@INPROCEEDINGS{10078524,

  author={Etedadi, Farshad and Kelouwani, Sousso and Laurencelle, François and Henao, Nilson and Agbossou, Kodjo and Amara, Fatima},

  booktitle={2023 IEEE Texas Power and Energy Conference (TPEC)}, 

  title={Bi-Level Transactive Coordination of Energy Management Systems in a Community}, 

  year={2023},

  volume={},

  number={},

  pages={1-6},

  doi={10.1109/TPEC56611.2023.10078524}}

@INPROCEEDINGS{10078675,

  author={Dominguez, J.A. and Parrado-Duque, A. and Montoya, O. D. and Henao, N. and Campillo, J. and Agbossou, K.},

  booktitle={2023 IEEE Texas Power and Energy Conference (TPEC)}, 

  title={Techno-economic Feasibility of A Trust and Grid-aware Coordination Scheme}, 

  year={2023},

  volume={},

  number={},

  pages={1-5},

  doi={10.1109/TPEC56611.2023.10078675}}

@ARTICLE{10093061,

  author={Domínguez-Jiménez, Juan and Henao, Nilson and Agbossou, Kodjo and Parrado, Alejandro and Campillo, Javier and Nagarsheth, Shaival H.},

  journal={IEEE Open Journal of Industry Applications}, 

  title={A Stochastic Approach to Integrating Electrical Thermal Storage in Distributed Demand Response for Nordic Communities With Wind Power Generation}, 

  year={2023},

  volume={4},

  number={},

  pages={121-138},

  doi={10.1109/OJIA.2023.3264651}}

@INPROCEEDINGS{10274534,
  author={Arnedo, Rafael and Henao, Nilson and Agbossou, Kodjo and Oviedo-Cepeda, Juan Carlos and Dominguez, Juan Antonio and Toquica, David},
  booktitle={2023 IEEE 11th International Conference on Smart Energy Grid Engineering (SEGE)}, 
  title={OpenATE: A Distributed Co-simulation Engine for Transactive Energy Systems}, 
  year={2023},
  volume={},
  number={},
  pages={188-193},
  keywords={Transactive energy;Regulators;Software architecture;Computational modeling;Simulation;Stochastic processes;Software;Co-simulation;Transactive Energy Systems;Event-driven architecture;Smart Grid},
  doi={10.1109/SEGE59172.2023.10274534}}

@ARTICLE{10296018,
  author={Toquica, David and Amara, Fatima and Malhamé, Roland and Agbossou, Kodjo and Henao, Nilson and Oviedo, Juan C. and Rueda, Luis},
  journal={IEEE Transactions on Industry Applications}, 
  title={Risk Analysis of Transactive Energy Retail Markets}, 
  year={2023},
  volume={60},
  number={1},
  pages={1611-1621},
  keywords={Costs;Risk management;Forward contracts;Uncertainty;Transactive energy;Generators;Cost function;Distribution grid;forward market;local energy market;risk assessment;transactive energy},
  doi={10.1109/TIA.2023.3327320}}

@INPROCEEDINGS{10389446,
  author={Galeano-Suarez, Daniel and Oviedo-Cepeda, JC and Henao, Nilson and Agbossou, Kodjo and Toquica, David and Fournier, Michael},
  booktitle={2023 14th International Renewable Energy Congress (IREC)}, 
  title={Co-Simulation Framework OpenDSS-Python to Consider Distribution Grid Constraints in a Transactive Energy System}, 
  year={2023},
  volume={},
  number={},
  pages={1-6},
  keywords={Transactive energy;Renewable energy sources;Reactive power;Systems operation;Voltage;Quality of service;Reliability engineering;Distribution grids;Open-source;Power flow simulation;Residential demand;Transactive energy},
  doi={10.1109/IREC59750.2023.10389446}}

