Filters








371 Hits in 4.4 sec

Data-driven demand response characterization and quantification

Guillaume Le Ray, Pierre Pinson, Emil Mahler Larsen
2017 2017 IEEE Manchester PowerTech  
Clustering on the average values and standard deviation of the contribution regroups households with the same average response.  ...  Independent Component Analysis (ICA) is used to characterize different DR delivery profiles.  ...  The FIR analysis can actually be used as a validation tool after sampling process, as it uses historical data and models the response of a pool of households.  ... 
doi:10.1109/ptc.2017.7981009 fatcat:zuocey6kurexdl5cqofmgfvd4e

Review of Low Voltage Load Forecasting: Methods, Applications, and Recommendations [article]

Stephen Haben, Siddharth Arora, Georgios Giasemidis, Marcus Voss, Danica Vukadinovic Greetham
2021 arXiv   pre-print
Reliable forecasting will be a necessary component of many of these systems to anticipate key features and uncertainties.  ...  Despite this urgent need, there has not yet been an extensive investigation into the current state-of-the-art of low voltage level forecasts, other than at the smart meter level.  ...  In [180] the authors developed a Gaussian Process regression-based 10-minute ahead forecast for the aggregated consumption of ten buildings using both actual and predicted temperature.  ... 
arXiv:2106.00006v2 fatcat:rb2yrt4tsjap3jhrb7dz76dg2e

Minutely Active Power Forecasting Models Using Neural Networks

Dimitrios Kontogiannis, Dimitrios Bargiotas, Aspassia Daskalopulu
2020 Sustainability  
Power forecasting is an integral part of the Demand Response design philosophy for power systems, enabling utility companies to understand the electricity consumption patterns of their customers and adjust  ...  In this study we compared the baseline performance and structure of different types of neural networks on residential energy data by formulating a suitable supervised learning problem, based on real world  ...  In 2015, Alamaniotis and Tsoukalas [9] presented a data-driven method for minutely active power forecasting based on Gaussian processes.  ... 
doi:10.3390/su12083177 fatcat:a7rlaf436fdk3aq7tfhzt54x3a

Watt's up at Home? Smart Meter Data Analytics from a Consumer-Centric Perspective

Benjamin Völker, Andreas Reinhardt, Anthony Faustine, Lucas Pereira
2021 Energies  
For example, forecasts of household energy consumption or photovoltaic production allow for improved power plant generation scheduling.  ...  The key advantage of smart meters over traditional metering devices is their ability to transfer consumption information to remote data processing systems.  ...  [133] attempted to forecast household day-ahead charging needs using machine learning ensembles.  ... 
doi:10.3390/en14030719 fatcat:atvoo3abprcwddsgigzwuen6ce

Simulating Tariff Impact in Electrical Energy Consumption Profiles with Conditional Variational Autoencoders [article]

Margaux Brégère, Ricardo J. Bessa
2020 arXiv   pre-print
The implementation of efficient demand response (DR) programs for household electricity consumption would benefit from data-driven methods capable of simulating the impact of different tariffs schemes.  ...  This non-parametric approach is compared to a semi-parametric data generator based on generalized additive models and that uses prior knowledge of energy consumption.  ...  Acknowledgments Margaux Brégère is very grateful to the entire team of the Center for Power and Energy Systems at INESC TEC for their wonderful welcome in Porto.  ... 
arXiv:2006.07115v1 fatcat:tbp72qesinbb3jmaw4idua6hfy

Advanced Economic Control of Electricity-Based Space Heating Systems in Domestic Coalitions with Shared Intermittent Energy Resources

Athanasios Aris Panagopoulos, Sasan Maleki, Alex Rogers, Matteo Venanzi, Nicholas R. Jennings
2017 ACM Transactions on Intelligent Systems and Technology  
In this context, we propose a simple and effective formulation for the site-specific calibration of such predictions based on adaptive Gaussian process modeling.  ...  the households.  ...  Predicting IER Power Output and Gaussian Processes An essential part of our AEC approach is a stochastic, short-term (up to 12 hours ahead), prediction of the shared IER power output.  ... 
doi:10.1145/3041216 fatcat:xuv7kyg4v5dhflryynz2syxfia

Performance assessment of aggregation control services for demand response

Daniel Esteban Morales Bondy, Giuseppe Tommaso Costanzo, Kai Heussen, Henrik W. Bindner
2014 IEEE PES Innovative Smart Grid Technologies, Europe  
The index is based on requirements formulated in service contracts and provides an overall assessment of the quality of service provided by an aggregation control algorithm.  ...  By a detailed case study we present and an application of the index, comparing the performance of two different control architectures for demand side management delivering a distribution grid service.  ...  ACKNOWLEDGMENT The authors acknowledge the financial support of iPower (www.ipower-net.dk). The authors thank Shi You from DTU Elektro for providing data for the non-controllable loads.  ... 
doi:10.1109/isgteurope.2014.7028779 fatcat:kwfmmhlphbc4vgclimzapavfqq

Decentralized neighborhood energy management with coordinated smart home energy sharing

