To this day, hyperparameter tuning remains a cumbersome task in Non-Intrusive Load Monitoring (NILM) research, as researchers and practitioners are forced to invest a considerable amount of time in this task. This paper proposes adaptive weighted recurrence graph blocks (AWRG) for appliance feature representation in event-based NILM. An AWRG block can be combined with traditional deep neural network architectures such as Convolutional Neural Networks for appliance recognition. Our approach transforms one cycle per activation current into an weighted recurrence graph and treats the associated hyper-parameters as learn-able parameters. We evaluate our technique on two energy datasets, the industrial dataset LILACD and the residential PLAID dataset. The outcome of our experiments shows that transforming current waveforms into weighted recurrence graphs provides a better feature representation and thus, improved classification results. It is concluded that our approach can guarantee uniqueness of appliance features, leading to enhanced generalisation abilities when compared to the widely researched V-I image features. Furthermore, we show that the initialisation parameters of the AWRG’s have a significant impact on the performance and training convergence.

The increased penetration of Renewable Energy Sources (RES) as part of a decentralized and distributed power system makes net-load forecasting a critical component in the planning and operation of power systems. However, compared to the transmission level, producing accurate short-term net-load forecasts at the distribution level is complex due to the small number of consumers. Moreover, owing to the stochastic nature of RES, it is necessary to quantify the uncertainty of the forecasted net-load at any given time, which is critical for the real-world decision process. This work presents parameterized deep quantile regression for short-term probabilistic net-load forecasting at the distribution level. To be precise, we use a Deep Neural Network (DNN) to learn both the quantile fractions and quantile values of the quantile function. Furthermore, we propose a scoring metric that reflects the trade-off between predictive uncertainty performance and forecast accuracy. We evaluate the proposed techniques on historical real-world data from a low-voltage distribution substation and further assess its robustness when applied in real-time. The experiment’s outcomes show that the resulting forecasts from our approach are well-calibrated and provide a desirable trade-off between forecasting accuracies and predictive uncertainty performance that are very robust even when applied in real-time.

The key advantage of smart meters over traditional metering devices is their ability to transfer consumption information to remote data processing systems. Besides enabling the automated collection of a customer’s electricity consumption for billing purposes, the data collected by these devices makes the realization of many novel use cases possible. However, the large majority of such services are tailored to improve the power grid’s operation as a whole. For example, forecasts of household energy consumption or photovoltaic production allow for improved power plant generation scheduling. Similarly, the detection of anomalous consumption patterns can indicate electricity theft and serve as a trigger for corresponding investigations. Even though customers can directly influence their electrical energy consumption, the range of use cases to the users’ benefit remains much smaller than those that benefit the grid in general. In this work, we thus review the range of services tailored to the needs of end-customers. By briefly discussing their technological foundations and their potential impact on future developments, we highlight the great potentials of utilizing smart meter data from a user-centric perspective. Several open research challenges in this domain, arising from the shortcomings of state-of-the-art data communication and processing methods, are furthermore given. We expect their investigation to lead to significant advancements in data processing services and ultimately raise the customer experience of operating smart meters.

The advance in energy-sensing and smart-meter technologies have motivated the use of a Non-Intrusive Load Monitoring (NILM), a data-driven technique that recognizes active end-use appliances by analyzing the data streams coming from these devices. NILM offers an electricity consumption pattern of individual loads at consumer premises, which is crucial in the design of energy efficiency and energy demand management strategies in buildings. Appliance classification, also known as load identification is an essential sub-task for identifying the type and status of an unknown load from appliance features extracted from the aggregate power signal. Most of the existing work for appliance recognition in NILM uses a single-label learning strategy which, assumes only one appliance is active at a time. This assumption ignores the fact that multiple devices can be active simultaneously and requires a perfect event detector to recognize the appliance. In this paper proposes the Convolutional Neural Network (CNN)-based multi-label learning approach, which links multiple loads to an observed aggregate current signal. Our approach applies the Fryze power theory to decompose the current features into active and non-active components and use the Euclidean distance similarity function to transform the decomposed current into an image-like representation which, is used as input to the CNN. Experimental results suggest that the proposed approach is sufficient for recognizing multiple appliances from aggregated measurements.

Appliance recognition is one of the vital sub-tasks of NILM in which a machine learning classier is used to detect and recognize active appliances from power measurements. The performance of the appliance classifier highly depends on the signal features used to characterize the loads. Recently, different appliance features derived from the voltage–current (V–I) waveforms have been extensively used to describe appliances. However, the performance of V–I-based approaches is still unsatisfactory as it is still not distinctive enough to recognize devices that fall into the same category. Instead, we propose an appliance recognition method utilizing the recurrence graph (RG) technique and convolutional neural networks (CNNs). We introduce the weighted recurrent graph (WRG) generation that, given one-cycle current and voltage, produces an image-like representation with more values than the binary output created by RG. Experimental results on three different sub-metered datasets show that the proposed WRG-based image representation provides superior feature representation and, therefore, improves classification performance compared to V–I-based features.

Power demand forecasting is becoming a crucial tool for the planning and operation of Low Voltage (LV) distribution systems. Most importantly, the high penetration of Photovoltaics (PV) power generation as part of Distributed Energy Resource (DER)s has transformed the power demand forecasting problem at the distribution level into net-load forecasting. This paper introduces a novel and scalable approach to probabilistic forecasting at LV substation with PV generation. It presents a multi-variates probabilistic forecasting approach, leveraging Quantile Regression (QR). The proposed architecture uses a computationally efficient feed-forward neural net to capture the complex interaction between the historical load demands and covariate variables such as solar irradiance. It is empirically demonstrated that the proposed method can efficiently produce well-calibrated forecasts, both auto-regressively or in a single forward pass. Furthermore, a benchmark against four state-of-the-art forecasting approaches shows that the proposed approach offers a desirable trade-off between forecasting accuracies, calibrated uncertainty, and computation complexity.