Appliance Load Research Articles

Sensitivity analysis for building energy audit calculation methods: Handling the uncertainties in small power load estimation

The use of static calculation models in building energy audits typically requires estimation of power loads, as appliance load monitoring is both expensive and intrusive. Small power loads are particularly difficult to monitor in detail and so, with increasing proportional contribution to overall building energy consumption, constitute a significant source of uncertainty in estimations. Little research has been conducted on how uncertainty in audit estimations (particularly of small power loads) should be handled and to what extent this impacts on what information is of most value in reducing audit uncertainties. The Morris method for sensitivity analysis has been adapted for small power load estimation to identify which inputs in static calculation models the output estimations are most sensitive to. The method is applied to the TM22 and TM54 audit calculation models from the Chartered Institute of Building Service Engineers (CIBSE); widely used in industry. Results demonstrate how the weight of input uncertainties differs according to the calculation model used. By providing uncertainty estimation in the audit process, auditors can choose an optimal energy assessment strategy for small power load estimations whilst also better understanding the significance of input uncertainty within the different energy calculation models.

Household attributes associated with peak period domestic appliance loads

Household appliances represent substantial electricity load within the residential sector, particularly during the electricity system's period of peak evening load. While there is broad understanding of the factors that systematically impact on aggregate residential loads, much less is known about appliance loads. A research priority is understanding how socio-demographic, dwelling, and appliance factors are associated with the timing and scale of appliance loads. Using data from Ireland the analysis finds that the number of household occupants; number of appliances; and daytime occupancy of the home are closely associated with appliance loads but varies depending on the time of day. No association is found between appliance uses and building tenure, type or age; or socio-demographic variables such as income, age or education. The empirical findings have relevance for modelling residential electricity loads, and for design of measures to shift residential loads away from the evening peak period.

Toward Load Identification Based on the Hilbert Transform and Sequence to Sequence Long Short-Term Memory

Load identification is a core concept in non-intrusive load monitoring (NILM). Through NILM systems, users can check their home appliance usage habits and then adjust their behavior to save electricity. In this way, a NILM system offers an effective method to detect the event status of household appliances as well as individual loads' energy consumption. However, prior NILM methods have encountered a challenge in improving recognition accuracy for both linear load and non-linear load types. These methods used a representative feature, namely transient load signals. However, the transient signals on these loads differ in terms of transient time and transient shape, which is the main cause of reduced accuracy performance in load identification. To this end, this paper presents a novel method, HT-LSTM (Hilbert Transform Long Short-Term Memory), which enhances recognition of the various load types that contain the difference in the transient time and the transient shape of any load signal. The proposed method consists of two main parts: (i) generating a novel transient feature based on a Hilbert transform (HT), called APF (Amplitude-Phase-Frequency). APF features are sequential data, which is used for the classification model; and (ii) applying Sequence-to-Sequence Long Short-Term Memory (Seq2Seq LSTM) to identify appliances by using APF features as the input data. In this work, we evaluate the HT-LSTM method using two high-frequency public datasets, Building-Level fUlly-labeled dataset for Electricity Disaggregation (BLUED) and Plug Load Appliance Identification Dataset (PLAID). Also, we evaluate our method using a private dataset collected in the lab. Based on the experimental results obtained and comparison classification performance pointed, the proposed method outperforms previous methods of F-score measurement on both public datasets in load identification as well as the private dataset.