@article{DAB2023113550,
title = {Consensus-based time-series clustering approach to short-term load forecasting for residential electricity demand},
journal = {Energy and Buildings},
volume = {299},
pages = {113550},
year = {2023},
issn = {0378-7788},
doi = {https://doi.org/10.1016/j.enbuild.2023.113550},
url = {https://www.sciencedirect.com/science/article/pii/S0378778823007806},
author = {Khansa Dab and Nilson Henao and Shaival Nagarsheth and Yves Dubé and Simon Sansregret and Kodjo Agbossou},
keywords = {Short-term load forecasting, Aggregated load forecast, Consensus clustering, Gaussian process, Residential load patterns, Time-series},
abstract = {Load forecasting could play a crucial role in energy management and control of buildings in residential neighborhoods. In these areas, electricity demand is influenced by different phenomena accounting for climate conditions and comfort preferences. The uncertain nature of these circumstances results in power profiles with diverse patterns. Under this condition, overall load prediction is suggested by utilizing Cluster-based Aggregate Forecasting (CBAF). Accordingly, this paper proposes a unified approach to such a practice. The proposed scheme employs an unsupervised machine-learning algorithm to develop a time-series clustering scheme that performs the classification task through the k-medoids-based clustering incorporating the Dynamic Time Warping (DTW) algorithm. Subsequently, a consensus is achieved among the resultant clusters where the Jaccard similarity index adjudges the similarity measurement. The Additive Gaussian Process (AGP), a powerful non-parametric forecasting technique, is exploited to predict aggregated load at each cluster level. With low complexity and high scalability, AGP is particularly utilized to provide effective forecasting. Numerical simulations on synthetic as well as real datasets have been carried out to illustrate the effectiveness of the proposed methodology. Additionally, two comparative studies are carried out with forecasts without clustering and with the benchmark non-parametric models employing a cluster-based technique. The proposed method demonstrates significant improvement in forecasting accuracy for both datasets by reducing the error metrics and achieving 7% improvement in the coefficient of determination (R2) value as compared to the aggregated load forecast achieved without clustering. The comparative study demonstrates that the proposed method with AGP can forecast the total residential load more accurately than other benchmark models with an improvement of 26% and 21% in R2, respectively, for both datasets.}
}

Load forecasting could play a crucial role in energy management and control of buildings in residential neighborhoods. In these areas, electricity demand is influenced by different phenomena accounting for climate conditions and comfort preferences. The uncertain nature of these circumstances results in power profiles with diverse patterns. Under this condition, overall load prediction is suggested by utilizing Cluster-based Aggregate Forecasting (CBAF). Accordingly, this paper proposes a unified approach to such a practice. The proposed scheme employs an unsupervised machine-learning algorithm to develop a time-series clustering scheme that performs the classification task through the k-medoids-based clustering incorporating the Dynamic Time Warping (DTW) algorithm. Subsequently, a consensus is achieved among the resultant clusters where the Jaccard similarity index adjudges the similarity measurement. The Additive Gaussian Process (AGP), a powerful non-parametric forecasting technique, is exploited to predict aggregated load at each cluster level. With low complexity and high scalability, AGP is particularly utilized to provide effective forecasting. Numerical simulations on synthetic as well as real datasets have been carried out to illustrate the effectiveness of the proposed methodology. Additionally, two comparative studies are carried out with forecasts without clustering and with the benchmark non-parametric models employing a cluster-based technique. The proposed method demonstrates significant improvement in forecasting accuracy for both datasets by reducing the error metrics and achieving 7% improvement in the coefficient of determination (R2) value as compared to the aggregated load forecast achieved without clustering. The comparative study demonstrates that the proposed method with AGP can forecast the total residential load more accurately than other benchmark models with an improvement of 26% and 21% in R2, respectively, for both datasets.

