A systematic approach in load disaggregation utilizing a multi-stage classification algorithm for consumer electrical appliances classification

The potential to save energy in existing consumer electrical appliances is very high. One of the ways to achieve energy saving and improve energy use awareness is to recognize the energy consumption of individual electrical appliances. To recognize the energy consumption of consumer electrical appliances, the load disaggregation methodology is utilized. Non-intrusive appliance load monitoring (NIALM) is a load disaggregation methodology that disaggregates the sum of power consumption in a single point into the power consumption of individual electrical appliances. In this study, load disaggregation is performed through voltage and current waveform, known as the V-I trajectory. The classification algorithm performs cropping and image pyramid reduction of the V-I trajectory plot template images before utilizing the principal component analysis (PCA) and the k-nearest neighbor (k-NN) algorithm. The novelty of this paper is to establish a systematic approach of load disaggregation through V-I trajectory-based load signature images by utilizing a multi-stage classification algorithm methodology. The contribution of this paper is in utilizing the “k-value,” the number of closest data points to the nearest neighbor, in the k-NN algorithm to be effective in classification of electrical appliances. The results of the multi-stage classification algorithm implementation have been discussed and the idea on future work has also been proposed.     

A systematic approach to ON-OFF event detection and clustering analysis of non-intrusive appliance load monitoring

The aim of non-intrusive appliance load monitoring (NIALM) is to disaggregate the energy consumption of individual electrical appliances from total power consumption utilizing non-intrusive methods. In this paper, a systematic approach to ON-OFF event detection and clustering analysis for NIALM were presented. From the aggregate power consumption data set, the data are passed through median filtering to reduce noise and prepared for the event detection algorithm. The event detection algorithm is to determine the switching of ON and OFF status of electrical appliances. The goodness-of-fit (GOF) methodology is the event detection algorithm implemented. After event detection, the events detected were paired into ON-OFF pairing appliances. The results from the ON-OFF pairing algorithm were further clustered in groups utilizing the K-means clustering analysis. The K-means clustering were implemented as an unsupervised learning methodology for the clustering analysis. The novelty of this paper is the determination of the time duration an electrical appliance is turned ON through combination of event detection, ON-OFF pairing and K-means clustering. The results of the algorithm implementation were discussed and ideas on future work were also proposed.     

A systematic approach in appliance disaggregation using k-nearest neighbours and naive Bayes classifiers for energy efficiency

One of the ways to achieve energy efficiency in various residential electrical appliances is with energy usage feedback. Research work done showed that with energy usage feedback, behavioural changes by consumers to reduce electricity consumption contribute significantly to energy efficiency in residential energy usage. In order to improve on the appliance-level energy usage feedback, appliance disaggregation or non-intrusive appliance load monitoring (NIALM) methodology is utilized. NIALM is a methodology used to disaggregate total power consumption into individual electrical appliance power usage. In this paper, the electrical signature features from the publicly available REDD data set are extracted by the combination of identifying the ON or OFF events of appliances and goodness-of-fit (GOF) event detection algorithm. The k-nearest neighbours (k-NN) and naive Bayes classifiers are deployed for appliances’ classification. It is observed that the size of the training sets effects classification accuracy of the classifiers. The novelty of this paper is a systematic approach of NIALM using few training examples with two generic classifiers (k-NN and naive Bayes) and one feature (power) with the combination of ON-OFF based approach and GOF technique for event detection. In this work, we demonstrated that the two trained classifiers are able to classify the individual electrical appliances with satisfactory accuracy level in order to improve on the feedback for energy efficiency.     

A model for generating household electricity load profiles

Electricity consumption data profiles that include details on the consumption can be generated with a bottom‐up load models. In these models the load is constructed from elementary load components that can be households or even their individual appliances. In this work a simplified bottom‐up model is presented. The model can be used to generate realistic domestic electricity consumption data on an hourly basis from a few up to thousands of households. The model uses input data that is available in public reports and statistics. Two measured data sets from block houses are also applied for statistical analysis, model training, and verification. Our analysis shows that the generated load profiles correlate well with real data. Furthermore, three case studies with generated load data demonstrate some opportunities for appliance level demand side management (DSM). With a mild DSM scheme using cold loads, the daily peak loads can be reduced 7.2% in average. With more severe DSM schemes the peak load at the yearly peak day can be completely levelled with 42% peak reduction and sudden 3 h loss of load can be compensated with 61% mean load reduction. Copyright © 2005 John Wiley & Sons, Ltd.     

