The rapid digitalization of the energy sector has led to the deployment of large-scale smart metering systems that generate high-frequency time series data,creating new opportunities and challenges for energy anomaly ...The rapid digitalization of the energy sector has led to the deployment of large-scale smart metering systems that generate high-frequency time series data,creating new opportunities and challenges for energy anomaly detection.Accurate identification of anomalous patterns in building energy consumption is essential for optimizing operations,improving energy efficiency,and supporting grid reliability.This study investigates advanced feature engineering and machine learning modeling techniques for large-scale time series anomaly detection in building energy systems.Expanding upon previous benchmark frameworks,we introduce additional features such as oil price indices and solar cycle indicators,including sunset and sunrise times,to enhance the contextual understanding of consumption patterns.Our comparative modeling approach encompasses an extensive suite of algorithms,including KNeighborsUnif,KNeighborsDist,LightGBMXT,LightGBM,RandomForestMSE,CatBoost,ExtraTreesMSE,NeuralNetFastAI,XGBoost,NeuralNetTorch,and LightGBMLarge.Data preprocessing includes rigorous handling of missing values and normalization,while feature engineering focuses on temporal,environmental,and value-change attributes.The models are evaluated on a comprehensive dataset of smart meter readings,with performance assessed using metrics such as the Area Under the Receiver Operating Characteristic Curve(AUC-ROC).The results demonstrate that the integration of diverse exogenous variables and a hybrid ensemble of traditional tree-based and neural network models can significantly improve anomaly detection performance.This work provides new insights into the design of robust,scalable,and generalizable frameworks for energy anomaly detection in complex,real-world settings.展开更多
Accurate electric energy(EE)measurements and billing estimations in a power system necessitate the development of an energy flow distribution model.This paper summarizes the results of investigations on a new problem ...Accurate electric energy(EE)measurements and billing estimations in a power system necessitate the development of an energy flow distribution model.This paper summarizes the results of investigations on a new problem related to the determination of EE flow in a power system over time intervals ranging from minutes to years.The problem is referred to as the energy flow problem(EFP).Generally,the grid state and topology may fluctuate over time.An attempt to use instantaneous(not integral)power values obtained from telemetry to solve classical electrical engineering equations leads to significant modeling errors,particularly with topology changes.A promoted EFP model may be suitable in the presence of such topological and state changes.Herein,EE flows are determined using state estimation approaches based on direct EE measurement data in Watt-hours(Volt-ampere reactive-hours)provided by electricity meters.The EFP solution is essential for a broad set of applications,including meter data validation,zero unbalance EE billing,and nontechnical EE loss check.展开更多
Aiming at the shortcomings of the existing electric energy metering method,combining with the harmonic responsibility analysis model based on the reference impedance method and the idea of apparent power decomposition...Aiming at the shortcomings of the existing electric energy metering method,combining with the harmonic responsibility analysis model based on the reference impedance method and the idea of apparent power decomposition in IEEE Std 1459-2010 standard,two new metering indicators—billing active power and billing power factor are defined.A new electric energy metering method is proposed and its specific implementation steps are given.The simulation model is built in Matlab/Simulink,and three different examples are set up.Using the simulation data,the various metering indicators need to be examined by the existing electric energy metering method and the new electric energy metering method are calculated.The calculation results show that the new electric energy metering method not only overcomes the shortcomings of the existing electric energy metering method,but also is very easy to be popularized and applied.展开更多
Currently a large effort is being done with the intention to educate people about how much energy each electrical appliance uses in their houses, since this knowledge is the fundamental basis of energy efficiency prog...Currently a large effort is being done with the intention to educate people about how much energy each electrical appliance uses in their houses, since this knowledge is the fundamental basis of energy efficiency programs that can be managed by the household owners. This paper presents a simple yet functional non-intrusive method for electric power measurement that can be applied in energy efficiency programs, in order to provide a better knowledge of the energy consumption of the appliances in a home.展开更多
