Electricity Data Research Articles

Global Identification of Unelectrified Built-Up Areas by Remote Sensing

Access to electricity (the proportion of the population with access to electricity) is a key indica for of the United Nations’ Sustainable Development Goal 7 (SDG7), which aims to provide affordable, reliable, sustainable, and modern energy services for all. Accurate and timely global data on access to electricity in all countries is important for the achievement of SDG7. Current survey-based access to electricity datasets suffers from short time spans, slow updates, high acquisition costs, and a lack of location data. Accordingly, a new method for identifying the electrification status of built-up areas based on the remote sensing of nighttime light is proposed in this study. More specifically, the method overlays global built-up area data with night-time light remote sensing data to determine whether built-up areas are electrified based on a threshold night-time light value. By using our approach, electrified and unelectrified built-up areas were extracted at 500 m resolution on a global scale for the years 2014 and 2020. The acquired results show a significant reduction in an unelectrified built-up area between 2014 and 2020, from 51,301.14 km2 to 22,192.52 km2, or from 3.05% to 1.32% of the total built-up area. Compared to 2014, 117 countries or territories had improved access to electricity, and 18 increased their proportion of unelectrified built-up area by >0.1%. The identification accuracy was evaluated by using a random sample of 10,106 points. The accuracies in 2014 and 2020 were 97.29% and 98.9%, respectively, with an average of 98.1%. The outcomes of this method are in high agreement with the spatial distribution of access to electricity data reported by the World Bank. This study is the first to investigate the global electrification of built-up areas by using remote sensing. It makes an important supplement to global data on access to electricity, which can aid in the achievement of SDG7.

Timing shift-based bi-residual network model for the detection of electricity stealing

With the increasing number of electricity stealing users, the interests of countries are jeopardized and it brings economic burden to the government. However, due to the small-scale stealing and its random time coherence, it is difficult to find electricity stealing users. To solve this issue, we first generate the hybrid dataset composed of real electricity data and specific electricity stealing data. Then, we put forward the timing shift-based bi-residual network (TS-BiResNet) model. It learns the features of electricity consumption data on two aspects, i.e., shallow features and deep features, and meanwhile takes time factor into consideration. The simulation results show that TS-BiResNet model can detect electricity stealing behaviors that are small scaled and randomly coherent with time. Besides, its detection accuracy is superior to the benchmark schemes, i.e., long short-term memory (LSTM), gated recurrent unit (GRU), combined convolutional neural network and LSTM (CNN-LSTM) and Bi-ResNet.

Mechanism design for data sharing: An electricity retail perspective

Information incompletion always forces market participants to make decisions under uncertainty in energy transactions, while obtaining related data is a feasible way for them to reduce uncertainty and gain profits. However, the application of data transactions is not yet mature. To extend the application range of data transactions and concretize the data transaction model, a novel framework of electricity-side and data-side transactions linked with data sharing is proposed from the electricity retail perspective in this paper. The necessity and processes of data sharing between the electricity retailer and data suppliers are elaborately illustrated in the framework. Data revenues and data costs are analyzed according to uncertainty reduction and information provision. Considering the widely used two-settlement system of electricity markets, data revenues and data costs can be expressed in closed forms and their differences are net profits that are regarded to drive the data flow. Furthermore, an ex-post profit allocation mechanism is matched to appropriately allocate the net profits between the electricity retailer and data suppliers in the data sharing model. By comparison with the Shapley value method, the mechanism is less time-consuming and will ensure the profitability of the electricity retailer. Finally, a practical case with real data is employed to realize the results proposed in the theoretical analysis, and the feasibility of the data sharing model and profit allocation mechanism is validated.