基于小电流电器的滑动窗双边CUSUM事件检测改进算法

事件检测是非侵入式负荷监测中的关键部分,然而事件检测方法对于一些小电流电器存在漏检问题。为此,提出一种基于小电流电器的滑动窗双边CUSUM事件检测改进算法,即在均值计算窗和暂态检测窗的基础上,引入方差计算窗区分运行时电流波动小的电器,通过权重参数δ提高检测过程中投入、切出事件的累计和,解决了滑动窗双边CUSUM事件检测算法的小电流电器漏检问题。采用方差阈值判断电器是否进入稳态,提高了电器进入稳态时检测的准确性,有效记录事件投入点和事件切出点。实测验证表明,所提算法不仅能够准确检测到传统算法易忽略的小电流电器的暂态事件,还能准确记录电器完整的事件投切过程,有利于其暂态过程的分析与处理,保证了特征提取的有效性,为事件检测方法的优化方向提供了借鉴。     

基于小电流电器的滑动窗双边CUSUM事件检测改进算法

事件检测是非侵入式负荷监测中的关键部分,然而事件检测方法对于一些小电流电器存在漏检问题。为此,提出一种基于小电流电器的滑动窗双边CUSUM事件检测改进算法,即在均值计算窗和暂态检测窗的基础上,引入方差计算窗区分运行时电流波动小的电器,通过权重参数δ提高检测过程中投入、切出事件的累计和,解决了滑动窗双边CUSUM事件检测算法的小电流电器漏检问题。采用方差阈值判断电器是否进入稳态,提高了电器进入稳态时检测的准确性,有效记录事件投入点和事件切出点。实测验证表明,所提算法不仅能够准确检测到传统算法易忽略的小电流电器的暂态事件,还能准确记录电器完整的事件投切过程,有利于其暂态过程的分析与处理,保证了特征提取的有效性,为事件检测方法的优化方向提供了借鉴。     

Decision-making in electrical appliance use in the home

This paper presents the results of a survey as well as an argument from the viewpoint of behavioral economics with the aim of clarifying how consumers make decisions about electrical appliance use in the home. A survey of consumers showed that most have little awareness of the energy efficiency of appliances, the price of the services produced by electrical appliances, or electricity rates. These findings indicate that price does not function as a signal in electricity consumption through electrical appliance use. Rather, we found that consumer decision-making in electricity consumption is dependent on the characteristics of the particular electrical appliances they use. Additionally, we argue that the payment system for home electricity consumption plays an important role in decision-making, causing biases due to aspects of human psychology discussed here in terms of satisficing and heuristics, payment decoupling, and budgeting. We conclude that decision-making about electrical appliance use and electricity consumption in the home is not always rational and is affected both by the particular characteristics of appliances and the payment system for electricity consumption along with human psychology.     

What's driving energy efficient appliance label awareness and purchase propensity?

The EU appliance energy consumption labeling scheme is a key component of efforts to increase the diffusion of energy-efficient household appliances. In this paper, the determinants of consumer knowledge of the energy label for household appliances and the choice of class-A energy-efficient appliances are jointly estimated using data from a large survey of more than 20,000 German households. The results for five major appliances suggest that lack of knowledge of the energy label can generate considerable bias in both estimates of rates of uptake of class-A appliances and in estimates of the underlying determinants of choice of class-A appliance. Simulations of the choice to purchase a class-A appliance, given knowledge of the labeling framework, reveal that residence characteristics and, in several cases, regional electricity prices strongly increase the propensity to purchase a class-A appliance, but socio-economic characteristics have surprisingly little impact on appliance energy-class choice.     