This article puts forward an automatic recognition algorithm of electric energy meter lead seals： firstly, the image will be histogram equalization, smoothing, binaryzation pretreatment, then according to the image c...This article puts forward an automatic recognition algorithm of electric energy meter lead seals： firstly, the image will be histogram equalization, smoothing, binaryzation pretreatment, then according to the image characteristics of text changes, the system can quickly and accurately segment image from complex background, finally the system extract different dimension and the feature of English and Arabia using digital projection transform coefficient method and to identify the corresponding number by BP neural network, solves the problem of automatic recognition of electric energy meter lead sealing.展开更多
Aiming at the problem of large energy consumption in hydraulic control system with large load and variable working conditions,based on the multi-level pressure switching control system(MPSCS),a multi-level pressure sw...Aiming at the problem of large energy consumption in hydraulic control system with large load and variable working conditions,based on the multi-level pressure switching control system(MPSCS),a multi-level pressure switching control system based on independent metering control is proposed combined with the independent metering control technology.The configuration principle of the system is given,the mathematical model of this system is established,and the control strategy of the system under 4 different working quadrants is put forward.Finally,the control performance and energy saving characteristics of the system are tested.The test results show that the switching of high and low pressure power supply has a certain effect on the response of step position and ramp position under impedance working condition.The displacement curves show slow climbing or abrupt change of ramp position,and the position accuracy is less than 1 mm.The multi-level pressure switching control system based on independent metering control can recover and store energy under the transcendence working conditions.The control accuracy is about 1 mm,and the energy recovery rate is about 70%~80%.展开更多
Purpose-For billing purposes,heavy-haul locomotives in Sweden are equipped with on-board energy meters,which can record several parameters,e.g.,used energy,regenerated energy,speed and position.Since there is a strong...Purpose-For billing purposes,heavy-haul locomotives in Sweden are equipped with on-board energy meters,which can record several parameters,e.g.,used energy,regenerated energy,speed and position.Since there is a strong demand for improving energy efficiency in Sweden,data from the energy meters can be used to obtain a better understanding of the detailed energy usage of heavy-haul trains and identify potential for future improvements.Design/methodology/approach-To monitor energy efficiency,the present study,therefore,develops key performance indicators(KPIs),which can be calculated with energy meter data to reflect the energy efficiency of heavy-haul trains in operation.Energy meter data of IORE class locomotives,hauling highly uniform 30-tonne axle load trains with 68 wagons,together with additional data sources,are analysed to identify significant parameters for describing driver influence on energy usage.Findings-Results show that driver behaviour varies significantly and has the single largest influence on energy usage.Furthermore,parametric studies are performed with help of simulation to identify the influence of different operational and rolling stock conditions,e.g.,axle loads and number of wagons,on energy usage.Originality/value-Based on the parametric studies,some operational parameters which have significant impact on energy efficiency are found and then the KPIs are derived.In the end,some possible measures for improving energy performance in heavy-haul operations are given.展开更多
Correction factors of both Rem-meters, the 10 inch diameter single-sphere Remmeter and the standard A-B Rem-meter, were estimated for measuring high energy neutron dose equivalent outside a concrete shielding wall and...Correction factors of both Rem-meters, the 10 inch diameter single-sphere Remmeter and the standard A-B Rem-meter, were estimated for measuring high energy neutron dose equivalent outside a concrete shielding wall and the effects that the emitted neutron spectra become remarkably "harder" penetrated through a concrete shielding wall, and the energy response of the Rem-meter were taken in account. The estimated results could be applied in the measurement of neutron dose equivalent for the intermediate energy heavy ion reactions to avoid the difficulty induced by the energy response of the Rem-meters.展开更多
智能电能表在复杂电网环境下的计量精度易受非线性误差影响。为提高其准确性,提出一种融合非线性自回归外生输入(nonlinear auto-regressive with exogenous inputs,NARX)模型与畸变功率的误差校正方法。利用NARX模型构建电能表的非线...智能电能表在复杂电网环境下的计量精度易受非线性误差影响。为提高其准确性,提出一种融合非线性自回归外生输入(nonlinear auto-regressive with exogenous inputs,NARX)模型与畸变功率的误差校正方法。利用NARX模型构建电能表的非线性误差模型,以捕捉其动态特性;从测量数据中分离基波与谐波电能,并计算谐波电能比差以量化谐波影响;引入畸变功率概念,构建以谐波电能比差和畸变功率为输入的误差校正模型,对非线性误差进行补偿。实验结果表明:经所提方法校正后,在不同谐波含量(5%、10%、20%)条件下,智能电能表的最大计量误差由校正前的2.4%、3.1%、10.3%均降至0.5%左右,同时非线性误差预测结果的拟合度得到了提升,有效提高了谐波环境下的计量精度。展开更多