Semi-supervised Intrusive Appliance Load Monitoring in Smart Energy Monitoring System

Intrusive Load Monitoring (ILM) is a method to measure and collect the energy consumption data of individual appliances via smart plugs or smart sockets. A major challenge of ILM is automatic appliance identification, in which the system is able to determine automatically a label of the active appliance connected to the smart device. Existing ILM techniques depend on labels input by end-users and are usually under the supervised learning scheme. However, in reality, end-users labeling is laboriously rendering insufficient training data to fit the supervised learning models. In this work, we propose a semi-supervised learning (SSL) method that leverages rich signals from the unlabeled dataset and jointly learns the classification loss for the labeled dataset and the consistency training loss for unlabeled dataset. The samples fit into consistency learning are generated by a transformation that is built upon weighted versions of DTW Barycenter Averaging algorithm. The work is inspired by two recent advanced works in SSL in computer vision and combines the advantages of the two. We evaluate our method on the dataset collected from our developed Internet-of-Things based energy monitoring system in a smart home environment. We also examine the method’s performances on 10 benchmark datasets. As a result, the proposed method outperforms other methods on our smart appliance datasets and most of the benchmarks datasets, while it shows competitive results on the rest datasets.

Multi-label LSTM autoencoder for non-intrusive appliance load monitoring

This work follows the multi-label classification based paradigm for non-intrusive load monitoring (NILM). Power consumption signals used for NILM are inherently time varying. However prior multi-label classification techniques could not model this dynamical behaviour. They used off-the-shelf algorithms for classifying static signals on NILM problems. This is the first work that shows how to account for the temporal variability of input signals in a multi-label classification framework. Results on benchmark datasets like REDD and Pecan Street show considerable improvement over several state-of-the-art shallow and deep techniques.

Data Acquisition: A Case Study at Residential Places in Delhi

The ever-rising consumption of electricity and its billing is one of the most addressed and common issue for a common man. The electricity charged by electricity providers (both government and private) does not have a clear and transparent process. One may have to go through a detailed analysis of the bill just to understand this. Our generation is considered to be a fast pace generation. We always expect things to be just taps and clicks away. To help this we are proposing a model. This paper consists of collecting data from residential places at Delhi and using them to monitor and control the MDI of houses. Residential consumers are one of the biggest and major consumers of electricity board and real time monitoring of these load appliances provides a transparency between users and the providers keeping the bill pricing fair and unbiased and also helps consumers to work under their sanctioned load limit. When these data are monitored real time it can help in creating a smart home followed by a smart grid and eventually a smart city.

Nonintrusive Residential Electricity Load Decomposition Based on Transfer Learning

Monitoring electricity consumption in residential buildings is an important way to help reduce energy usage. Nonintrusive load monitoring is a technique to separate the total electrical load of a single household into specific appliance loads. This problem is difficult because we aim to extract the energy consumption of each appliance by only using the total electrical load. Deep transfer learning is expected to solve this problem. This paper proposes a deep neural network model based on an attention mechanism. This model improves the traditional sequence-to-sequence model with a time-embedding layer and an attention layer so that it can be better applied in nonintrusive load monitoring. In particular, the improved model abandons the recurrent neural network structure and shortens the training time, which means it is more appropriate for use in model pretraining with large datasets. To verify the validity of the model, we selected three open datasets and compared them with the current leading model. The results show that transfer learning can effectively improve the prediction ability of the model, and the model proposed in this study has a better performance than the most advanced available model.

A systems dynamics approach to the bottom-up simulation of residential appliance load

Residential demand from real residences can be resource intensive to collect. There is need to generate synthetic residential load in energy research, and new approaches are welcome. Most of the simulation models of synthetic residential load that output realistic loads are tightly coupled to historic correlations. This paper presents a high-resolution simulation model that generates a residential appliance load using the tools of System Dynamics via a bottom-up approach. In addition to being realistic, the model aims to minimise historic coupling. Whilst the intermediary outputs of the modelling process are subjected to systematic scrutiny, the final output is validated by comparing statistical characteristics of the model’s output to a validated model and data from real residences. The aims of the model were sufficiently met, and the modelling approach shows potential to simplify; by driving the model on average frequency of appliance use instead of probability distributions of human activities. Other outputs from the model, specifically distribution of appliances’ activation and operation, as well as complexity are discussed. Some benefits of the model are also discussed especially with regard to cost of modelling, interpretability of model and potential for transdisciplinary research. This study represents the first attempt to develop a bottom-up simulation model of residential load based on a System Dynamics approach.