@article{DAB2023113550,
title = {Consensus-based time-series clustering approach to short-term load forecasting for residential electricity demand},
journal = {Energy and Buildings},
volume = {299},
pages = {113550},
year = {2023},
issn = {0378-7788},
doi = {https://doi.org/10.1016/j.enbuild.2023.113550},
url = {https://www.sciencedirect.com/science/article/pii/S0378778823007806},
author = {Khansa Dab and Nilson Henao and Shaival Nagarsheth and Yves Dubé and Simon Sansregret and Kodjo Agbossou},
keywords = {Short-term load forecasting, Aggregated load forecast, Consensus clustering, Gaussian process, Residential load patterns, Time-series},
abstract = {Load forecasting could play a crucial role in energy management and control of buildings in residential neighborhoods. In these areas, electricity demand is influenced by different phenomena accounting for climate conditions and comfort preferences. The uncertain nature of these circumstances results in power profiles with diverse patterns. Under this condition, overall load prediction is suggested by utilizing Cluster-based Aggregate Forecasting (CBAF). Accordingly, this paper proposes a unified approach to such a practice. The proposed scheme employs an unsupervised machine-learning algorithm to develop a time-series clustering scheme that performs the classification task through the k-medoids-based clustering incorporating the Dynamic Time Warping (DTW) algorithm. Subsequently, a consensus is achieved among the resultant clusters where the Jaccard similarity index adjudges the similarity measurement. The Additive Gaussian Process (AGP), a powerful non-parametric forecasting technique, is exploited to predict aggregated load at each cluster level. With low complexity and high scalability, AGP is particularly utilized to provide effective forecasting. Numerical simulations on synthetic as well as real datasets have been carried out to illustrate the effectiveness of the proposed methodology. Additionally, two comparative studies are carried out with forecasts without clustering and with the benchmark non-parametric models employing a cluster-based technique. The proposed method demonstrates significant improvement in forecasting accuracy for both datasets by reducing the error metrics and achieving 7% improvement in the coefficient of determination (R2) value as compared to the aggregated load forecast achieved without clustering. The comparative study demonstrates that the proposed method with AGP can forecast the total residential load more accurately than other benchmark models with an improvement of 26% and 21% in R2, respectively, for both datasets.}
}

Load forecasting could play a crucial role in energy management and control of buildings in residential neighborhoods. In these areas, electricity demand is influenced by different phenomena accounting for climate conditions and comfort preferences. The uncertain nature of these circumstances results in power profiles with diverse patterns. Under this condition, overall load prediction is suggested by utilizing Cluster-based Aggregate Forecasting (CBAF). Accordingly, this paper proposes a unified approach to such a practice. The proposed scheme employs an unsupervised machine-learning algorithm to develop a time-series clustering scheme that performs the classification task through the k-medoids-based clustering incorporating the Dynamic Time Warping (DTW) algorithm. Subsequently, a consensus is achieved among the resultant clusters where the Jaccard similarity index adjudges the similarity measurement. The Additive Gaussian Process (AGP), a powerful non-parametric forecasting technique, is exploited to predict aggregated load at each cluster level. With low complexity and high scalability, AGP is particularly utilized to provide effective forecasting. Numerical simulations on synthetic as well as real datasets have been carried out to illustrate the effectiveness of the proposed methodology. Additionally, two comparative studies are carried out with forecasts without clustering and with the benchmark non-parametric models employing a cluster-based technique. The proposed method demonstrates significant improvement in forecasting accuracy for both datasets by reducing the error metrics and achieving 7% improvement in the coefficient of determination (R2) value as compared to the aggregated load forecast achieved without clustering. The comparative study demonstrates that the proposed method with AGP can forecast the total residential load more accurately than other benchmark models with an improvement of 26% and 21% in R2, respectively, for both datasets.