针对智能电网配电室能耗数据网接入的安全挑战,提出一种融合5G切片与边缘计算的安全机制。该机制通过数据分类分级、虚拟扩展局域网(Virtual eXtensible Local Area Network,VXLAN)隔离、SM4二次加密及双向长短期记忆(Bidirectional Lon...针对智能电网配电室能耗数据网接入的安全挑战,提出一种融合5G切片与边缘计算的安全机制。该机制通过数据分类分级、虚拟扩展局域网(Virtual eXtensible Local Area Network,VXLAN)隔离、SM4二次加密及双向长短期记忆(Bidirectional Long Short-Term Memory,Bi-LSTM)异常检测等技术,实现对多源异构数据的差异化防护,保障数据的完整性、准确性与抗篡改性。实验结果表明,其异常检测准确率较高,可为高安全要求场景下的能源数据网络安全接入与协同防护提供有效的解决方案。展开更多
文摘The rapid digitalization of the energy sector has led to the deployment of large-scale smart metering systems that generate high-frequency time series data,creating new opportunities and challenges for energy anomaly detection.Accurate identification of anomalous patterns in building energy consumption is essential for optimizing operations,improving energy efficiency,and supporting grid reliability.This study investigates advanced feature engineering and machine learning modeling techniques for large-scale time series anomaly detection in building energy systems.Expanding upon previous benchmark frameworks,we introduce additional features such as oil price indices and solar cycle indicators,including sunset and sunrise times,to enhance the contextual understanding of consumption patterns.Our comparative modeling approach encompasses an extensive suite of algorithms,including KNeighborsUnif,KNeighborsDist,LightGBMXT,LightGBM,RandomForestMSE,CatBoost,ExtraTreesMSE,NeuralNetFastAI,XGBoost,NeuralNetTorch,and LightGBMLarge.Data preprocessing includes rigorous handling of missing values and normalization,while feature engineering focuses on temporal,environmental,and value-change attributes.The models are evaluated on a comprehensive dataset of smart meter readings,with performance assessed using metrics such as the Area Under the Receiver Operating Characteristic Curve(AUC-ROC).The results demonstrate that the integration of diverse exogenous variables and a hybrid ensemble of traditional tree-based and neural network models can significantly improve anomaly detection performance.This work provides new insights into the design of robust,scalable,and generalizable frameworks for energy anomaly detection in complex,real-world settings.
文摘Accurate electric energy(EE)measurements and billing estimations in a power system necessitate the development of an energy flow distribution model.This paper summarizes the results of investigations on a new problem related to the determination of EE flow in a power system over time intervals ranging from minutes to years.The problem is referred to as the energy flow problem(EFP).Generally,the grid state and topology may fluctuate over time.An attempt to use instantaneous(not integral)power values obtained from telemetry to solve classical electrical engineering equations leads to significant modeling errors,particularly with topology changes.A promoted EFP model may be suitable in the presence of such topological and state changes.Herein,EE flows are determined using state estimation approaches based on direct EE measurement data in Watt-hours(Volt-ampere reactive-hours)provided by electricity meters.The EFP solution is essential for a broad set of applications,including meter data validation,zero unbalance EE billing,and nontechnical EE loss check.
基金National Natural Science Foundation of China(No.51367010)Science and Technology Program of Gansu Province(No.17JR5RA083)+1 种基金Program for Excellent Team of Scientific Research of Lanzhou Jiaotong University(No.201701)Scientific Research Program of Colleges and Universities of Gansu Province(No.2016B-032)。
文摘Aiming at the shortcomings of the existing electric energy metering method,combining with the harmonic responsibility analysis model based on the reference impedance method and the idea of apparent power decomposition in IEEE Std 1459-2010 standard,two new metering indicators—billing active power and billing power factor are defined.A new electric energy metering method is proposed and its specific implementation steps are given.The simulation model is built in Matlab/Simulink,and three different examples are set up.Using the simulation data,the various metering indicators need to be examined by the existing electric energy metering method and the new electric energy metering method are calculated.The calculation results show that the new electric energy metering method not only overcomes the shortcomings of the existing electric energy metering method,but also is very easy to be popularized and applied.
文摘Currently a large effort is being done with the intention to educate people about how much energy each electrical appliance uses in their houses, since this knowledge is the fundamental basis of energy efficiency programs that can be managed by the household owners. This paper presents a simple yet functional non-intrusive method for electric power measurement that can be applied in energy efficiency programs, in order to provide a better knowledge of the energy consumption of the appliances in a home.