A Smart Home Energy Management System Using Two-Stage Non-Intrusive Appliance Load Monitoring over Fog-Cloud Analytics Based on Tridium's Niagara Framework for Residential Demand-Side Management.

Electricity is a vital resource for various human activities, supporting customers’ lifestyles in today’s modern technologically driven society. Effective demand-side management (DSM) can alleviate ever-increasing electricity demands that arise from customers in downstream sectors of a smart grid. Compared with the traditional means of energy management systems, non-intrusive appliance load monitoring (NIALM) monitors relevant electrical appliances in a non-intrusive manner. Fog (edge) computing addresses the need to capture, process and analyze data generated and gathered by Internet of Things (IoT) end devices, and is an advanced IoT paradigm for applications in which resources, such as computing capability, of a central data center acted as cloud computing are placed at the edge of the network. The literature leaves NIALM developed over fog-cloud computing and conducted as part of a home energy management system (HEMS). In this study, a Smart HEMS prototype based on Tridium’s Niagara Framework® has been established over fog (edge)-cloud computing, where NIALM as an IoT application in energy management has also been investigated in the framework. The SHEMS prototype established over fog-cloud computing in this study utilizes an artificial neural network-based NIALM approach to non-intrusively monitor relevant electrical appliances without an intrusive deployment of plug-load power meters (smart plugs), where a two-stage NIALM approach is completed. The core entity of the SHEMS prototype is based on a compact, cognitive, embedded IoT controller that connects IoT end devices, such as sensors and meters, and serves as a gateway in a smart house/smart building for residential DSM. As demonstrated and reported in this study, the established SHEMS prototype using the investigated two-stage NIALM approach is feasible and usable.

Solar panels and smart thermostats: The power duo of the residential sector?

Rising peak demand is a major cause for high emissions from the electricity sector. In this study, we investigate how different combinations of distributed energy technologies affect peak grid load, energy consumption from the grid, and emissions in the residential sector under time-varying prices. To do so, we develop an optimization framework in which households with varied amalgamations of distributed energy technologies minimize electricity costs, amortized capital, and operational costs over a year, with marginally increasing penalties for deviating from room temperature set-points. The four technologies we consider are: solar panels, lithium-ion batteries, ice cold thermal energy storage, and smart thermostats. The study also incorporates a one-parameter thermal model of the home, so that the discomfort penalties can apply to the room temperature rather than the total appliance load. Based on empirical energy consumption profiles and solar generation data from 25 homes in Austin, we find that residential customers would keep overall annual expenditure and environmental footprint low by investing in solar panels and smart thermostats. The capital costs of both storage systems are still too high to make them economically profitable investments for typical residential customers. Additionally, the Value of Solar policy disincentivizes solar customer investment in storage systems. The study also shows that, while the energetic effect of the two storage systems can be favorable or detrimental depending upon the pricing structure and the household load profile, lithium-ion batteries are the main instruments to avoid high demand charges. Thus, we recommend that, as an effective peak load control mechanism, electric utilities should offer significant rebates to encourage residential customer investment in storage systems in addition to subjecting them to demand charges.

Holistic Privacy for Electricity, Water, and Natural Gas Metering in Next Generation Smart Homes

In smart electricity grids, high time granularity (HTG) power consumption data can be decomposed into individual appliance load signatures via nonintrusive appliance load monitoring techniques to expose appliance usage profiles. Various methods ranging from load shaping to noise addition and data aggregation have been proposed to mitigate this problem. However, with the growing scarcity of natural resources, utilities other than electricity (e.g., water and natural gas) have also begun to be subject to HTG metering, which creates privacy issues similar to that of electricity. Therefore, employing privacy protection countermeasures for only electricity usage is ineffective for appliances that utilize additional/other metered resources. As such, existing privacy countermeasures and metrics need to be reevaluated to address not only electricity, but also any other resource that is metered. Furthermore, a holistic privacy protection approach for all metered resources must be adopted as the information leak from any of the resources has the potential to render the privacy preserving countermeasures for all the other resources futile. This article introduces the privacy preservation problem for multiple HTG metered resources and explores potential solutions for its mitigation.