How do household characteristics affect appliance usage? Application of conditional demand analysis to Japanese household data

Although both appliance ownership and usage patterns determine residential electricity consumption, it is less known how households actually use their appliances. In this study, we conduct conditional demand analyses to break down total household electricity consumption into a set of demand functions for electricity usage, across 12 appliance categories. We then examine how the socioeconomic characteristics of the households explain their appliance usage. Analysis of micro-level data from the Nation Survey of Family and Expenditure in Japan reveals that the family and income structure of households affect appliance usage. Specifically, we find that the presence of teenagers increases both air conditioner and dishwasher use, labor income and nonlabor income affect microwave usage in different ways, air conditioner usage decreases as the wife's income increases, and microwave usage decreases as the husband's income increases. Furthermore, we find that households use more electricity with new personal computers than old ones; this implies that the replacement of old personal computers increases electricity consumption.     

Tackling global electricity shortage through human power: Technical opportunities from direct or indirect utilizations of the pervasive and green human energy

With the energy and environmental problems becoming increasingly serious, human power, as a pervasive, renewable, mobile and environment friendly energy, draws more and more attention over the world. In this paper, the most basic features of human power are presented. The currently available human power harvesting theories and devices are briefly reviewed and compared. Further, direct or indirect utilization of human power in daily life, especially transportation and home appliances, such as human-powered car, watercraft, aircraft, washing machine and television etc. are summarized. Considering that the total energy from an individual is rather limited, as previously focused by most of the former works, it is conceived in this paper that an important future for large scale use of human powers lies in the efficient conversion, collection and storage of such energy from discrete people and then use it later on as desired. With the huge amount of energy gathered, the application category of human power would be significantly expended. Starting from this point, three technical ways towards efficiently utilizing human power are sketched, which are termed as human-powered grid (HPG), human-powered charger (HPC) and human-powered storage (HPS), among which, HPG is capable of collecting the electric power produced by each individual at different regions and thus can supply unique and flexible power to the customers covered in the area, without relying on the conventional electricity grid. The HPC can then charge various kinds of electrical devices instantly by a human driven generator which converts human power into electricity. Finally, the HPS can store electricity in time for later use. In this way, even for the devices requiring electricity that is strong enough, the collected human power can also serve as its reliable energy source. Meanwhile, utilization of human power becomes rather convenient and timely which guarantees its practical value. It is expected that with further research and increasing applications, human power could partially relieve the current global electricity shortage and environmental issues via its pervasive contribution.     

The applicability of energy models to occupied houses: Summer electric use in Davis

Total electricity use and cooling loads for a three month cooling season (July–September, 1980) in single-family detached houses in Davis, California, are estimated and compared with measured data. Total electricity use is estimated by predicting cooling loads and appliance electricity use using a technique approximating a relatively low cost audit program. Cooling loads are estimated using an interpolation model to simplify application of the DOE-2.1A energy use computer model. Appliance electricty use is derived from manufacturers' data, and patterns of appliance use are elicited from occupants through a survey. While reasonably accurate prediction of aggregate electricity use and cooling load for a group of houses is possible, similar accuracy for individual houses is more difficult because of variation and uncertainty in occupant behavior patterns and building parameters. We conclude that precise forecasting of individual house electricity use is unlikely, even when there are no changes in occupancy, unless impracticably expensive monitoring techniques are employed.     

What can we learn from high-frequency appliance-level energy metering? Results from a field experiment

This study uses high-frequency appliance-level electricity consumption data for 124 apartments over 24 months to provide a better understanding of appliance-level electricity consumption behavior. We conduct our analysis in a standardized set of apartments with similar appliances, which allows us to identify behavioral differences in electricity use. The Results show that households' estimations of appliance-level consumption are inaccurate and that they overestimate lighting use by 75% and underestimate plug-load use by 29%. We find that similar households using the same major appliances exhibit substantial variation in appliance-level electricity consumption. For example, households in the 75th percentile of HVAC usage use over four times as much electricity as a user in the 25th percentile. Additionally, we show that behavior accounts for 25–58% of this variation. Lastly, we find that replacing the existing refrigerator with a more energy-efficient model leads to overall energy savings of approximately 11%. This is equivalent to results from behavioral interventions targeting all appliances but might not be as cost effective. Our findings have important implications for behavior-based energy conservation policies.     

