Abstract:In the current electrical load profile analysis, considering the shortage of traditional methods on the typical load profile extraction of single consumers and the load profile feature extraction, this paper proposes an approach based on time series data mining. Firstly, this method reduces the dimension of the load profile of a single consumer based on the Piecewise Aggregate Approximation(PAA), and re-expresses the load profile of the consumer over a period based on the Symbolic Aggregate approXimation(SAX),… Show more
“…Power companies are particularly interested in producing accurate forecasts for the load profile (e.g., [ 9 , 30 , 31 ]). This is because it can directly affect the optimal scheduling of power generation units.…”
Section: Classification Of Demand Forecasting Techniquesmentioning
Smart grids are able to forecast customers’ consumption patterns, i.e., their energy demand, and consequently electricity can be transmitted after taking into account the expected demand. To face today’s demand forecasting challenges, where the data generated by smart grids is huge, modern data-driven techniques need to be used. In this scenario, Deep Learning models are a good alternative to learn patterns from customer data and then forecast demand for different forecasting horizons. Among the commonly used Artificial Neural Networks, Long Short-Term Memory networks—based on Recurrent Neural Networks—are playing a prominent role. This paper provides an insight into the importance of the demand forecasting issue, and other related factors, in the context of smart grids, and collects some experiences of the use of Deep Learning techniques, for demand forecasting purposes. To have an efficient power system, a balance between supply and demand is necessary. Therefore, industry stakeholders and researchers should make a special effort in load forecasting, especially in the short term, which is critical for demand response.
“…Power companies are particularly interested in producing accurate forecasts for the load profile (e.g., [ 9 , 30 , 31 ]). This is because it can directly affect the optimal scheduling of power generation units.…”
Section: Classification Of Demand Forecasting Techniquesmentioning
Smart grids are able to forecast customers’ consumption patterns, i.e., their energy demand, and consequently electricity can be transmitted after taking into account the expected demand. To face today’s demand forecasting challenges, where the data generated by smart grids is huge, modern data-driven techniques need to be used. In this scenario, Deep Learning models are a good alternative to learn patterns from customer data and then forecast demand for different forecasting horizons. Among the commonly used Artificial Neural Networks, Long Short-Term Memory networks—based on Recurrent Neural Networks—are playing a prominent role. This paper provides an insight into the importance of the demand forecasting issue, and other related factors, in the context of smart grids, and collects some experiences of the use of Deep Learning techniques, for demand forecasting purposes. To have an efficient power system, a balance between supply and demand is necessary. Therefore, industry stakeholders and researchers should make a special effort in load forecasting, especially in the short term, which is critical for demand response.
“…Fuzzy C-means clustering is one of the algorithms of clustering besides another algorithms which are hierarchical, K-means, and dynamic [9]. The well-known clustering method is K-means which basically uses iterative method for clustering [8], [10], [11] then the result can be used to analyze the power consumption behaviour [12]. If the clustering is done by considering each data as a separate cluster and then merging the similar ones, it is called hierarchical clustering as done in some literatures [10], [13], [14].…”
Section: Introductionmentioning
confidence: 99%
“…The cluster results then is analyzed for its load profile characterization. The statictical method based on time series data can be implemented to get the statistic descriptive [12]. Another approach of load profile characterization is by using the frequency domain analysis [18], but the accuracy depends on the data sampling frequency.…”
As the rising of electricity demand, electricity load profile characterization (ELPC) is the integral aspect in planning, operating system, and distribution network development. The approach in the existing ELPC is still relatively macro in nature and does not involve other aspects outside the electricity variable, so the results tend to be biased for areas experiencing rapid land use changes. Therefore, this paper proposes an ELPC approach based on micro-spatial. Microspatial analysis is done by dividing area in the form of the smallest grids involving various electrical, demographic, geographic and socio-economic variables, which are then grouped using adaptive clustering based on fuzzy C-means (FCM). The adaptive clustering algorithm is proven to be able to determine the degree of membership of each grid data against each cluster with the ability to determine the number of clusters automatically according to the attribute data provided. The ELPC results which consist of 5 clusters are then analyzed using descriptive statistic, plotted, and mapped to obtain more accurate and realistic load characteristics in accordance with the pattern and geographical conditions of the region, so that the results can be used as a reference in load forecasting, network development, and distributed generation (DG) integration.
“…Electrical design engineers of Iraq DPGs aim to meet two objectives [2][3][4]: studying the current residential dwelling load profile characteristics [5][6][7][8][9][10][11] and model the electricity kW demand [12][13][14][15][16][17][18]. The common factor among residential dwellings, called the diversity factor ( ), is the backbone of electricity demand modeling.…”
In Baghdad City's distribution power grid, a massive number of 630 kV distribution transformers (DTs) are used in residential neighborhoods. Each DT is joined to nine low-voltage 0.415 kV distribution feeders. Each feeder has a designated size of 1 × 240 mm 2 and is joined to a specified number of residential dwellings (= 30) fixed in the initial design stage. The size and number of low-voltage 0.415 kV distribution feeders are set with no change. In this investigation, we use a new approach for modeling electricity demand in residential neighborhoods in Baghdad City and overcome this constraint by finding the optimum number of residential dwellings joined to the same low-voltage 0.415 kV distribution feeder. Two sets of the experimental equations are created to compute the number of residential dwellings that are required to be joined to the low-voltage 0.415 kV distribution feeder. The multi-gradient particle swarm optimization algorithm is used as an optimization tool to handle these experimental equations. Results show that each low-voltage 0.415 kV distribution feeder can be loaded with 50 dwellings instead of 30 due to the diversity among residential dwellings. Several facts about the load profile characteristics of
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.