Artificial Bee Colony Optimization Based Non-Intrusive Appliances Load Monitoring Technique in a Smart Home

Recent advances of energy management system in a smart home can lead to load monitoring of electrical appliances for energy saving and reduction of electricity bill. Thus, smart metering technology is getting widely implemented in several electricity distribution networks. Most of the existing research are concentrated towards individual power consumption of different household loads using some machine learning algorithm, which can increase computational burden of the processor. In this article, an improved method for estimation of the individual appliance current is carried out from a group of connected consumer electronics loads. The proposed method consists of two steps, first is to collect and store the current data of individual appliances with varying load for on line application. The second step is to estimate the individual load current using the stored data. In the proposed method, a search-based optimization, i.e., Artificial Bee Colony (ABC) algorithm is used for the estimation of individual electrical load. Suitable simulations and experimental studies are carried out on a practical household system to demonstrate the suitability of the proposed methodology.

IoT Based Approach for Load Monitoring and Activity Recognition in Smart Homes

Appliance load monitoring in smart homes has been gaining importance due to its significant advantages in achieving an energy efficient smart grid. The methods to manage such processes can be classified into hardware-based methods, including intrusive load monitoring (ILM) and software-based methods referring to non-intrusive load monitoring (NILM). ILM is based on low-end meter devices attached to home appliances in opposition to NILM techniques, where only a single point of sensing is needed. Although ILM solutions can be relatively expensive, they provide higher efficiency and reliability than NILMs. Moreover, future solutions are expected to be hybrid, combining the benefits of NILM along with individual power measurement by smart plugs and smart appliances. This paper proposes a novel ILM approach for load monitoring that aims to develop an activity recognition system based on IoT architecture. The proposed IoT architecture consists of the appliances layer, perception layer, communication network layer, middleware layer, and application layer. The main function of the appliance recognition module is to label sensor data and allow the implementation of different home applications. Three different classifier models are tested using real data from the UK-DALE dataset: feed-forward neural network (FFNN), long short-term memory (LSTM), and support vector machine (SVM). The developed activities of daily living (ADL) algorithm maps each ADL to a set of criteria depending on the appliance used. The features are extracted according to the consumption in Watt-hours and the times where they are switched on. In the FFNN and the LSTM networks, the accuracy is above 0.9 while around 0.8 for the SVM network. Other experiments are performed to evaluate the classifier model using a new test set. A sensitivity analysis is also carried out to study the impact of the group size on the classifier accuracy.

Identification Method of Electrical Load for Electrical Appliances Based on K-Means ++ and GCN

Most cluster identification studies regarding consumer electricity load is faced with problems of erroneous clustering method similarity, low clustering quality and poor identification accuracy. To solve these problems, this paper utilizes the elbow method, k- Means ++, entropy weight method and a graph convolutional neural network to provide a means for cluster identification based on electrical appliance power data collected via smart sockets. In this article, elbow and entropy weight methods were used to achieve the adaptive clustering algorithm. To obtain the electrical appliance load curves, Euclidean and dynamic time warping (DTW) distances were integrated and the similarity measurement method was used to improve the k-means ++ algorithm, which was then applied to data collected via smart socket clustering. Next, clustering results were input into the graph convolutional neural network (GCN) for identification purposes and appliance type information was obtained. Finally, experiments were conducted using electrical load data from 20 commercial users. The method used was a combination of the k-means algorithm and long short-term memory network (LSTM). The results show that under optimal K value conditions (as determined by the elbow score), the methods used in this paper have improved clustering quality and recognition accuracy, when compared to LSTM.