Smart residential energy management system for demand response in buildings with energy storage devices

In the present scenario, the utilities are focusing on smart grid technologies to achieve reliable and profitable grid operation. Demand side management (DSM) is one of such smart grid technologies which motivate end users to actively participate in the electricity market by providing incentives. Consumers are expected to respond (demand response (DR)) in various ways to attain these benefits. Nowadays, residential consumers are interested in energy storage devices such as battery to reduce power consumption from the utility during peak intervals. In this paper, the use of a smart residential energy management system (SREMS) is demonstrated at the consumer premises to reduce the total electricity bill by optimally time scheduling the operation of household appliances. Further, the SREMS effectively utilizes the battery by scheduling the mode of operation of the battery (charging/floating/discharging) and the amount of power exchange from the battery while considering the variations in consumer demand and utility parameters such as electricity price and consumer consumption limit (CCL). The SREMS framework is implemented in Matlab and the case study results show significant yields for the end user.     

Energy efficiency standards for refrigerators in Brazil: A methodology for impact evaluation

In Brazil energy efficiency standards for cold appliances was established in 2007. A specified single set of MEPS (minimum energy performance standards) for refrigerators, freezers and freezer refrigerators was implemented without evaluating its impacts and estimation of potential electricity savings. This paper presents a methodology for assessing the impacts of the Brazilian MEPS for cold appliances. It uses a bottom-up approach to estimate residential end-use consumption and to evaluate the energy saving potential for refrigerators. The household electricity consumption is projected by modeling appliance ownership using an econometric approach based on the recent household survey data. A cost–benefit analysis for more stringent standards is presented from the perspective of the society and electricity customers. The results showed that even considering the current market conditions (high discount rate for financing new efficient equipment) some MEPS options are advantageous for customers. The analysis also demonstrates significant cost-effective saving potential from the society perspective that could reach 21 TWh throughout the period of 2010–2030—about 25% of current residential consumption.     

A framework for home energy management and its experimental validation

With the Smart Grid revolution and the increasing interest in renewable energy sources, the management of the electricity consumption and production of individual households and small residential communities is becoming an essential element of new power systems. The electric energy chain can greatly benefit from a flexible interaction with end-users based on the optimization of load profiles and the exploitation of local generation and energy storage. This paper proposes a framework for the development of a complete energy management system for individual residential units and small communities of domestic users, taking into account both the power system and the final users’ perspectives. All the main elements of the framework are considered, and contributions are provided on the users’ habits profiling, electricity generation forecast, energy load, and storage optimization. Specifically, we propose a linear regression model to predict the photovoltaic panels production, a stochastic method to forecast the home appliances usage, and two optimization models to optimize the electricity management of residential users with the goal of minimizing their bills. The study shows that it is possible to reduce the energy bill of residential users through the electricity optimization driven by dynamic energy prices. Moreover, remarkable improvements of the electric grid efficiency can be achieved with the cooperation among users, confirming that services for the coordination of the demand of groups of users allow huge benefits on the power system performance.     

Short-term prediction of household electricity consumption: Assessing weather sensitivity in a Mediterranean area