BERK CELIK, Robin Roche, David Bouquain, Abdellatif Miraoui
2017 IEEE Transactions on Smart Grid  
The aim of this study is to establish a day-ahead decentralized coordination method with appliance scheduling and energy sharing (among smart homes) to minimize the electricity bills of consumers under  ...  This paper introduces a day-ahead energy management algorithm for the coordination of smart homes with renewable energy sources and energy storage systems in neighborhood areas.  ...  are price anticipative, and the effect of other users consumption is considered in the price.  ... 
doi:10.1109/tsg.2017.2710358 fatcat:p6epsph5lffopeiwrxdnloenxa

Online unsupervised occupancy anticipation system applied to residential heat load management

Luis Rueda, Kodjo Agbossou, Nilson Henao, Sousso Kelouwani, Juan C. Oviedo-Cepeda, Brice Le Lostec, Simon Sansregret, Michael Fournier
2021 IEEE Access  
and Φ in is the rated electrical power consumption of the heating system (applied thermal flux).  ...  up to 24 hours ahead.  ... 
doi:10.1109/access.2021.3098631 fatcat:xxwcqgdppneincrym7vm73edcq

Optimization Models for EV Aggregator Participation in a Manual Reserve Market

Ricardo J. Bessa, Manuel A. Matos
2013 IEEE Transactions on Power Systems  
Furthermore, two operational management algorithms covering alternative gate closures (i.e., day-ahead and hour-ahead) are also described.  ...  A casestudy with data from the Iberian electricity market and synthetic EV time series is used for evaluating the algorithms.  ...  The simulation time step is 30 minutes. Each EV was characterized in terms of battery size and consumption per km.  ... 
doi:10.1109/tpwrs.2012.2233222 fatcat:c4ntuqzyrrgujokrpmkhnwki3a

Abstracts from the 9th DACH+ Conference on Energy Informatics

2020 Energy Informatics  
Energy Informatics 2020, 3(Suppl 2):P1 Summary A successful deployment and operation of smart grids depends on the reliability and security of the protocols used to gather data from the various components  ...  By applying this process to a well-known implementation of the IEC 61850 protocol, several bugs have been found and reported to the developers.  ...  Availability of data and materials After the final publication of the results, the model and the model results will be made freely accessible via an online platform.  ... 
doi:10.1186/s42162-020-00113-9 fatcat:dgbgi6ybzjextfsllsuv4wqokq

Performance of Heuristic Optimization in Coordination of Plug-In Electric Vehicles Charging

Sara Deilami, Amir Masoum, Mohammad Masoum, A. Abu- Siada
2013 International Journal of Renewable Energy and Biofuels  
The impacts of optimization period T (varied from 15 minutes to 24 hours) and optimization time interval (varied 15 minutes to one hour) on the performance, accuracy and speed of the H-LMA is investigated  ...  period T while maintaining network operation criteria such as power generation and bus voltages within their permissible limits.  ...  The peak power consumption of a house is assumed to be on average 2 kW with a power factor of 0.9.  ... 
doi:10.5171/2013.898203 fatcat:uycqtywcprharm743a5lzgz63y

Artificial intelligence techniques for enabling Big Data services in distribution networks: A review

Sara Barja-Martinez, Mònica Aragüés-Peñalba, Íngrid Munné-Collado, Pau Lloret-Gallego, Eduard Bullich-Massagué, Roberto Villafafila-Robles
2021 Renewable & Sustainable Energy Reviews  
AI can be applied in all the power system domains, including generation, transmission, distribution and consumption.  ...  Considering the potential of the data collected in electrical networks, the scientific community is applying and developing AI techniques for power system applications [9] .  ...  Multiple ML methods such as ANNs, SVMs and Gaussian Process Regression are studied in [203] for wind and solar power generation.  ... 
doi:10.1016/j.rser.2021.111459 fatcat:43mrjxzeijhrpll35ifzyihtde

Human in the loop heterogeneous modelling of thermostatically controlled loads for demand side management studies

Alexandros Kleidaras, Aristides E. Kiprakis, John S. Thompson
2018 Energy  
We anticipate similar realistic models to be used for real world applications and aggregation methods based on them, especially for cold loads and similar TCLs, where external factors and heterogeneity  ...  Most models developed so far use Wiener processes to represent this behaviour, which in aggregated models, such as those based on Coupled Fokker-Planck Equations (CFPE), have a negligible effect as "white  ...  3 Hb per load type (per event) Events per day (Gaussian) MC (events, minute resolution) fluctuations were used to describe the general behaviour of the population.  ... 
doi:10.1016/j.energy.2017.12.120 fatcat:bg7zh5bkjzcznfzln4slw7damu

Machine learning methods for modelling and analysis of time series signals in geoinformatics [article]

Maria Kaselimi
2021 arXiv   pre-print
Ionospheric modeling using signal processing techniques is the subject of discussion in the present contribution.  ...  energy consumption.  ...  Given the power consumption per appliance the forward problem is to predict the total power consumption in a household.  ... 
arXiv:2109.09499v1 fatcat:6cukjkk6ivahjf56gecj7noxti
« Previous Showing results 1 — 15 out of 371 results