Fixing energy leakage caused by diferent anomalies can result in significant energy savings and extended appliance life. Further, it assists grid operators in scheduling their resources to meet the actual needs of end users, while helping end users reduce their energy costs. In this paper, we analyze the patterns pertaining to the power consumption of dishwashers used in two houses of the REFIT dataset. Then two autoencoder (AE) architectures with 1D-CNN and TCN as backbones are trained to diferentiate the normal patterns from the abnormal ones. Our results indicate that TCN outperforms CNN1D in detecting anomalies in energy consumption. Finally, the data from the Fridge_Freezer and the Freezer of house No. 3 in REFIT is also used to evaluate our approach.
higher power consumption or damage in the most critical
cases [
Throughout recent years, the energy demand has signifi- Thus, for optimization purposes in smart homes, via
cantly gone up due to urban and industrial development implementing load monitoring systems and formulating
alongside an increase in population [
To this end, utilizing AI-based technologies and smart 1-dimensional CNN and TCN, to detect abnormal usage.
homes as novel interventions to recognize abnormal For this purpose, any predicted value that is greater than
power utilization and understand the reasons for each ab- twice the standard deviation of the electricity
consumpnormality could pave the way for end-consumers both to tion the day before is considered abnormal.
renovate wasteful devices and adopt a more sustainable The rest of the paper is organized as follows. We
proenergy consumption behavior [
In addition, electrical anomalies are less likely to remain unnoticed for a long period of time which would result in 2. Related work method, the feature representations are enforced to learn important regularities of the data so that reconstruction errors are minimized. Consequently, anomalies are dififcult to reconstruct from the resulting representations and are, therefore, subject to large reconstruction errors [17].
tain cleaned electrical consumption data in Watts for 20
households in the UK at both the aggregate and
appliFigure 1: The architecture of the CNN-based autoencoder ance level. The data is related to a period of two years
(CNN-AE) comprising nine individual appliance measurements at
8-second intervals per house with 1,194,958,790 readings
[16]. The models proposed in this paper are trained using
level monitoring devices are needed to continuously mon- dishwasher data from houses No. 1 and 2. Furthermore,
itor the power consumption of individual appliances in data from the Fridge_Freezer and the Freezer of house
a house [
Autoencoder-based approaches are often used to identify by a factor of . To do so, groups of size are averaged anomalous behavior by analyzing the reconstruction er- along the time axis. ror of the data [18][19][20]. Having learned a nonlinear In the decoder module, the downsampled sequence transformation of the input data into a compressed rep- is returned to its original length by performing a nearresentation, latent variables are used to reconstruct the est neighbor interpolation on the upsampled sequence. original input. On the other hand, utilizing the convolu- Upsampled sequences are passed through a second TCN tion mechanism in sequential models is computationally with independent weights parameterized similarly to the optimal [21]. Also, due to CNNs’ equivariance proper- encoder-TCN. As a final step, the input sequence is reties and sparse interactions, they are translated from constructed with a Conv1D layer that ensures that the computer vision into the time domain using temporal dimensionality of the input is matched (by setting = 1 convolutional networks (TCN)[20]. and = ) [20]. As described in the next section,
In the following sections, we will describe how we the input sequence and its reconstruction will be used used autoencoders (AEs) for time series data that utilize for detecting anomalies after TCN-AE has been trained. 1-dimensional CNNs and TCNs as building blocks to detect energy anomalies in the REFIT dataset.
3.3.1. Anomaly detection 3.2.1. CNN-based autoencoder (CNN-AE) We used TensorFlow to implement the architecture consisting of two smaller sequential models, an encoder and a decoder. Also, considering the speed of the model convergence, our CNN-based autoencoder is comprised of 3 layers of Conv1D using the data of the households’ dishwashers. Furthermore, a nonlinear ReLu activation function is used in each convolution layer. In this model, a standard rate of 0.2 is considered for the dropout layer to randomly remove 20% of the upper layer during learning.
Figure 1. shows the layers and the number of input and output parameters of each. The input layer is 320 × 1 (3200 seconds), calculated according to the maximum operation time of the device. 3.2.2. TCN-based autoencoder (TCN-AE) The temporal convolutional network (TCN) combines simplicity with auto-regressive prediction, residual blocks, and a very long memory. In general, a TCN can be broken down into three components: a list of dilation rates = {1, 2, ..., }, the number of , and the kernel size , which is the same for all filters in a TCN [20][22]. Inspired by a classical (deep) autoencoder, the TCN autoencoder encodes sequences, along the temporal axis, of length into a compressed representation of length / (where ∈ Z+) and then tries to reconstruct the original sequence[20]. √︂ ∑︀
In Figure 2, each layer of the TCN-AE is described = =1( − )2 (2) by its parameters within the box. TCN-AE receives a sequence [] of length and dimensionality as its ℎℎ = ̂︀ + 2 (3) input. Using a TCN, the encoder first processes input sequence [] of length and dimension . Afterward, a where is the standard deviation, ℎℎ is the one-dimensional convolutional layer with = 1, = 1, threshold, ̂︀ is the predicted value, is the electricity and = 8 is used to reduce the dimensionality of consumption, is the average electricity consumption, the TCN’s output. As the last layer in the encoder, the and is the number of samples. temporal average pooling layer downsamples the series A normal electricity usage pattern detection for the dishwasher is shown in Figure 3 (a), where the real-time We compute a threshold value of 2 above the predicted value to measure the trend in electricity consumption over time, where 2 is the standard deviation on the day before the actual moment [23]. An abnormal state is defined as a value exceeding the threshold for predicted electricity consumption at the actual moment. Equations (2) and (3) show the calculation of and ℎℎ:
Division Ratio
Division Ratio threshold curve follows the sequence trend, indicating tection techniques, abnormal behaviors can be mitigated. the model depicts the dishwasher’s normal electricity us- This is possible, especially if user-centric explainable age. As can be seen in the gfiure, the real power consump- recommender systems are combined with anomaly detion curve does not exceed the threshold range, which tection modules. However, there is no proper labeled indicates a normal level of electricity consumption. As dataset available to develop accurate algorithms or deshown in Figure 3 (b), anomalous consumption patterns tect diferent types of anomalies. Accordingly, we plan to occur when actual values exceed the threshold. Conse- run a laboratory to build the first appropriately labeled quently, the method can distinguish between normal and energy anomaly dataset. abnormal consumption behavior. 3.3.2. Evaluation
best performance is obtained with the data division ratio of 8:2, and clearly, TCN-AE is more eficient than CNNAE. Our unsupervised approach has also been evaluated using the data from the Fridge_Freezer and the Freezer of house No. 3 in REFIT. The results in Table 3. confirm the best division ratio of 8:2 and the higher performance of TCN compared to CNN1D.
This paper presents the starting point of our work on studying how would applying deep learning algorithms, and explainability improve energy eficiency, environmental sustainability, and user adoption. In this regard, ifrst, we preprocessed our data by resampling and diferentiating each usage. Next, the extracted patterns of dishwasher usage in houses No. 1 and 2 of the REFIT dataset were analyzed. Two deep learning models, CNN-AE and TCN-AE were then trained to detect abnormalities. While the TCN backbone performed better, we evaluated our models using the data from the refrigerators of house No. 3 in REFIT as well.
Through the implementation of energy monitoring systems and the formulation of intelligent anomaly de
Model