Urban microclimatic variations, along with a rapid reduction of unit cost of air-conditioning (AC) equipments, can be addressed as some of the main causes of the raising residential energy demand in the more developed countries. This paper presents a forecasting model based on an Elman artificial neural network (ANN) for the short-time prediction of the household electricity consumption related to a suburban area. Due to the lack of information about the real penetration of electric appliances in the investigated area and their utilization profiles it was not possible to implement a statistical model to define the weather and climate sensitivities of appliance energy consumption. For this reason an ANN model was used to predict the household electric energy demand of the investigated area and to evaluate the influence of the AC equipments on the overall consumption.The data used to train the network were recorded in Palermo (Italy) and include electric current intensity and weather variables as temperature, relative humidity, global solar radiation, atmospheric pressure and wind speed values between June 1, 2002 and September 10, 2003.The work pointed out the importance of a thermal discomfort index, the Humidex index, for a simple but effective evaluation of the conditions affecting the occupant behaviour and thus influencing the household electricity consumption related to the use of heating, ventilation and air conditioning (HVAC) appliances. The prediction performances of the model are satisfying and bear out the ability of ANNs to manage incomplete and noisy data, solve nonlinear problems and learn complex underlying relationships between input and output patterns.     

Household electricity demand forecast and energy savings potential for Vientiane,Lao PDR

This paper uses the survey data on household electricity demand from five districts of Vientiane, Lao PDR, for the demand projection up to 2030 using the end-use model. The scenario analysis is used to verify the potential of an energy-saving program by alternating selected appliances with more energy-efficient ones following the labelling standard of Thailand. The demographic structure of electrified households and the energy efficiency of electric appliances are considered as the dominant factors affecting electricity demand. Under the base-case scenario, the total electricity demand of Vientiane increased from 593?GWh in 2013 to 965?GWh in 2030. In the energy efficiency scenario, it is revealed that the appliance standard enhancement program can save total electricity demand in 2030 by 147?GWh (?15.2%), where 117?GWh (?12.1%) of which is contributed by the air conditioner and 30?GWh (?3.1%) by the lighting equipment.     

Internet of things and cloud computing‐based energy management system for demand side management in smart grid

A smart grid is an electricity network, which deals with electronic power conditioning and control of production, transmission, and distribution of electrical power by employing digital communication technologies to monitor and manage local changes in electricity usage. In the traditional power grid, energy consumers remain oblivious to their power consumption patterns, resulting in wasted energy as well as money. This issue is severely pronounced in the developing countries where there is a huge gap between demand and supply, resulting in frequent power outages and load‐shedding. For electrical energy savings, the smart grid employs demand side management (DSM), which refers to adaptation in consumer's demand for energy through various approaches such as financial incentives and awareness. The DSM in future smart grid must exploit automated energy management systems (EMS) built upon the state‐of‐the‐art technologies such as the internet of things (IoT) and cloud and/or fog computing. In this paper, we present the architecture framework, design, and implementation of an IoT and cloud computing‐based EMS, which generates load profile of consumer to be accessed remotely by utility company or by the consumer. The consumers' load profiles enable utility companies to regulate and disseminate their incentives and incite the consumers to adapt their energy consumption. Our designed EMS is implemented on a Project Circuit Board (PCB) to be easily installed at the consumer premises where it performs the following tasks: (a) monitors energy consumption of electrical appliances by means of our designed current and voltage sensors, (b) uploads sensed data to Google Firebase cloud over many‐to‐many IoT communication protocol Message Queuing Telemetry Transport (MQTT) where consumer's load profile is generated, which can be accessed via a web portal. These load profiles serve as input for implementing the various DSM approaches. Our results demonstrate generated load profiles of consumer load in terms of current, voltage, energy, and power accessible via a web portal.     

模糊ISODATA算法在城市负荷分类中的应用

鉴于目前电力大数据总量大、数据复杂度高、价值密度低等,基于模糊ISODATA聚类算法研究了商场、宾馆酒店、办公等典型城市负荷用电特性,建立了城市负荷的建筑类型、总能耗、照明与插座用能、空调用能、动力用能、特殊和其他用能的数据维度模型用以辅助分类决策,并在不同维度、数量级的样本数据下与传统聚类算法的性能进行比较。同时与传统的基于日负荷曲线的分类方法准确率进行对比。结果表明,基于模糊ISODATA算法的城市用电行为分析模型聚类效果好、精度高,适用于当前高维度、大规模的电力大数据的分类,并在一定程度上能够克服当前电力大数据负荷分类中聚类数目设置难、易陷入局部最优等问题。研究成果可用于指导工程实践。