO),and grey wolf optimization(GWO),are used to optimize the parameters of the LSTM-based model,and the results are compared with that of the proposed approach.Experimental results show that the proposed DDTOSFS+LSTM can accurately forecast the energy consumption with root mean square error RMSE of 0.00013,which is the best among the recorded results of the other methods.In addition,statistical experiments are conducted to prove the statistical difference of the proposed model.The results of these tests confirmed the expected outcomes.

Comprehensive optimized GM(1,1) model and application for short term forecasting of Chinese energy consumption and production

In order to improve prediction accuracy of the grey prediction model and forecast China energy consumption and production in a short term, this paper proposes a novel com- prehensively optimized GM（1,1） model, also named COGM（1,1）, based on the grey modeling mechanism. First, the relationship of the background value formula and its whitenization equation is analyzed and a new method optimizing background values is proposed to eliminate systemic errors in the modeling process. Second, the solving process of the new model is derived. For parameter estimation, a set of auxiliary parameters are used to change grey equation＇s form. Then, original parameters are re- stored by an equations system. After solving the whitenization equation, initial value in time response function is established by least errors criteria. Finally, a numerical case and comparison with other grey prediction models are made to testify the new model＇s effectiveness, and the computational results show that the COGM（1,1） model has a better property and achieves higher precision. The new model is used to forecast China energy con- sumption and production, and the ability of energy self-sufficiency is further analyzed. Results indicate that gaps between consump- tion and production in future are predicted to decline.

Analysis and forecast of residential building energy consumption in Chongqing on carbon emissions

Carbon emissions mainly result from energy consumption. Carbon emissions inevitably will increase to some extent with economic expansion and rising energy consumption. We introduce a gray theory of quantitative analysis of the energy consumption of residential buildings in Chongqing,China,on the impact of carbon emission factors. Three impacts are analyzed,namely per capita residential housing area,domestic water consumption and the rate of air conditioner ownership per 100 urban households. The gray prediction model established using the Chongqing carbon emission-residential building energy consumption forecast model is sufficiently accurate to achieve a measure of feasibility and applicability.

A Review of Energy-Related Cost Issues and Prediction Models in Cloud Computing Environments

With the expansion of cloud computing,optimizing the energy efficiency and cost of the cloud paradigm is considered significantly important,since it directly affects providers’revenue and customers’payment.Thus,providing prediction information of the cloud services can be very beneficial for the service providers,as they need to carefully predict their business growths and efficiently manage their resources.To optimize the use of cloud services,predictive mechanisms can be applied to improve resource utilization and reduce energy-related costs.However,such mechanisms need to be provided with energy awareness not only at the level of the Physical Machine(PM)but also at the level of the Virtual Machine(VM)in order to make improved cost decisions.Therefore,this paper presents a comprehensive literature review on the subject of energy-related cost issues and prediction models in cloud computing environments,along with an overall discussion of the closely related works.The outcomes of this research can be used and incorporated by predictive resource management techniques to make improved cost decisions assisted with energy awareness and leverage cloud resources efficiently.

Research on Calculation Models of Coal Comminution Energy Consumption

在总结粉碎功耗规律的研究进展的基础上，分析了单一粒度颗粒的粉碎功耗预测理论，介绍了粉碎功耗理论的3种著名假说体积假说、面积假说、裂缝假说及其修正计算方法，并进行了比较，描述了粉碎功耗计算的通用关系式和近年来提出的新机制，包括原生裂纹假说、突变理论及分形理论等；进而针对具有复杂粒度分布物料的粉碎功耗，将给料与产品粒度分布作为参数引入能耗计算中，获得了当粒度分布分别满足G．S分布、R—R分布、分形分布时的各种粉碎功耗理论预测结果。此外，还列出了部分常用的粉碎功耗经验关联式并进行了比较。文中提出在研究煤的粉碎功耗规律时，采用Walker计算式结合分形粒度分布或R-R分布的能耗模型及Morrell经验式是可行的。

