Similar Consumption Patterns Research Articles

Enhancing multivariate, multi-step residential load forecasting with spatiotemporal graph attention-enabled transformer

Short-term residential load forecasting (STRLF) holds great significance for the stable and economic operation of distributed power systems. Different households in the same region may exhibit similar consumption patterns owing to the analogous environmental parameters. Incorporating the spatiotemporal correlations can enhance the load forecasting performance of individual households. To this end, a spatiotemporal graph attention (STGA)-enabled Transformer is proposed for multivariate, multi-step residential load forecasting in this paper. Specifically, the multiple residential loads are cast to a graph and a Transformer with a graph sequence-to-sequence (Seq2Seq) structure is employed to model the multi-step load forecasting problem. Gated fusion-based STGA blocks are embedded in the encoder and decoder of the Transformer to extract dynamic spatial correlations and non-linear temporal patterns among multiple residential loads. A transform attention block is further designed to transfer historical graph observations into future graph predictions and alleviate the error propagation between the encoder and decoder. The embedding of multiple attention modules in the Seq2Seq framework allows us to capture the spatiotemporal correlations between residents and achieve confident inference of load values several steps ahead. Numerical simulations on residential data from three different regions demonstrate that the developed Transformer method improves multi-step load forecasting by 14.7% at least, compared to the state-of-the-art benchmarks.

Effects of different brewing conditions on acrylamide levels in Turkish black tea and health risk assessment

In this study, the effects of different brewing parameters (brewing method, teapot spout shape, brewing time, brewing water temperature) on acrylamide levels in black tea were investigated. Then, the level of acrylamide exposure from black tea consumption was evaluated in terms of carcinogenic and non-carcinogenic health risks. The average acrylamide level of all black tea samples brewed with 24 different methods was 53.2±17.1 µg/L. There was no significant difference in acrylamide levels (median) between brewing parameters except for the brewing water temperature value (p < 0.01). Individuals aged 15 years and over living in Türkiye were found to have an acrylamide exposure level in the range of 0.06−0.27 µg/kg bw/day. Consumption of brewed black tea according to different brewing parameters in light, normal and over-brewed forms was found to be safe in terms of non-carcinogenic health risks. However, acrylamide exposure levels indicate the presence of potential and significant health risks in terms of carcinogenic risks considering similar consumption patterns. When all the data are evaluated together, in order to reduce the acrylamide exposure level and potential health risks of acrylamide, black tea should be brewed with water at 95 ℃ and over-brewed tea consumption should be avoided.

Pak-Afghan Bilateral Trade:

Afghanistan and Pakistan are located at the junction of Central Asia and South Asia. Owing to geographical contiguity, common border, common culture and similar consumption patterns, bilateral trade between the two countries should have increased with the passage of time, in line with the assumptions of the Gravity Model of international trade. However, it has been observed that during the period 2012-2018, bilateral trade between the two countries has either stagnated or declined. There are various causes responsible for the declining trends in trade where this study uses both quantitative and qualitative evidences as primary and secondary data. The gravity model of trade was estimated by using random effect estimation technique for panel data set (secondary data). Furthermore, the trade potential was estimated which shows that Pak-Afghan trade is operating below potential level. For qualitative evidences, the input of the actual stakeholders (primary data) including traders, transporters, clearing agents and customs officials was taken and analyzed. The finding of the study shows that Pak-Afghan trade is operating below the potential level and is not in line with GMT. Similarly the non-tariff barriers (NTBs) for Pak-Afghan bilateral trade have resulted in trade diversion to Afghanistan’s trade with India, Iran and Uzbekistan.

Consumer Preferences of Jalapeño Pepper in the Mexican Market

The jalapeño pepper is one of the best-known and most commonly consumed chili peppers in Mexico; its consumption is a tradition that dates to the first migrations of Europeans to the country. With time, its demand has increased, although in recent years its consumption presented a stabilization and stagnation. This work aimed to determine the preferences of Mexican consumers for jalapeño pepper, taking as a reference quality attributes and motivations that influence their purchasing and consumption habits, under the hypothesis that consumers in each region seek a certain type of jalapeño pepper based on specific quality attributes. In total, 1200 surveys were carried out in five regions of the country. The analysis of the information was performed using the ANOVA test, correspondence analysis, and multidimensional scaling. The main results of this study show that although there is a tendency towards frequent consumption, each purchase weighs less than 500 g. In the same way, the physical appearance of the product is fundamental at the time of purchase, in addition to other attributes such as flavor, color, and size, which are highly valued by consumers. Although there are similar consumption patterns, purchasing behaviors change by region, which can serve as a basis and spearhead for the development of differentiated strategies in the production and marketing of the product.