@article{ETEDADI2023120833,
title = {Consensus and sharing based distributed coordination of home energy management systems with demand response enabled baseboard heaters},
journal = {Applied Energy},
volume = {336},
pages = {120833},
year = {2023},
issn = {0306-2619},
doi = {https://doi.org/10.1016/j.apenergy.2023.120833},
url = {https://www.sciencedirect.com/science/article/pii/S0306261923001976},
author = {Farshad Etedadi and Sousso Kelouwani and Kodjo Agbossou and Nilson Henao and François Laurencelle},
keywords = {Demand response, Home energy management, Coordination, Smart grids, Gain distribution, Transactive energy},
abstract = {The repercussions from excessive penetration of uncoordinated Home Energy Management Systems (HEMSs) have proven to be pernicious in the distribution system regarding contingencies, instabilities, and rebound peaks. This paper aims to design a distributed coordination technique with the required topology to coordinate transactive HEMSs with demand response enabled electric baseboard heater thermostats to avoid the detrimental effects of uncoordinated HEMSs in a residential group. Specifically, the proposed technique establishes a consensus to fulfill individual as well as shared objectives by modifying consumers’ consumption patterns. The shared objective is to flatten the aggregated profile and decrease the total cost in the grid. In addition, an incentive policy has been designed to pay a total reward to the team for encouraging consumers to participate in the coordination. The presented coordination technique comprises a Shapley game-based reward-sharing mechanism and an incentive-compatible mechanism, where the team’s gain is distributed among the players based on their contribution. Besides, the coordination leads to agents’ complementary decision-making and mitigates the grid challenges. The functionality and effectiveness of the proposed coordinated HEMSs algorithm are tested for a set of different case studies based on user preferences and coordination levels. The simulation results indicate that the proposed coordination improves aggregated profile’s load factor up to 0.85 and reduces the electricity bill by 21.4%.}
}

The repercussions from excessive penetration of uncoordinated Home Energy Management Systems (HEMSs) have proven to be pernicious in the distribution system regarding contingencies, instabilities, and rebound peaks. This paper aims to design a distributed coordination technique with the required topology to coordinate transactive HEMSs with demand response enabled electric baseboard heater thermostats to avoid the detrimental effects of uncoordinated HEMSs in a residential group. Specifically, the proposed technique establishes a consensus to fulfill individual as well as shared objectives by modifying consumers’ consumption patterns. The shared objective is to flatten the aggregated profile and decrease the total cost in the grid. In addition, an incentive policy has been designed to pay a total reward to the team for encouraging consumers to participate in the coordination. The presented coordination technique comprises a Shapley game-based reward-sharing mechanism and an incentive-compatible mechanism, where the team’s gain is distributed among the players based on their contribution. Besides, the coordination leads to agents’ complementary decision-making and mitigates the grid challenges. The functionality and effectiveness of the proposed coordinated HEMSs algorithm are tested for a set of different case studies based on user preferences and coordination levels. The simulation results indicate that the proposed coordination improves aggregated profile’s load factor up to 0.85 and reduces the electricity bill by 21.4%.

@ARTICLE{10296018,

  author={Toquica, David and Amara, Fatima and Malhamé, Roland and Agbossou, Kodjo and Henao, Nilson and Oviedo, Juan C. and Rueda, Luis},