Predicting Energy Consumption Using Stacked LSTM Snapshot Ensemble

The ability to make accurate energy predictions while considering all related energy factors allows production plants,regulatory bodies,and governments to meet energy demand and assess the effects of energy-saving initiatives.When energy consumption falls within normal parameters,it will be possible to use the developed model to predict energy consumption and develop improvements and mitigating measures for energy consumption.The objective of this model is to accurately predict energy consumption without data limitations and provide results that are easily interpretable.The proposed model is an implementation of the stacked Long Short-Term Memory(LSTM)snapshot ensemble combined with the Fast Fourier Transform(FFT)and meta-learner.Hebrail and Berard’s Individual Household Electric-Power Consumption(IHEPC)dataset incorporated with weather data are used to analyse the model’s accuracy with predicting energy consumption.The model is trained,and the results measured using Root Mean Square Error(RMSE),Mean Absolute Error(MAE),Mean Absolute Percentage Error(MAPE),and coefficient of determination(R^(2))metrics are 0.020,0.013,0.017,and 0.999,respectively.The stacked LSTM snapshot ensemble performs better than the compared models based on prediction accuracy and minimized errors.The results of this study show that prediction accuracy is high,and the model’s stability is high as well.The model shows that high levels of accuracy prove accurate predictive ability,and together with high levels of stability,the model has good interpretability,which is not typically accounted for in models.However,this study shows that it can be inferred.

Combined Prediction for Vehicle Speed with Fixed Route

Achieving accurate speed prediction provides the most critical support parameter for high-level energy management of plug-in hybrid electric vehicles.Nowadays,people often drive a vehicle on fixed routes in their daily travels and accurate speed predictions of these routes are possible with random prediction and machine learning,but the prediction accuracy still needs to be improved.The prediction accuracy of traditional prediction algorithms is difficult to further improve after reaching a certain accuracy;problems,such as over fitting,occur in the process of improving prediction accuracy.The combined prediction model proposed in this paper can abandon the transitional dependence on a single prediction.By combining the two prediction algorithms,the fusion of prediction performance is achieved,the limit of the single prediction performance is crossed,and the goal of improving vehicle speed prediction performance is achieved.In this paper,an extraction method suitable for fixed route vehicle speed is designed.The application of Markov and back propagation(BP)neural network in predictions is introduced.Three new combined prediction methods,all named Markov and BP Neural Network(MBNN)combined prediction algorithm,are proposed,which make full use of the advantages of Markov and BP neural network algorithms.Finally,the comparison among the prediction methods has been carried out.The results show that the three MBNN models have improved by about 19%,28%,and 29%compared with the Markov prediction model,which has better performance in the single prediction models.Overall,the MBNN combined prediction models can improve the prediction accuracy by 25.3%on average,which provides important support for the possible optimization of plug-in hybrid electric vehicle energy consumption.

基于机器学习的空气源热泵干燥能耗回归预测

为了降低空气源热泵干燥过程能耗,研究了空气源热泵干燥能耗特性,采用多元线性回归模型(multivariate linear regression model, MLRM)和BP神经网络(back propagation neural network, BPNN)模型来预测干燥工艺能耗。在分析干燥能耗影响特征参数的基础上,提出将干燥工艺过程进行切分处理的方法以降低数据获取难度。选取烘房设定温度、烘房设定湿度、烘房初始温度、烘房初始湿度、环境平均温度、环境平均湿度、物料质量和初始含水率8个特征参数作为模型输入,能耗和物料结束含水率作为模型输出。使用MLRM模型、BPNN模型和其他机器学习模型进行能耗预测,MLRM模型对能耗拟合的决定系数为0.739,对物料结束含水率拟合的决定系数为0.931;BPNN模型使用Sigmoid函数作为激活函数时对能耗拟合的决定系数最高,为0.828,使用Identity函数作为激活函数时对物料结束含水率拟合的决定系数最高,为0.942,拟合效果优于其他机器学习模型,能够满足实际生产需求。以复水豌豆为干燥对象设计加载物料65 kg、持续时间4 h的完整变温变湿干燥工艺进行验证试验,结果表明:试验总能耗为15.066 kW·h,MLRM模型和BPNN模型的预测总能耗分别为14.476 kW·h、15.183 kW·h,预测精度分别为96.08%、99.23%;试验结束含水率为8.541%,MLRM模型和BPNN模型的预测结束含水率分别为9.560%、8.889%,预测精度分别为88.07%、95.93%。该研究提出了一种使用MLRM模型和BPNN模型对空气源热泵干燥能耗进行分段精准预测的有效手段,对于优化干燥工艺和降低干燥能耗具有实际意义。