Short-term residential load forecasting using Graph Convolutional Recurrent Neural Networks

The abundance of energy consumption data collected by smart meters has inspired researchers to employ deep neural networks to solve the existing problems in the power industry, such as Short-Term Load Forecasting (STLF). Most studies addressing the STLF problem, focus on historical load data and to achieve higher performance, they supplement costly accessible environmental and calendar variables with data. This approach ignores the existing spatial information among the consumers which subsequently might lead into the emergence of similar consumption patterns. In this paper, we present a Graph Convolutional Recurrent Neural Network, a novel neural architecture, for STLF problem that combines Graph Convolutional Networks and Long Short-Term Memory networks to simultaneously extract spatial and temporal information from users with similar consumption patterns. Our model captures spatial information from users without prior knowledge of their geographic location and does not rely on additional environmental variables. We compared our model to traditional baseline models for STLF using two real-world electricity consumption datasets. The empirical results demonstrate a significant improvement in prediction compared with the baseline models, exhibiting a 9.5% and an 8% improvement in terms of Mean Absolute Percentage Error, in the Customer Behavior Trials and Low Carbon London datasets, respectively.

Mixed-Integer Nonlinear Programming for State-Based Non-Intrusive Load Monitoring

Energy disaggregation, known in the literature as Non-Intrusive Load Monitoring (NILM), is the task of inferring the energy consumption of each appliance given the aggregate signal recorded by a single smart meter. In this paper, we propose a novel two-stage optimization-based approach for energy disaggregation. In the first phase, a small training set consisting of disaggregated power profiles is used to estimate the parameters and the power states by solving a mixed integer programming problem. Once the model parameters are estimated, the energy disaggregation problem is formulated as a constrained binary quadratic optimization problem. We incorporate penalty terms that exploit prior knowledge on how the disaggregated traces are generated, and appliance-specific constraints characterizing the signature of different types of appliances operating simultaneously. Our approach is compared with existing optimization-based algorithms both on a synthetic dataset and on three real-world datasets. The proposed formulation is computationally efficient, able to disambiguate loads with similar consumption patterns, and successfully reconstruct the signatures of known appliances despite the presence of unmetered devices, thus overcoming the main drawbacks of the optimization-based methods available in the literature.

Behavior segmentation of electricity consumption patterns: A cluster analytical approach

Developing effective energy use and management strategies requires the knowledge of determinants and patterns of the electricity usage behavior of different consumers. This paper examines data-driven unsupervised learning schemes to partition the smart meter users into different clusters such that the users in the same cluster have similar consumption patterns represented by their similar daily routines and peak demand time periods. However, it is critical to resolve the problem of high dimensional space in long time series of smart meter data to make the clustering practical. This problem is resolved by time series data mining based on meaningful statistics and behavioral characteristics to emphasize the essential features for reducing the dimensionality and noisiness of the data. Our work involves rigorous data analysis of smart meter data to identify the essential behavioral characteristics and the source of variability in the behavior and analysis of these behavioral characteristics to select the clustering algorithm and its parameters appropriately. These behavioral features will be extracted from each time-series and then used for clustering using a Gaussian mixture modeling​ algorithm. The clustering algorithm is executed on a real-world electricity consumption dataset of 5038 consumers in Slovenia. The classifications obtained with the algorithm are effective when tested visually and by scoring methods of internal indices. The results indicate that the time of day, day of the week, day-to-day variability and seasonality differences that exist in different clusters can be used to formulate new energy management and grid planning strategies.

Clustering Electricity Consumers: Challenges and Applications for Operating Smart Grids

With the progressive advancement of the smart grid paradigm, electricity systems worldwide are deploying advanced metering technologies in residential sectors. Smart meters can monitor and process the electricity use of households at very high sampling rates. The availability of hundreds of thousands of time-series load profiles opens the possibility of applying clustering methods for grouping consumers with similar consumption patterns.