European Energy Regulatory, Socioeconomic, and Organizational Aspects: An Analysis of Barriers Related to Data-Driven Services across Electricity Sectors

Data-driven services offer a major shift away from traditional monitoring and control approaches that have been applied exclusively over the transmission and distribution networks. These services assist the electricity value chain stakeholders to enhance their data reach and improve their internal intelligence on electricity-related optimization functions. However, the penetration of data-driven services within the energy sector poses challenges across the regulatory, socioeconomic, and organizational (RSEO) domains that are specific to such business models. The present review examines the existence and importance of various obstacles across these domains regarding innovative energy services, new business models, data exchanges, and other actors’ synergies across the electricity data value chain. This research is centered around the European landscape, with a particular focus on the five demonstration countries (Greece, Spain, Austria, Finland, and Croatia) of the SYNERGY consortium. A state-of-the-art analysis on the regulatory, socioeconomic, and organizational aspects related to innovative energy services (IESs) revealed a plethora of such potential obstacles that could affect, in various degrees, the realization of such services, both at a prototyping and a market replication level. More specifically, 13 barriers were identified in the regulatory domain, 19 barriers were identified in the socioeconomic domain, and 16 barriers were identified in the organizational domain. Then, a comprehensive, survey-based data gathering exercise was designed, formulated, and conducted at a national level as well as at a stakeholder type level. To ensure that our analysis encompassed business-wide perspectives and was validated from the whole electricity data value chain, we utilized a trilevel analysis (i.e., partner, stakeholder type, demo country) to formulate qualitative interviews with business experts from each stakeholder type (namely TSOs, DSOs, aggregators/ESCOs, facility managers/urban planners, and RES Operators). By combining the quantitative data with the qualitative interviews, further recommendations on identifying and facilitating ways to overcome the identified barriers are provided. For the regulatory domain, it is recommended to treat nationally missing regulations by conforming to the provisions of the relevant EU directives, as well as to provide a flexibility-related regulation. For the socioeconomic domain, recommendations were made to increase consumer awareness and thus alleviate the three more impactful barriers identified in this domain. All organizational barriers can be alleviated by taking complex big-data-related issues away from the hands of the organizations and offering them data-as-a-service mechanisms that safeguard data confidentiality and increase data quality.

A PCA-based variable ranking and selection approach for electric energy load forecasting

PurposeThis paper aims to propose an approach based upon the principal component analysis (PCA) to define a contribution rate for each variable and then select the main variables as inputs to a neural network for energy load forecasting in the region southeastern Brazil.Design/methodology/approachThe proposed approach defines a contribution rate of each variable as a weighted sum of the inner product between the variable and each principal component. So, the contribution rate is used for selecting the most important features of 27 variables and 6,815 electricity data for a multilayer perceptron network backpropagation prediction model. Several tests, starting from the most significant variable as input, and adding the next most significant variable and so on, are accomplished to predict energy load (GWh). The Kaiser–Meyer–Olkin and Bartlett sphericity tests were used to verify the overall consistency of the data for factor analysis.FindingsAlthough energy load forecasting is an area for which databases with tens or hundreds of variables are available, the approach could select only six variables that contribute more than 85% for the model. While the contribution rates of the variables of the plants, plus energy exchange added, have only 14.14% of contribution, the variable the stored energy has a contribution rate of 26.31% being fundamental for the prediction accuracy.Originality/valueBesides improving the forecasting accuracy and providing a faster predictor, the proposed PCA-based approach for calculating the contribution rate of input variables providing a better understanding of the underlying process that generated the data, which is fundamental to the Brazilian reality due to the accentuated climatic and economic variations.

Secure Multi-Dimensional and Multi-Angle Electricity Data Aggregation Scheme for Fog Computing-Based Smart Metering System

Smart Meters (SMs) can regularly report their detailed real time electricity consumption data to utility company, which can improve the balance of electrical load and the efficiency of energy usage. However, the fine-grained electricity data reported by smart meters is easy to disclose the privacy of users. Therefore, data aggregation technology is often used to protect the privacy of users. Currently the existing data aggregation schemes cannot meet the requirement of further fine-grained analysis. In this paper, we propose a multi-dimensional and multi-angle electricity data aggregation scheme for fog computing-based smart metering system. In our proposed scheme, the smart meters use the super-incremental sequence matrix to structure and encrypt their obtained electricity consumption data; the fog nodes regularly collect and aggregate these ciphertexts of electricity consumption data by using the homomorphic Paillier cryptosystem; the control center decrypts the aggregated ciphertext to obtain multi-dimensional and multi-angle electricity data, which is accurate to the types of household appliances and their corresponding electricity angles (energy efficiency indexes). According to the security requirements, we analyze the security of our proposed scheme, which can achieve identity anonymity. Additionally, the experimental results show our scheme is efficient.