文摘This article puts forward an automatic recognition algorithm of electric energy meter lead seals： firstly, the image will be histogram equalization, smoothing, binaryzation pretreatment, then according to the image characteristics of text changes, the system can quickly and accurately segment image from complex background, finally the system extract different dimension and the feature of English and Arabia using digital projection transform coefficient method and to identify the corresponding number by BP neural network, solves the problem of automatic recognition of electric energy meter lead sealing.
基金the National Natural Science Foundation of China(No.51575471)the Natural Science Foundation of Hebei Province(No.E2018203028).
文摘Aiming at the problem of large energy consumption in hydraulic control system with large load and variable working conditions,based on the multi-level pressure switching control system(MPSCS),a multi-level pressure switching control system based on independent metering control is proposed combined with the independent metering control technology.The configuration principle of the system is given,the mathematical model of this system is established,and the control strategy of the system under 4 different working quadrants is put forward.Finally,the control performance and energy saving characteristics of the system are tested.The test results show that the switching of high and low pressure power supply has a certain effect on the response of step position and ramp position under impedance working condition.The displacement curves show slow climbing or abrupt change of ramp position,and the position accuracy is less than 1 mm.The multi-level pressure switching control system based on independent metering control can recover and store energy under the transcendence working conditions.The control accuracy is about 1 mm,and the energy recovery rate is about 70%~80%.
文摘Purpose-For billing purposes,heavy-haul locomotives in Sweden are equipped with on-board energy meters,which can record several parameters,e.g.,used energy,regenerated energy,speed and position.Since there is a strong demand for improving energy efficiency in Sweden,data from the energy meters can be used to obtain a better understanding of the detailed energy usage of heavy-haul trains and identify potential for future improvements.Design/methodology/approach-To monitor energy efficiency,the present study,therefore,develops key performance indicators(KPIs),which can be calculated with energy meter data to reflect the energy efficiency of heavy-haul trains in operation.Energy meter data of IORE class locomotives,hauling highly uniform 30-tonne axle load trains with 68 wagons,together with additional data sources,are analysed to identify significant parameters for describing driver influence on energy usage.Findings-Results show that driver behaviour varies significantly and has the single largest influence on energy usage.Furthermore,parametric studies are performed with help of simulation to identify the influence of different operational and rolling stock conditions,e.g.,axle loads and number of wagons,on energy usage.Originality/value-Based on the parametric studies,some operational parameters which have significant impact on energy efficiency are found and then the KPIs are derived.In the end,some possible measures for improving energy performance in heavy-haul operations are given.
文摘Correction factors of both Rem-meters, the 10 inch diameter single-sphere Remmeter and the standard A-B Rem-meter, were estimated for measuring high energy neutron dose equivalent outside a concrete shielding wall and the effects that the emitted neutron spectra become remarkably "harder" penetrated through a concrete shielding wall, and the energy response of the Rem-meter were taken in account. The estimated results could be applied in the measurement of neutron dose equivalent for the intermediate energy heavy ion reactions to avoid the difficulty induced by the energy response of the Rem-meters.
文摘智能电能表在复杂电网环境下的计量精度易受非线性误差影响。为提高其准确性,提出一种融合非线性自回归外生输入(nonlinear auto-regressive with exogenous inputs,NARX)模型与畸变功率的误差校正方法。利用NARX模型构建电能表的非线性误差模型,以捕捉其动态特性;从测量数据中分离基波与谐波电能,并计算谐波电能比差以量化谐波影响;引入畸变功率概念,构建以谐波电能比差和畸变功率为输入的误差校正模型,对非线性误差进行补偿。实验结果表明:经所提方法校正后,在不同谐波含量(5%、10%、20%)条件下,智能电能表的最大计量误差由校正前的2.4%、3.1%、10.3%均降至0.5%左右,同时非线性误差预测结果的拟合度得到了提升,有效提高了谐波环境下的计量精度。
文摘针对智能电网配电室能耗数据网接入的安全挑战,提出一种融合5G切片与边缘计算的安全机制。该机制通过数据分类分级、虚拟扩展局域网(Virtual eXtensible Local Area Network,VXLAN)隔离、SM4二次加密及双向长短期记忆(Bidirectional Long Short-Term Memory,Bi-LSTM)异常检测等技术,实现对多源异构数据的差异化防护,保障数据的完整性、准确性与抗篡改性。实验结果表明,其异常检测准确率较高,可为高安全要求场景下的能源数据网络安全接入与协同防护提供有效的解决方案。