Surrogate-Assisted Multi-Objective Probabilistic Optimal Power Flow for Distribution Network With Photovoltaic Generation and Electric Vehicles

The uncertainties of solar photovoltaics generation, electric vehicle charging demand, and home appliances load are the major challenge of energy management planning in the residential areas. Optimal allocation of battery energy storage systems for distribution networks based on probabilistic power flow (PPF) is an effective solution to deal with these uncertainties. However, the high computational burden is the main obstacle of this method. Therefore, this paper proposes a surrogate-assisted multi-objective probabilistic optimal power flow (POPF) to reduce the expensive computational time. The surrogate model is developed by using a machine learning method namely deep learning which is used for bypassing the deterministic load flow calculation. Zhao’s point estimation method combined with Nataf transformation is selected to handle the PPF analysis considering correlated uncertain input variables. The multi-objective POPF problem is solved using the multi-objective differential evolution. The historical data including solar irradiation, ambient temperature, residential load, and electric vehicle (EV) travel distance is calculated in the low voltage distribution system to demonstrate the potential advantages of the proposed method. Numerical results show that the proposed surrogate assisted multi-objective POPF method provides the optimal solution for operating cost, helps to prolong transformer life and reducing environmental impact. Moreover, the results show that the proposed surrogate-assisted optimization framework gives a better solution when comparing with the conventional surrogate-assisted method.

A Fair Pricing Mechanism in Smart Grids for Low Energy Consumption Users

Based on energy demand, consumers can be broadly categorized into low energy consumers (LECs) and high energy consumers (HECs). HECs use heavy load appliances, e.g., electric heaters and air conditioners, and LECs do not use heavy load appliances. Thus, HECs demand more energy compared to LECs. The usage of high energy consumption appliances by HECs leads to peak formation in various time intervals. Different pricing schemes, i.e., time of use (ToU), real time pricing (RTP), inclined block rate (IBR), and critical peak pricing (CPP), have been proposed previously. In ToU, an energy tariff is divided into three blocks, i.e., on-peak (high rates), off-peak (low rates), and mid-peak (between on-peak and off-peak rates) hours, and these rates are applied to all electricity users without distinction. The high energy demand by HECs causes the high peak formation; thus, higher rates should be applied to only HECs rather than all consumers, which is not the case in existing billing mechanisms. LECs are also charged higher rates in on-peak intervals and this billing mechanisms are unjustified. Thus, in this paper, a fair pricing scheme (FPS) based on power demand forecasting is developed to reduce extra bills of LECs. First, we developed a machine learning-based electricity load forecasting method, i.e., an extreme learning machine (ELM), in order to differentiate LECs and HECs. With the proposed FPS, electricity cost calculations for LECs and HECs are based on the actual energy consumption; thus, LECs do not subsidize HECs. Simulations were conducted for performance evaluation of our proposed FPS mechanism, and the results demonstrate LECs can reduce electricity cost up to 11.0075%, and HECs are charged relatively higher than previous pricing schemes as a penalty for their contribution to the on-peak formation. As a result, a fairer system is realized, and the total revenue of the utility company is assured.

Electrical Energy Prediction in Residential Buildings for Short-Term Horizons Using Hybrid Deep Learning Strategy

Smart grid technology based on renewable energy and energy storage systems are attracting considerable attention towards energy crises. Accurate and reliable model for electricity prediction is considered a key factor for a suitable energy management policy. Currently, electricity consumption is rapidly increasing due to the rise in human population and technology development. Therefore, in this study, we established a two-step methodology for residential building load prediction, which comprises two stages: in the first stage, the raw data of electricity consumption are refined for effective training; and the second step includes a hybrid model with the integration of convolutional neural network (CNN) and multilayer bidirectional gated recurrent unit (MB-GRU). The CNN layers are incorporated into the model as a feature extractor, while MB-GRU learns the sequences between electricity consumption data. The proposed model is evaluated using the root mean square error (RMSE), mean square error (MSE), and mean absolute error (MAE) metrics. Finally, our model is assessed over benchmark datasets that exhibited an extensive drop in the error rate in comparison to other techniques. The results indicated that the proposed model reduced errors over the individual household electricity consumption prediction (IHEPC) dataset (i.e., RMSE (5%), MSE (4%), and MAE (4%)), and for the appliances load prediction (AEP) dataset (i.e., RMSE (2%), and MAE (1%)).