Anomaly Detection and Classification of Household Electricity Data: A Time Window and Multilayer Hierarchical Network Approach

With the increasing popularity of the smart grid, huge volumes of data are gathered from numerous sensors. How to classify, store, and analyze massive data sets to facilitate the development of the smart grid has recently attracted much attention. In particular, with the popularity of household smart meters and electricity monitoring sensors, a large amount of data can be obtained to analyze household electricity usage so as to better diagnose the leakage and theft behaviors, identify man-made tampering and data fraud, and detect powerline loss. In this article, the time window method is first proposed to obtain the features and potential periodicity of household electricity data. Combining the denoising ability of the autoencoder and the induction ability of the feedforward neural network, a multilayer hierarchical network (MLHN) is then established to detect anomalies in single sensor data and classify multiple groups of sensor data, respectively. The experimental results show that the accuracy of detecting abnormal data and data classification is significantly improved compared with the presented scheme.

Impacts of electric-driven heat pumps on residential electricity consumption: An empirical analysis from Arizona, USA

Heat pumps play an important role in the electrification of the residential sector. The electrification of building energy consumption can have a significant impact on the load management of the electric grid. This study provides the first empirical investigation of the changes in hour-of-day loads after adopting heat pumps. We apply unique hourly electricity data for 13,010 residential consumers in Arizona during 2014–2019. Statistical matching, fixed effects regression, and difference-in-differences approach are applied to analyze electricity consumption. Contrary to the predictions from engineering models which indicate energy savings after heat pump adoption, our main analysis suggests that heat pumps do not necessarily save electricity for cooling and heating in Arizona. Besides, we also quantify the increase in electricity consumption when switching from natural gas furnaces to heat pumps. The increased environmental damages from electricity changes are estimated to be $0.59 per household during the summer and $1.64 during the winter. This also indicates an increase for electric loads by 8.8 (2.7) MW in the winter (summer) if all SRP utility consumers shifted to heat pumps. The findings have implications for the energy performance of heat pumps at households. The results could also help improve the sustainability of the electric sector, which can integrate more clean energy into a smarter grid.

Deadline-constrained energy-aware workflow scheduling in geographically distributed cloud data centers

The energy cost of cloud data centers is increasingly concerned worldwide; the minimization of energy cost is becoming an urgent problem. Considering data centers are geographically distributed, electricity prices are different in each data center. Consequently, it is also critical to assign workflow tasks to the geographically distributed data centers because data required by tasks is usually conserved in the given data center. So, as electricity prices and data transmission times change, it becomes a big challenge to minimize energy costs when scheduling workflow tasks to heterogeneous servers in cloud data centers. A DEWS (Deadline-constrained Energy-aware Workflow Scheduling) algorithm is proposed in this paper, which consists of task sequencing, VND-based data center searches, task sequence adjustment, and VM searching with Dynamic Voltage Frequency Scaling (DVFS). The DVFS method is included in the optimization procedure to cut down the additional energy cost of service providers. The experimental results show that the proposed algorithm outperforms the compared algorithms and reduces energy cost by 5%–20%.

A Lightweight and Privacy-Friendly Data Aggregation Scheme against Abnormal Data.

Abnormal electricity data, caused by electricity theft or meter failure, leads to the inaccuracy of aggregation results. These inaccurate results not only harm the interests of users but also affect the decision-making of the power system. However, the existing data aggregation schemes do not consider the impact of abnormal data. How to filter out abnormal data is a challenge. To solve this problem, in this study, we propose a lightweight and privacy-friendly data aggregation scheme against abnormal data, in which the valid data can correctly be aggregated but abnormal data will be filtered out during the aggregation process. This is more suitable for resource-limited smart meters, due to the adoption of lightweight matrix encryption. The automatic filtering of abnormal data without additional processes and the detection of abnormal data sources are where our protocol outperforms other schemes. Finally, a detailed security analysis shows that the proposed scheme can protect the privacy of users’ data. In addition, the results of extensive simulations demonstrate that the additional computation cost to filter the abnormal data is within the acceptable range, which shows that our proposed scheme is still very effective.

