Smart meter based short-term load forecasting for residential customers

Ghofrani, M.; Hassanzadeh, Mohammad Esmaeil; Etezadi-Amoli, M.; Fadali, M. Sami

doi:10.1109/naps.2011.6025124

Cited by 126 publications

(73 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…When using CBAF, empirically we found that clustering customers into 8 to 10 clusters delivers the best forecasting accuracy across different 11 They refer to CBAF as disaggregated load forecasting. 12 Interestingly, although [1], [25] and our work focus on different customer types and use different forecasting and clustering algorithms, all conclude that clustering customers and forecasting each cluster separately could indeed improve aggregate forecasts. error metrics, forecating algorithms, and clustering approaches.…”

Section: Discussionmentioning

confidence: 87%

“…The work by Ghofrani et al [12] can be considered as one of the earliest works in the field, where they forecast the electricity demand of a single household, using one day of training and one day of test data. Since then, some interesting results have been published.…”

Section: Related Workmentioning

confidence: 99%

“…11 However, Misiti et al consider only industrial customers, and Alzate and Sinn consider a mix of residential customers and small/medium enterprises. Additionally, they focused on wavelet-based and kernel spectral clustering 12 and did not investigate the effect of different customer sizes to the improvement provided by CBAF.…”

Section: Related Workmentioning

confidence: 99%

See 2 more Smart Citations

Cluster-based aggregate forecasting for residential electricity demand using smart meter data

Wijaya

Vasirani

Humeau

et al. 2015

2015 IEEE International Conference on Big Data (Big Data)

View full text Add to dashboard Cite

Abstract-While electricity demand forecasting literature has focused on large, industrial, and national demand, this paper focuses on short-term (1 and 24 hour ahead) electricity demand forecasting for residential customers at the individual and aggregate level. Since electricity consumption behavior may vary between households, we first build a feature universe, and then apply Correlation-based Feature Selection to select features relevant to each household. Additionally, smart meter data can be used to obtain aggregate forecasts with higher accuracy using the so-called Cluster-based Aggregate Forecasting (CBAF) strategy, i.e., by first clustering the households, forecasting the clusters' energy consumption separately, and finally aggregating the forecasts. We found that the improvement provided by CBAF depends not only on the number of clusters, but also more importantly on the size of the customer base.

show abstract

Section: Discussionmentioning

confidence: 87%

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Cluster-based aggregate forecasting for residential electricity demand using smart meter data

Wijaya

Vasirani

Humeau

et al. 2015

2015 IEEE International Conference on Big Data (Big Data)

View full text Add to dashboard Cite

show abstract

“…Aggregation on the other hand reduces the inherent variability in electricity consumption resulting in increasingly smooth load shapes, and as a result, the relative forecasting errors typically seen at the level of substations have been quite low in terms of MAPE (1% 2%) [14] and in cases higher (12%-30%) [15]. Figure 1b presents the calculated MAPE of aggregated peak demand of all endpoints in each day of the two-month period used for testing accuracy.…”

Section: Accuracy a Datasetmentioning

confidence: 99%

Methodology for managing cost-effective demand response campaigns based on demand elasticity profiles

Anastopoulou

Kalogiros

Stamoulis

2017

2017 Sustainable Internet and ICT for Sustainability (SustainIT)

View full text Add to dashboard Cite

Abstract-We develop and evaluate a methodology for running manual implicit and explicit Demand Response campaigns in order to improve the sustainability of smart grids. Initially, we introduce a flexibility profiling engine that relies on the correlation among end-user's consumption, prices and environmental conditions. Then, we investigate two mechanisms so that an Aggregator, acting as an intermediate between the Distribution System Operator or Retailer and the consumers, achieves the desired demand flexibility. More precisely we introduce: (i) a price-based mechanism that determines the new price that consumers will be paying during the DR campaign, and (ii) a reward-based mechanism that determines which set of consumers should participate in the campaign, along with the load flexibility to be asked from each one and the reward offered. The proposed methodology is evaluated using a publicly-available dataset. It is shown that CES model achieves high accuracy and that the details obtained using the proposed mechanisms are more favorable than the equivalent used. 1

show abstract

“…Based on NIALM, there have been research attempts devoted to load prediction on the individual household level [16][17][18][19]. They utilize smart meter data enriched with a set of household behavioral data (patterns of home appliances usage) and dwelling characteristics to benefit significant improvement in terms of the accuracy of the forecasts generated at the household level.…”

Section: Literature Review On Related Workmentioning

confidence: 99%

Data Mining Techniques for Detecting Household Characteristics Based on Smart Meter Data

Gajowniczek

Ząbkowski

2015

Energies

View full text Add to dashboard Cite

Abstract:The main goal of this research is to discover the structure of home appliances usage patterns, hence providing more intelligence in smart metering systems by taking into account the usage of selected home appliances and the time of their usage. In particular, we present and apply a set of unsupervised machine learning techniques to reveal specific usage patterns observed at an individual household. The work delivers the solutions applicable in smart metering systems that might: (1) contribute to higher energy awareness; (2) support accurate usage forecasting; and (3) provide the input for demand response systems in homes with timely energy saving recommendations for users. The results provided in this paper show that determining household characteristics from smart meter data is feasible and allows for quickly grasping general trends in data.

show abstract

Smart meter based short-term load forecasting for residential customers

Cited by 126 publications

References 13 publications

Cluster-based aggregate forecasting for residential electricity demand using smart meter data

Cluster-based aggregate forecasting for residential electricity demand using smart meter data

Methodology for managing cost-effective demand response campaigns based on demand elasticity profiles

Data Mining Techniques for Detecting Household Characteristics Based on Smart Meter Data

Contact Info

Product

Resources

About