  journal={IEEE Transactions on Industry Applications}, 

  title={Risk Analysis of Transactive Energy Retail Markets}, 

  year={2023},

  volume={},

  number={},

  pages={1-11},

  doi={10.1109/TIA.2023.3327320}}

@Article{s23167288,
AUTHOR = {Hosseini, Sayed Saeed and Delcroix, Benoit and Henao, Nilson and Agbossou, Kodjo and Kelouwani, Sousso},
TITLE = {Towards Feasible Solutions for Load Monitoring in Quebec Residences},
JOURNAL = {Sensors},
VOLUME = {23},
YEAR = {2023},
NUMBER = {16},
ARTICLE-NUMBER = {7288},
URL = {https://www.mdpi.com/1424-8220/23/16/7288},
PubMedID = {37631824},
ISSN = {1424-8220},
ABSTRACT = {For many years, energy monitoring at the most disaggregate level has been mainly sought through the idea of Non-Intrusive Load Monitoring (NILM). Developing a practical application of this concept in the residential sector can be impeded by the technical characteristics of case studies. Accordingly, several databases, mainly from Europe and the US, have been publicly released to enable basic research to address NILM issues raised by their challenging features. Nevertheless, the resultant enhancements are limited to the properties of these datasets. Such a restriction has caused NILM studies to overlook residential scenarios related to geographically-specific regions and existent practices to face unexplored situations. This paper presents applied research on NILM in Quebec residences to reveal its barriers to feasible implementations. It commences with a concise discussion about a successful NILM idea to highlight its essential requirements. Afterward, it provides a comparative statistical analysis to represent the specificity of the case study by exploiting real data. Subsequently, this study proposes a combinatory approach to load identification that utilizes the promise of sub-meter smart technologies and integrates the intrusive aspect of load monitoring with the non-intrusive one to alleviate NILM difficulties in Quebec residences. A load disaggregation technique is suggested to manifest these complications based on supervised and unsupervised machine learning designs. The former is aimed at extracting overall heating demand from the aggregate one while the latter is designed for disaggregating the residual load. The results demonstrate that geographically-dependent cases create electricity consumption scenarios that can deteriorate the performance of existing NILM methods. From a realistic standpoint, this research elaborates on critical remarks to realize viable NILM systems, particularly in Quebec houses.},
DOI = {10.3390/s23167288}
}

For many years, energy monitoring at the most disaggregate level has been mainly sought through the idea of Non-Intrusive Load Monitoring (NILM). Developing a practical application of this concept in the residential sector can be impeded by the technical characteristics of case studies. Accordingly, several databases, mainly from Europe and the US, have been publicly released to enable basic research to address NILM issues raised by their challenging features. Nevertheless, the resultant enhancements are limited to the properties of these datasets. Such a restriction has caused NILM studies to overlook residential scenarios related to geographically-specific regions and existent practices to face unexplored situations. This paper presents applied research on NILM in Quebec residences to reveal its barriers to feasible implementations. It commences with a concise discussion about a successful NILM idea to highlight its essential requirements. Afterward, it provides a comparative statistical analysis to represent the specificity of the case study by exploiting real data. Subsequently, this study proposes a combinatory approach to load identification that utilizes the promise of sub-meter smart technologies and integrates the intrusive aspect of load monitoring with the non-intrusive one to alleviate NILM difficulties in Quebec residences. A load disaggregation technique is suggested to manifest these complications based on supervised and unsupervised machine learning designs. The former is aimed at extracting overall heating demand from the aggregate one while the latter is designed for disaggregating the residual load. The results demonstrate that geographically-dependent cases create electricity consumption scenarios that can deteriorate the performance of existing NILM methods. From a realistic standpoint, this research elaborates on critical remarks to realize viable NILM systems, particularly in Quebec houses.

@INPROCEEDINGS{10274534,

  author={Arnedo, Rafael and Henao, Nilson and Agbossou, Kodjo and Oviedo-Cepeda, Juan Carlos and Dominguez, Juan Antonio and Toquica, David},

  booktitle={2023 IEEE 11th International Conference on Smart Energy Grid Engineering (SEGE)}, 

  title={OpenATE: A Distributed Co-simulation Engine for Transactive Energy Systems}, 