A short-term load forecasting model based on mixup and transfer learning

When the amount of historical load data is insufficient, the use of deep learning for load forecasting is prone to overfitting. This paper proposes a short-term electric load forecasting model based on mixup and transfer learning. Mixup is introduced to achieve data enhancement, which improves the generalization ability of the forecasting model by expanding the distribution of training samples. Transfer the historical load of other users with similar consumption patterns to supplement data samples and avoid overfitting of the forecasting model. The similarity between the target load sequence and the source load sequence is measured by the maximal information coefficient (MIC). Finally, the expanded load data adopts a long short-term memory (LSTM) neural network that can learn the long-term dependence in the time series for load forecasting. Experimental results on the residential data set demonstrate that the model proposed in this paper improves the accuracy of load forecasting in scenarios where historical data is scarce.

A Study on Formation of Space through Production with Plane Extensibility – Focusing on Image Expansion in the Webtoon Series Tilly the Spiky Hands

The advancement of digital media and information and communication technology has led to flat images having more of a sense of space. Virtual and augmented reality technologies have advanced in recent years; although these technologies are based in reality, they include additional information that amplify the sense of reality. However, webtoons, which are one of the leading contents of Korean culture, have maintained similar consumption patterns wherein elements are placed in each frame based on the author’s intention. This study will explain how elements in the frames were expanded in the 2D webtoon Tilly the Spiky Hands, and how space was formed through reproduction. Each element in a frame in the webtoon was separated using multiplane camera shooting techniques. Following this, to re-connect objects that were disconnected in the process, additional directing and redrawing was conducted. Regarding the background, the image was enlarged at least three times its original size, according to the device being used by the consumer, thus the consumer would be presented with the option to view the background from different angles and provide a larger sense of space.

Spatial-Temporal Residential Short-Term Load Forecasting via Graph Neural Networks

Electric load forecasting, especially short-term load forecasting, is of significant importance for the safe and efficient operation of power grids. With the wide adoption of advanced smart meters, more attention has been paid to short-term residential load forecasting. Most of the existing load forecasting methods are mainly focused on using temporal information of historical loads, and information of neighboring houses are generally ignored. However, houses in the same or neighboring areas may show similar consumption patterns due to shared conditions such as temperature, holiday impacts. Such information can be very helpful for machine learning based forecasting methods. In this paper, we propose to tackle the short-term residential load forecasting including both the individual load and aggregated load with a graph neural network based forecasting framework. The proposed framework can capture the hidden spatial dependencies of different houses without even any prior knowledge requirement on the geographic information for these houses. The proposed framework is evaluated on data sets of different residential houses from several areas. The experimental results demonstrate that the proposed framework can improve the residential forecasting accuracy by a wide margin compared with the baselines.

Segmentation of heat energy consumers based on data on daily power consumption

Purpose. Improving the quality of the analysis of energy consumption modes of buildings of educational institutions by determining the typical patterns of their consumption by the k-means method based on statistics of thermal energy consumed, their area, outdoor and indoor air temperature. Methodology. Methods of statistical and intellectual data analysis, optimization methods, k-means method. Findings. It is shown that most of the researched consumers of thermal energy have similar patterns of its consumption and can be divided into separate segments according to the peculiarities of functioning. The used data set is diverse as it includes three groups of data (conditionally formed by the type of educational institutions). The buildings in groups have different areas, internal temperature to be maintained, operation modes of heating systems and so on. For each of the groups, the number of clusters corresponding to low, medium and high values of heat consumption is determined. It was found that the amount of the consumed heat and consumer behavior depends on the day of the week. The obtained results can be difficult to generalize for all existing types of buildings, but it is expected that communal buildings may have similar consumption patterns, as operating modes and norms of internal microclimate remain the same for different temperature zones and territories. Originality. The method for dividing the consumers of thermal energy into segments on the basis of the data on daily energy consumption applying the k-means clustering algorithm, implemented in the programming language R, is further developed. For the first time, it has been proposed to consider not one, but three groups of objects of the educational institutions. It is proposed to determine the modes of energy consumption by buildings analytically by taking into account such parameters as the area of buildings, the amount of heat consumed by them, external and internal air temperature. Practical value. The results of the research are useful for heat supply companies, municipalities and can be used to develop programs and policies for energy efficiency. The given information and analytical support create a basis for the development of software solutions with the function of integration into local energy monitoring systems of a separate building, energy management system of the district and/or city. The presented results provide an opportunity to predict the cost of energy resources used for heating buildings, which increases the efficiency of engineering systems of buildings.