MLTF: Model less time-series forecasting

Multi-step ahead long term forecasting remains a pertinent challenge in time series literature due to non-stationary behaviour of real-world data. Predominantly most traditional time series models are parametric in nature and they use the predicted values to generate forecast for future time steps. This leads to error accumulation in each step of the forecasting horizon which causes increasingly poorer forecast in long-term. Other than the problem of error accumulation, most parametric algorithms also require significant pre-processing, hyper-parameter tuning, training and post-processing which can often put high computational burden on the system. Therefore, this paper proposes, Model Less Time-series Forecasting (MLTF), a non-parametric approach for forecasting which does not require any pre-processing or traditional training (i.e. Backpropagation). MLTF is a non-parametric method which uses statistical representations such as trend, linearity, entropy etc. to cluster series from a pre-defined repository and the series from same cluster are tagged as similar series. The trajectory of the target series is extracted from these similar series after applying an adaptive re-sampling technique. There is minimal training involved in MLTF, therefore this framework is computationally very efficient. The model-less nature also enables it to not suffer from error accumulation in long-horizon forecast. MLTF is validated empirically with a rich set of experiments involving M1, M3 competition dataset, Electricity, Volatility and COVID-19 data (over 4500 independent uni-variate series of different frequencies i.e. Hourly, Daily, Monthly, Quarterly and Yearly). The experiments demonstrate that, MLTF is significantly faster while being similar (or better) in terms of forecasting accuracy than the state-of-the-art DL methods and other non-parametric time series model.

A deep LSTM network for the Spanish electricity consumption forecasting

Nowadays, electricity is a basic commodity necessary for the well-being of any modern society. Due to the growth in electricity consumption in recent years, mainly in large cities, electricity forecasting is key to the management of an efficient, sustainable and safe smart grid for the consumer. In this work, a deep neural network is proposed to address the electricity consumption forecasting in the short-term, namely, a long short-term memory (LSTM) network due to its ability to deal with sequential data such as time-series data. First, the optimal values for certain hyper-parameters have been obtained by a random search and a metaheuristic, called coronavirus optimization algorithm (CVOA), based on the propagation of the SARS-Cov-2 virus. Then, the optimal LSTM has been applied to predict the electricity demand with 4-h forecast horizon. Results using Spanish electricity data during nine years and half measured with 10-min frequency are presented and discussed. Finally, the performance of the proposed LSTM using random search and the LSTM using CVOA is compared, on the one hand, with that of recently published deep neural networks (such as a deep feed-forward neural network optimized with a grid search) and temporal fusion transformers optimized with a sampling algorithm, and, on the other hand, with traditional machine learning techniques, such as a linear regression, decision trees and tree-based ensemble techniques (gradient-boosted trees and random forest), achieving the smallest prediction error below 1.5%.

Spatiotemporal Modeling of the Electricity Production from Variable Renewable Energies in Germany

In recent years, electricity production from wind turbines and photovoltaic systems has grown significantly in Germany. To determine the multiple impacts of rising variable renewable energies on an increasingly decentralized power supply, spatially and temporally resolved data on the power generation are necessary or, at least, very helpful. Because of extensive data protection regulations in Germany, especially for smaller operators of renewable power plants, such detailed data are not freely accessible. In order to fill this information gap, simulation models employing publicly available plant and weather data can be used. The numerical simulations are performed for the year 2016 and consider an ensemble of almost 1.64 million variable renewable power plants in Germany. The obtained time series achieve a high agreement with measured feed-in patterns over the investigated year. Such disaggregated power generation data are very advantageous to analyze the energy transition in Germany on a spatiotemporally resolved scale. In addition, this study also derives meaningful key figures for such an analysis and presents the generated results as detailed maps at county level. To the best of our knowledge, such highly resolved electricity data of variable renewables for the entire German region have never been shown before.