Artificial Intelligence, Accelerated in Parallel Computing and Applied to Nonintrusive Appliance Load Monitoring for Residential Demand-Side Management in a Smart Grid: A Comparative Study

A smart grid is a promising use-case of AIoT (AI (artificial intelligence) across IoT (internet of things)) that enables bidirectional communication among utilities that arises with demand response (DR) schemes for demand-side management (DSM) and consumers that manage their power demands according to received DR signals. Disaggregating composite electric energy consumption data from a single minimal set of plug-panel current and voltage sensors installed at the electric panel in a practical field of interest, nonintrusive appliance load monitoring (NIALM), a cost-effective load disaggregation approach for (residential) DSM, is able to discern individual electrical appliances concerned without accessing each of them by individual plug-load power meters (smart plugs) deployed intrusively. The most common load disaggregation approaches are based on machine learning algorithms such as artificial neural networks, while approaches based on evolutionary computing, metaheuristic algorithms considered as global optimization and search techniques, have recently caught the attention of researchers. This paper presents a genetic algorithm, developed in consideration of parallel evolutionary computing, and aims to address NIALM, whereby load disaggregation from composite electric energy consumption data is declared as a combinatorial optimization problem and is solved by the algorithm. The algorithm is accelerated in parallel, as it would involve large amounts of NIALM data disaggregated through evolutionary computing, chromosomes, and/or evolutionary cycles to dominate its performance in load disaggregation and excessively cost its execution time. Moreover, the evolutionary computing implementation based on parallel computing, a feed-forward, multilayer artificial neural network that can learn from training data across all available workers of a parallel pool on a machine (in parallel computing) addresses the same NIALM/load disaggregation. Where, a comparative study is made in this paper. The presented methodology is experimentally validated by and applied on a publicly available reference dataset.

Local and centralized conditioning systems

This article discusses two main types of air conditioning systems in office buildings: local and centralized systems. Since equipment developers, customers and users have different requirements for the design, installation and operation of air conditioning systems in office buildings, depending on the workload of buildings, location, external conditions, as well as space-planning solutions, air conditioning systems currently come in different types and configurations. Reliable knowledge of classification and the ability to distinguish one system from another is key when choosing the right air conditioning system for the customer. To form a proper understanding of the systems discussed, it is necessary to understand some of the basic terminology and principles of air conditioning systems. These include methods for system design criteria, load calculations (tangible and latent thermal loads, penetration loads, equipment and appliance loads, and air conditioning system requirements).

Remote Appliance Load Monitoring and Identification in a Modern Residential System With Smart Meter Data

In this article, an innovative procedure for residential electrical load monitoring applicable to smart meters is proposed based on a modified decisive multi-objective optimization. In this procedure, different load features are extracted from household loads for optimization-based monitoring. Each load monitoring feature reflects an objective function, which is also simultaneously minimized using modified Artificial Bee Colony (ABC) algorithm. This technique is not heavily dependent on high amount of training data which is essential for the most machine learning techniques with some modification in choosing the initial search space. The proposed technique uses with real life raw data using low sampling rates. An Internet of Things (IoT) based approach is also implemented for remote monitoring of connected loads in the system along with monitoring. The proposed technique is user friendly, requires only load signature data for verification purpose which can be easily extracted. The paper demonstrates event-based appliance load monitoring and comparison with benchmark dataset which shows marked improvement over existing state-of-the-art-techniques.