  year={2023},

  volume={},

  number={},

  pages={188-193},

  doi={10.1109/SEGE59172.2023.10274534}}

@article{ETEDADI2023120833,
title = {Consensus and sharing based distributed coordination of home energy management systems with demand response enabled baseboard heaters},
journal = {Applied Energy},
volume = {336},
pages = {120833},
year = {2023},
issn = {0306-2619},
doi = {https://doi.org/10.1016/j.apenergy.2023.120833},
url = {https://www.sciencedirect.com/science/article/pii/S0306261923001976},
author = {Farshad Etedadi and Sousso Kelouwani and Kodjo Agbossou and Nilson Henao and François Laurencelle},
keywords = {Demand response, Home energy management, Coordination, Smart grids, Gain distribution, Transactive energy},
abstract = {The repercussions from excessive penetration of uncoordinated Home Energy Management Systems (HEMSs) have proven to be pernicious in the distribution system regarding contingencies, instabilities, and rebound peaks. This paper aims to design a distributed coordination technique with the required topology to coordinate transactive HEMSs with demand response enabled electric baseboard heater thermostats to avoid the detrimental effects of uncoordinated HEMSs in a residential group. Specifically, the proposed technique establishes a consensus to fulfill individual as well as shared objectives by modifying consumers’ consumption patterns. The shared objective is to flatten the aggregated profile and decrease the total cost in the grid. In addition, an incentive policy has been designed to pay a total reward to the team for encouraging consumers to participate in the coordination. The presented coordination technique comprises a Shapley game-based reward-sharing mechanism and an incentive-compatible mechanism, where the team’s gain is distributed among the players based on their contribution. Besides, the coordination leads to agents’ complementary decision-making and mitigates the grid challenges. The functionality and effectiveness of the proposed coordinated HEMSs algorithm are tested for a set of different case studies based on user preferences and coordination levels. The simulation results indicate that the proposed coordination improves aggregated profile’s load factor up to 0.85 and reduces the electricity bill by 21.4%.}
}

The repercussions from excessive penetration of uncoordinated Home Energy Management Systems (HEMSs) have proven to be pernicious in the distribution system regarding contingencies, instabilities, and rebound peaks. This paper aims to design a distributed coordination technique with the required topology to coordinate transactive HEMSs with demand response enabled electric baseboard heater thermostats to avoid the detrimental effects of uncoordinated HEMSs in a residential group. Specifically, the proposed technique establishes a consensus to fulfill individual as well as shared objectives by modifying consumers’ consumption patterns. The shared objective is to flatten the aggregated profile and decrease the total cost in the grid. In addition, an incentive policy has been designed to pay a total reward to the team for encouraging consumers to participate in the coordination. The presented coordination technique comprises a Shapley game-based reward-sharing mechanism and an incentive-compatible mechanism, where the team’s gain is distributed among the players based on their contribution. Besides, the coordination leads to agents’ complementary decision-making and mitigates the grid challenges. The functionality and effectiveness of the proposed coordinated HEMSs algorithm are tested for a set of different case studies based on user preferences and coordination levels. The simulation results indicate that the proposed coordination improves aggregated profile’s load factor up to 0.85 and reduces the electricity bill by 21.4%.

@ARTICLE{9775945,

  author={Fraija, Alejandro and Agbossou, Kodjo and Henao, Nilson and Kelouwani, Sousso and Fournier, Michaël and Hosseini, Sayed Saeed},

  journal={IEEE Access}, 

  title={A Discount-Based Time-of-Use Electricity Pricing Strategy for Demand Response With Minimum Information Using Reinforcement Learning}, 

  year={2022},

  volume={10},

  number={},

  pages={54018-54028},

  doi={10.1109/ACCESS.2022.3175839}}

@ARTICLE{9775959,

  author={Dante, Abdoul Wahab and Kelouwani, Sousso and Agbossou, Kodjo and Henao, Nilson and Bouchard, Jonathan and Hosseini, Sayed Saeed},

  journal={IEEE Access}, 

  title={A Stochastic Approach to Designing Plug-In Electric Vehicle Charging Controller for Residential Applications}, 

  year={2022},

  volume={10},

  number={},

  pages={52876-52889},

  doi={10.1109/ACCESS.2022.3175817}}

@ARTICLE{9783190,

  author={Toquica, David and Agbossou, Kodjo and Malhamé, Roland and Henao, Nilson and Kelouwani, Sousso and Fournier, Michaël},

  journal={IEEE Open Journal of Industry Applications}, 

  title={A Recommender System for Predictive Control of Heating Systems in Economic Demand Response Programs}, 

  year={2022},

  volume={3},

  number={},

  pages={79-89},

  doi={10.1109/OJIA.2022.3178235}}

@INPROCEEDINGS{9889758,

  author={Aliabadi, Farshad Etedadi and Agbossou, Kodjo and Henao, Nilson and Kelouwani, Sousso and Laurencelle, François},