Efficient Privacy-Preserving Data Aggregation Scheme with Fault Tolerance in Smart Grid

As the traditional grid produces a large amount of greenhouse gas and cannot adapt to such new demands as dynamic electricity prices, data analysis, and early warning, smart grid with high efficiency and reliability is increasingly valued. It plays a key role in achieving carbon neutrality. Nonetheless, smart grid requires the collection of real-time power data, and personal privacy may be leaked through the frequent electricity measurement reports. With the requirements of data analysis and prediction while preserving users’ personal privacy, data aggregation schemes have emerged. However, existing schemes cannot resolve all the troubles well. Some schemes do not consider the failures for smart meters, and most of the schemes have expensive computation cost. In view of this, an efficient privacy-preserving data aggregation scheme with fault tolerance in smart grid is put forward in this paper. To be specific, the proposed scheme is lightweight due to the application of the symmetric homomorphic encryption technology and the elliptic curve cryptography. Even if some smart meters are destroyed, the proposed scheme can still successfully obtain aggregated data. Moreover, the proposed data aggregation scheme is proved to be secure, and all security requirements can be satisfied. Performance evaluation illustrates the relatively low computation cost and communication overhead of the proposed scheme compared to other related schemes.

Seasonal variation of residential cooling use behaviour derived from energy demand data and stochastic building energy simulation

In recent years, a bottom-up approach based on building-energy simulations coupled with stochastic modelling of occupant behaviours has been intensively developed to properly estimate the effect of diverse and stochastic occupant behaviours on energy loads, mainly for developing smart building-energy-management systems and the promotion of renewable energy sources. Considering this background, the objective of this study is to elucidate the modelling of the state transitional probability of occupants’ heat pump (HP) use embedded in most bottom-up approaches based on statistical analysis of the 2-year electricity data of 586 dwellings. The analysis results clearly suggested that the relationship between daily hours of HP use and the daily mean outdoor air temperature has seasonal differences, in which frequency of HP use in early summer and early winter is lower than that in late summer and late winter under the same daily mean outdoor air temperature conditions. In addition, the authors presented statistical models of daily HP use hours with an explanatory variable of outdoor temperature for a lapse of 10 days to model the seasonal influence, and showed better performance compared to the model expressed by daily mean outdoor temperature. Furthermore, the authors revealed that such a seasonal change in behaviour is attributed to the state transitional probability of cooling use as a function of indoor thermal conditions based on a numerical simulation of the bottom-up approach. Finally, the authors proposed a revised model with the state transitional probability considering seasonal behaviour change, and the estimation results of household cooling use are consistent with the measured data.

Life cycle assessment of Irish district heating systems: a comparison of waste heat pump, biomass-based and conventional gas boiler

This paper presents a life cycle assessment of heat supply scenarios towards replacement of fossil-based energy systems through a case study focusing on an existing gas-fired boiler supplying heat for buildings located in Tallaght, Ireland. The three replacement systems considered are a waste heat-fed heat pump district heating system, a biomass-based district heating system, and an individual gas boiler. Current study found both the district heating systems have lower environmental impact than the conventional boiler system, with the biomass-based system being superior to heat pump. However, using 2030 electricity data showed almost similar impacts for both the district heating systems. Human toxicity potential was found highest among all impact categories studied due to the large additional infrastructure requirement across all three systems, whereas the other impacts, global warming, fossil fuel depletion and eutrophication, were due to involving usage of natural gas and electricity in use phase. The heating system employing biomass as resource showed reduced greenhouse gas (GHG) emissions by 45% and fossil fuel depletion by 73% compared to the conventional boiler. However, using 2030 electricity data, the heat pump system decreased GHG emissions by 42% and fossil fuel depletion by 47%. Further, replacing biomethane with the natural gas decreased global warming by at least 11.4%. The present study concludes that the environmental benefit of a district heating system is largely dependent on the carbon intensity of the electricity it uses, thus recommending the district heating systems for large-scale retrofitting schemes in Ireland to reach Europe’s 2030 GHG reduction targets.Graphic abstract

Do solar households want demand response and shared electricity data? Exploring motivation, ability and opportunity in Australia

The success of Australia's energy transition is dependent on households’ motivation, ability and opportunity to participate in it. This involves technologically-mediated participation in demand response, such as sharing control of solar or battery assets or sharing electricity data use/generation data with third parties. Applying the Motivation Opportunity Ability (MOA) framework, this paper uses in-depth interviews and speculative design with 39 Australian solar panel owners (“prosumers”) to understand the values and concerns driving their motivation and ability to participate. Fairness, autonomy, control, trust, privacy and collectivism affect participants’ motivation to curtail energy use, share control of solar/battery assets and share energy data, yet motivation does not guarantee ability to participate. The paper contributes and operationalises a provisional method for scoring Motivation, Ability in the MOA framework, toward better understanding customers’ potential use or participation in future energy technologies and interactions. This quantification overcomes limitations of existing scoring systems which do not adequately account for negative (rather than simply low) motivation. Findings suggest that increasing users’ ability with emergent technologies requires first increasing familiarity and further avenues for more involved consumer participation in the design of energy futures.