ADMM‐based distributed response quantity estimation: a probabilistic perspective

With the wide deployment of smart meters in the end-user side, demand response (DR) is gaining prominence. Estimating the potential response is a preliminary step to the DR implementation. However, how to select proper features, how to protect privacy, and how to capture the response uncertainty remains three challenges to the customer response potential estimation. This study provides a detailed response quantity estimation for each customer. The authors proposed a probabilistic response quantity estimation framework and solved the problem by alternating direction method of multipliers (ADMM) in a fully-distributed way. In particular, by utilising a similar consumption pattern matching principle, the feature for each DR day of each customer is selected based on the matched DR participants. Then, the pinball loss-guided ridge regression is formulated, so the quantiles are obtained to cope with the uncertainty. The training process can be solved by each customer at the local site in a fully-distributed way, which protects the privacy and reduces the centralised processing burden. Finally, in the case study, the assumption behind a similar consumption pattern matching principle is validated empirically. Also, the proposed method is confirmed to have good convergence performance and can produce reasonable estimation results.

IS STREETWEAR THE NEW FACE OF LUXURY OR JUST A PASSING EXPERIENTIAL TREND?

Streetwear can be thought of as a lifestyle, which in turn is a choice of how one facilitates money and time in the process and pattern of consumption of products. The user’s affinity with like-minded individuals or groupings and how they spend their disposable or available income creates groupings. These similar minded individuals fall into groups or lifestyle segments and their consumption patterns mirror their lifestyle choices. Group identities focus around expressive symbolism, following similar consumption patterns and change over time as the group preferences move onto the next desire or trend (Solomon, 2007).

The rise of the sugar trade and sugar consumption in early British America, 1650–1720*

Abstract This article draws on new archival sources to explore how sugar pervaded British North America much earlier that previous scholarly literature has suggested. Sugar arrived in North America with the very first colonists, and was widely available to a variety of consumers across the socio-economic spectrum. The product was foundational to the development of the North American economic world – in the creation of rum distilleries, grocers’ shops and through the use of commodity money. While sugar brought North American colonists closer to Britain through similar consumption patterns and a shared sense of taste, it also began to pull the two countries apart. By 1733, sugar had become a central source of tension between the colony and the metropole; it allowed colonists’ economic relationships to spread much further than Britain, and consequently, as America’s sweet tooth developed, its relationship with Britain began to decay.

National Food Consumption Patterns: Converging Trends and the Implications for Health

SummaryWorldwide, obesity almost tripled between 1975 and 2016 and is now prevalent in both rich and poor countries. Using annual food availability data produced by the Food and Agriculture Organisation of the United Nations (FAO) covering half a century in 118 countries, this article explores the diets that are central to the problem of obesity, identifying groups of countries with similar consumption patterns. Applying algorithms from the fuzzy clustering literature, five distinct consumption patterns are revealed whose dietary composition broadly corresponds to diets that we label ‘Western’, ‘Traditional’, ‘Mediterranean’, ‘Tropical’ and ‘Vegetarian’. Despite differences in dietary characteristics, all five share two common themes: rising total calories and declining healthiness, both of which are linked to the substitution of plant‐based foods with food derived from animals. That the evidence points to a convergence on the ‘Western’ diet, the most obesogenic and least healthy of all the diets we consider, is a cause for concern. The key message is that in a future where people are predicted to live longer – but not necessarily healthier – lives, recent efforts to address the challenge are prescient, and as the results in the article imply, need to be heeded globally.

An empirical analysis of domestic electricity load profiles: Who consumes how much and when?

With the increased share of renewables in power generation, end users play a key role in keeping the demand at levels that better match variable supply, maintaining lower overall system costs, and reducing carbon dioxide emissions. To increase the potential for demand-side flexibility, a deeper understanding of domestic electricity load profiles is needed. Informed by customer grouping based on similar consumption patterns and drivers, targeted interventions can be better designed to time-shift peak loads and reduce overall demand. Thus, the objectives of this study are (i) to segment households in relation to their electricity load patterns using K-means clustering and (ii) to investigate household characteristics that have an influence on electricity load patterns by employing multinomial probit regression. This study uses hourly electricity consumption for 2017, combined with population-based register data for a large sample of Danish households. The results indicate that four distinct Danish household groups are characterized by different timing and magnitudes of electricity consumption, which are influenced by specific sociodemographics and dwelling characteristics. Similarities between the groups emerge with respect to the evening peak consumption, seasonal variation in electricity demand, and weekend morning demand ramp-up. Challenges and opportunities for domestic load profiling in the power industry and policymaking are discussed.