  booktitle={2022 IEEE 10th International Conference on Smart Energy Grid Engineering (SEGE)}, 

  title={Distributed Residential Demand Response Using Building Mass and Electric Thermal Storage System}, 

  year={2022},

  volume={},

  number={},

  pages={19-25},

  doi={10.1109/SEGE55279.2022.9889758}}

@INPROCEEDINGS{9898470,

  author={Toquica, David and Amara, Fatima and Agbossou, Kodjo and Henao, Nilson and Oviedo, Juan C. and Rueda, Luis},

  booktitle={2022 International Conference on Smart Energy Systems and Technologies (SEST)}, 

  title={Risk Assessment of Local Forward Markets in a Transactive Energy System}, 

  year={2022},

  volume={},

  number={},

  pages={1-6},

  doi={10.1109/SEST53650.2022.9898470}}

@ARTICLE{9925213,

  author={Sabir, Sameer and Kelouwani, Sousso and Henao, Nilson and Agbossou, Kodjo and Fournier, Michaël and Nagarsheth, Shaival Hemant},

  journal={IEEE Access}, 

  title={A Computationally Efficient Method for Energy Allocation in Spot Markets With Application to Transactive Energy Systems}, 

  year={2022},

  volume={10},

  number={},

  pages={111351-111362},

  doi={10.1109/ACCESS.2022.3215954}}

@INPROCEEDINGS{9969092,

  author={Dominguez, J. A. and Rueda, L. and Henao, N. and Agbossou, K. and Campillo, J.},

  booktitle={IECON 2022 – 48th Annual Conference of the IEEE Industrial Electronics Society}, 

  title={Distributed Co-simulation for Smart Homes Energy Management in the Presence of Electrical Thermal Storage}, 

  year={2022},

  volume={},

  number={},

  pages={1-6},

  doi={10.1109/IECON49645.2022.9969092}}

@INPROCEEDINGS{10012251,

  author={Sabir, Sameer and Kelouwani, Sousso and Hosseini, Sayed Saeed and Henao, Nilson and Fournier, Michaël and Agbossou, Kodjo},

  booktitle={2022 North American Power Symposium (NAPS)}, 

  title={A Bid Selection Model for Computational Cost Reduction of Transactive Energy Aggregator in Smart Grids}, 

  year={2022},

  volume={},

  number={},

  pages={1-6},

  doi={10.1109/NAPS56150.2022.10012251}}

@inproceedings{10.1145/3563357.3566151,
author = {Hosseini, Sayed Saeed and Delcroix, Benoit and Henao, Nilson and Agbossou, Kodjo and Kelouwani, Sousso},
title = {A Case Study on Obstacles to Feasible NILM Solutions for Energy Disaggregation in Quebec Residences},
year = {2022},
isbn = {9781450398909},
publisher = {Association for Computing Machinery},
address = {New York, NY, USA},
url = {https://doi.org/10.1145/3563357.3566151},
doi = {10.1145/3563357.3566151},
abstract = {The Non-Intrusive Load Monitoring (NILM) concept is suggested as a practical means for energy monitoring at the most disaggregated level. Notwithstanding, a viable solution to this idea for residential applications should overcome its common and specific issues raised by technical specifications of the case study. Knowing the fact that the former has been dealt with through basic research for many years, this study presents an applied research to examine actual implementations. It focuses on load disaggregation in Quebec residences by proposing a combinatory approach based on supervised and unsupervised machine learning techniques. The proposed method aims to identify major appliances by extracting overall heating demand from the aggregated one first while exploiting low sampling rate data of active power as the only source of information. The results of this work emphasize real circumstances under which existing NILM methods can be challenged. From a realistic viewpoint, this paper discusses essential remarks inevitable to achieve a fruitful NILM system, specifically, for the Quebec case.},
booktitle = {Proceedings of the 9th ACM International Conference on Systems for Energy-Efficient Buildings, Cities, and Transportation},
pages = {363–367},
numpages = {5},
keywords = {baseboard heaters, load disaggregation, non-intrusive load monitoring (NILM), datasets},
location = {Boston, Massachusetts},
series = {BuildSys '22}
}