Scalable Fabrication of Metallic Conductive Fibers from Rheological Tunable Semi-Liquid Metals.

Conductive polymer fibers/wires (CPFs) are important materials in modern technologies due to their unique one-dimension geometry, electrical conductivity, and flexibility. However, the advanced applications of current CPFs are limited by their low electrical conductivities (<500 S/m) and poor interfacial interactions between conductive fillers (e.g., graphite) and polymers. Therefore, in current electrical applications, metal wires/foils like copper and aluminum are the most frequently utilized conductive fibers/wires instead of the inferior conductive CPFs. This work successfully addresses the heavy phase segregation between polymers and conductive inorganic materials to obtain semiliquid metal polymer fibers (SLMPFs) which exhibit an ultrahigh electrical conductivity (over 106 S/m), remarkable thermal processability, and considerable mechanical performance (Young's modulus: ~300 MPa). Semiliquid metal (gallium-tin alloy) with tunable viscosities is the key to achieve the excellent miscibility between metals and polymers. Both the rheological results and numerical simulations demonstrate the critical viscosity matching for the successful preparation of the fibers. More importantly, the fibers are adapted with classic polymer melt-processing like melt injection, which indicates the scalable production of the highly conductive fibers. The SLMPFs are highly promising substitutes for metal wires/fibers in modern electrical applications such as electricity transmission, data communication, and underwater works.

Application of Federated Learning Algorithm Based on K-Means in Electric Power Data

Accurate electricity forecasting is the key basis for guiding the power sector to arrange operation plans and guaranteeing the profitability of electric power companies. However, with the increasing demand of enterprises and departments for data security, the phenomenon of “Isolated Data Island” becomes more and more serious, resulting in the accuracy loss of the traditional electricity prediction model. Federated learning, as an emerging artificial intelligence technology, is designed to ensure data privacy while carrying out efficient machine learning, which provides a new way to solve the problem of “Isolated Data Island” in terms of electricity forecasting. Nonetheless, due to the popularity of smart meters, the collected electricity data presents the characteristics of uneven distribution and huge data volume, so it is difficult to apply the electric quantity prediction model generated only by federated learning in practice. To solve this problem, a clustering federated learning method (C-FL) is proposed to protect data privacy while improving the accuracy of power prediction. Firstly, C-FL uses K-means algorithm to cluster power data locally in power enterprises, and then builds accurate power forecasting models for each class of power data combined with other local clients through federated learning. A large number of experimental results show that the clustering federated learning method proposed in this paper is superior to the existing federated learning models in terms of the accuracy of electric power forecasting.

Classifying land-use patterns by integrating time-series electricity data and high-spatial resolution remote sensing imagery

Accurate identification of urban land-use patterns is essential to rational optimization of urban structure. By combining the external physical characteristics of city parcels obtained from remote sensing images and the socioeconomic attributes revealed by social sensing data, land use can be better classified. However, most of the existing social sensing data have location bias and lack temporal resolution, which cannot accurately reflect the socioeconomic information of land use and leads to low classification accuracy. Based on the above problems, this study explores the deep semantic information of high-spatial and temporal resolution time-series electricity data to explore its relationship with socioeconomic attributes and construct a neural network (TR-CNN) that can fuse time-series electricity data and remote sensing images to identify urban land-use types. We selected Anyuan District in Pingxiang City, Jiangxi Province for a demonstration study, and the results show that the accuracy of the proposed model is 0.934, which is 4.3% and 6.7% higher than that of the ResNet18 model using only remotely sensed images and the LSTM-FCN model using only time-series electricity data. The results also show that the use of time-series electricity data can effectively identify residential and commercial areas, but it is difficult to identify public service facilities compared with remote sensing images. This study finds for the first time that the semantic features of electricity data can fully reflect socioeconomic attributes and can accurately perceive urban land-use patterns from both “top-down” and “bottom-up” recognition patterns by coupling remote sensing images and electricity data.