Non-intrusive energy disaggregation by detecting similarities in consumption patterns

&#x0D; &#x0D; &#x0D; Breaking down the aggregated energy consumption into a detailed consumption per appliance is a crucial tool for energy efficiency in residential buildings. Non-intrusive load monitoring allows implementing this strategy using just a smart energy meter without installing extra hardware. The obtained information is critical to provide an accurate characterization of energy consumption in order to avoid an overload of the electric system, and also to elaborate special tariffs to reduce the electricity cost for users. This article presents an approach for energy consumption disaggregation in households, based on detecting similar consumption patterns from previously recorded labelled datasets. The experimental evaluation of the proposed method is performed over four different problem instances that model real household scenarios using data from an energy consumption repository. Experimental results are compared with twobuilt-in algorithms provided by the nilmtk framework (combinatorial optimization and factorial hidden Markov model). The proposed algorithm was able to achieve accurate results regarding standard prediction metrics. The accuracy was not affected in a significant manner by the presence of ambiguity between the energy consumption of different appliances or by the difference of consumption between training and test appliances.&#x0D; &#x0D; &#x0D;

The buffet is open: Alpine soil macro-decomposers feed on a wide range of litter types in a microcosm cafeteria experiment

Alpine semi-natural grasslands were formed by hundreds of years of traditional and extensive land-use resulting in a distinct flora and fauna. Socio-economic changes in the last century led to the abandonment of a large number of alpine pasturelands. Even though litter composition and quality will permanently alter due to shifts in plant species composition, consequences of abandonment and the subsequent shrub encroachment on the feeding activities of decomposers are not well known.We conducted cafeteria feeding experiments in microcosms in a climate chamber with four abundant alpine decomposer species (two earthworms and two millipedes), offering them three representative alpine litter types (dwarf shrub, grass, and forb) as single litters and mixtures.The epi-endogeic earthworm Lumbricus rubellus (Hoffmeister, 1843), dominant in alpine pastureland, had highest mean consumption rates (34.7 ± 24.7 mg), while Dendrobaena octaedra (Savigny, 1826), a strictly epigeic earthworm, showed considerably lower consumption rates. Millipedes showed similar consumption patterns, with Cylindroiulus fulviceps (Latzel, 1884) being less active than C. meinerti (Verhoeff, 1891). We found several cases where litter mixtures were preferred over single litters, including higher consumption rates of low-quality dwarf shrub litter by D. octaedra and C. meinerti when mixed with high-quality litter.The tested specimens showed a high intra- and interspecific variability as they fed on all offered litter types and qualities, resulting in few specific food preferences and selections. We conclude that alpine soil macro-decomposer such as earthworms and millipedes are generalists feeding on a wide range of litter qualities, allowing them, in theory, to better adapt to the litter resources that become available when pastures are abandoned and reverted to shrubland.

Detection and identification of energy theft in advanced metering infrastructures

This paper presents a novel approach for detection and identification of energy theft in distribution systems considering advanced metering infrastructure. For the energy theft detection stage, a three phase state estimator based on phasor measurement units is used to detect the transformers which have evidence of energy theft. The next step is to identify consumers which are stealing energy. A Self-Organizing Map (SOM) was trained for clustering consumers according to similar consumption patterns. For each class defined by the SOM, a Multilayer Perceptron Artificial Neural Network (MP-ANN) for classification of consumers into two classes, either honest or fraudulent, was created. The main contribution of the energy theft detection step is the reduction of the number of transformers which have suspect consumers without the need to install measurement units on all transformers. The use of ANN allows to identify the fraudulent users considering either cyber or physical attacks. Tests were conducted for energy theft detection step on the IEEE 70 busbar test system. Real data from 5000 consumers were used for identification of fraudulent users. The results show the effectiveness and robustness of the proposed technique, presenting a detection rate close to 93% with a false positive rate less than 2%.