民居建筑室内空间热环境多点能耗精准预测

在民居建筑室内热环境多点能耗预测时,若不能有效确定热环境下室内当前状态下舒适程度,会直接影响能耗预测精度。因此,提出考虑舒适度的民居建筑室内空间热环境多点能耗预测方法。根据室内状态建立民居建筑内热环境模型,采用主元分析法获取能耗评价指标,构建热环境下室内能耗指标评价体系,并利用指标建立评价模型,从而确定室内当前热环境能耗;将确定指标作为模型输入向量,利用RBF神经网络构建室内能耗多点预测模型;通过建立的模型实现对民居建筑室内空间多点能耗的精准预测。实验结果表明,所提方法开展室内能耗多点预测时,预测精度高、效果好。

融合工况预测的燃料电池汽车里程自适应等效氢耗最小控制策略

为有效地提高插电式燃料电池汽车的经济性,实现燃料电池和动力电池的功率最优分配,考虑到行驶工况、电池荷电状态(State of charge,SOC)、等效因子与氢气消耗之间的密切联系,制定融合工况预测的里程自适应等效氢耗最小策略.通过基于误差反向传播的神经网络来实现未来短期车速的预测,分析未来车辆需求功率变化,同时借助全球定位系统规划一条通往目的地的路径,智能交通系统便可获取整个行程的交通流量信息,利用行驶里程和SOC实时动态修正等效消耗最小策略中的等效因子,实现能量管理策略的自适应性.基于MATLAB/Simulink软件,搭建整车仿真模型与传统的能量管理策略进行仿真对比验证.仿真结果表明,采用基于神经网络的工况预测算法能够较好地预测未来短期工况,其预测精度相较于马尔可夫方法提高12.5%,所提出的能量管理策略在城市道路循环工况(UDDS)下的氢气消耗比电量消耗维持(CD/CS)策略下降55.6%.硬件在环试验表明,在市郊循环工况(EUDC)下的氢气消耗比CD/CS策略下降26.8%,仿真验证结果表明了所提出的策略相比于CD/CS策略在氢气消耗方面的优越性能,并通过硬件在环实验验证了所提策略的有效性.

数模联动的多特征工件加工能耗预测方法研究

在实际切削加工过程中材料去除率是不断变化的,现有将其视为恒量的能耗建模方法难以实现能耗准确预测。为了提高切削过程能耗预测精度,提出了一种基于材料去除率的数模联动加工能耗预测方法。首先,基于切削过程刀具与工件的接触关系分析了切入、完全切入和切出阶段材料去除率变化规律,并对相应的加工能耗特性进行了分析;其次,提出了数据驱动的刀具切入,切出阶段加工能耗预测方法,以及模型驱动的完全切入阶段加工能耗预测方法,实现加工过程能耗准确预测;最后,利用实验案例验证了所提模型及方法的有效性,为今后研究能耗预测精度奠定了基础。

朴素贝叶斯下新型建筑室内空调瞬态能耗预测

新型建筑通常具有较为复杂的结构,使得室内空调系统的能耗受到如建筑朝向、室内人员活动以及设备使用情况等因素影响,导致无法精准预测空调能耗。为此,提出新型建筑室内空调瞬态能耗朴素贝叶斯预测方法。采用K均值聚类(K-means clustering,K-Means)算法将新型建筑室内空调划分为除湿模式、制冷模式、通风模式、制热模式和自动模式,并分析影响空调瞬态能耗的因素,建立朴素贝叶斯预测模型,剔除空调瞬态能耗异常数据,输入至朴素贝叶斯预测模型中,实现新型建筑室内空调的瞬态能耗预测。仿真结果表明,所提方法可有效完成不同模式和运行时间下的瞬态能耗预测,与实际能耗之间的偏离程度较低,期望误差仅为2.31%,变异系数为4.76%,预测误差小。