The Non-Intrusive Load Monitoring (NILM) concept is suggested as a practical means for energy monitoring at the most disaggregated level. Notwithstanding, a viable solution to this idea for residential applications should overcome its common and specific issues raised by technical specifications of the case study. Knowing the fact that the former has been dealt with through basic research for many years, this study presents an applied research to examine actual implementations. It focuses on load disaggregation in Quebec residences by proposing a combinatory approach based on supervised and unsupervised machine learning techniques. The proposed method aims to identify major appliances by extracting overall heating demand from the aggregated one first while exploiting low sampling rate data of active power as the only source of information. The results of this work emphasize real circumstances under which existing NILM methods can be challenged. From a realistic viewpoint, this paper discusses essential remarks inevitable to achieve a fruitful NILM system, specifically, for the Quebec case.

@article{DAB2022111459,
title = {A compositional kernel based gaussian process approach to day-ahead residential load forecasting},
journal = {Energy and Buildings},
volume = {254},
pages = {111459},
year = {2022},
issn = {0378-7788},
doi = {https://doi.org/10.1016/j.enbuild.2021.111459},
url = {https://www.sciencedirect.com/science/article/pii/S037877882100743X},
author = {Khansa Dab and Kodjo Agbossou and Nilson Henao and Yves Dubé and Sousso Kelouwani and Sayed Saeed Hosseini},
keywords = {Gaussian process, Kernels interactions, Bayesian inference method, Aggregated load forecasting, Non-parametric regression approach},
abstract = {Load forecasting is an expected ability of electric power networks to enable effective capacity planning. This paper proposes a probabilistic approach to short-term load forecasting (STLF) of residential power consumption. The proposed method is based on Bayesian regression modeling. It utilizes an additive Gaussian Process (GP) to estimate climate-sensitive and calendar factors of power demand. The GP model is constructed by using a set of compositional kernels that represent the most significant interactions between input variables. Such collection is built up through a sampling method, capable of selecting the n-upmost order-based interactions. Moreover, a technique is performed to deal with challenges related to multivariate input and large dataset training complexity. The forecasting model is applied to actual power consumption data of a set of houses, located in Quebec, during winter. The results demonstrate that the suggested scheme is highly efficient to model and predict residential electricity use. Furthermore, it is competitive with other forecasting algorithms, as manifested by a comparative analysis.}
}

Load forecasting is an expected ability of electric power networks to enable effective capacity planning. This paper proposes a probabilistic approach to short-term load forecasting (STLF) of residential power consumption. The proposed method is based on Bayesian regression modeling. It utilizes an additive Gaussian Process (GP) to estimate climate-sensitive and calendar factors of power demand. The GP model is constructed by using a set of compositional kernels that represent the most significant interactions between input variables. Such collection is built up through a sampling method, capable of selecting the n-upmost order-based interactions. Moreover, a technique is performed to deal with challenges related to multivariate input and large dataset training complexity. The forecasting model is applied to actual power consumption data of a set of houses, located in Quebec, during winter. The results demonstrate that the suggested scheme is highly efficient to model and predict residential electricity use. Furthermore, it is competitive with other forecasting algorithms, as manifested by a comparative analysis.

@ARTICLE{9363112,

  author={Etedadi Aliabadi, Farshad and Agbossou, Kodjo and Kelouwani, Sousso and Henao, Nilson and Hosseini, Sayed Saeed},

  journal={IEEE Access}, 

  title={Coordination of Smart Home Energy Management Systems in Neighborhood Areas: A Systematic Review}, 

  year={2021},

  volume={9},

  number={},

  pages={36417-36443},

  doi={10.1109/ACCESS.2021.3061995}}

@ARTICLE{9367182,

  author={Rueda, Luis and Sansregret, Simon and Le Lostec, Brice and Agbossou, Kodjo and Henao, Nilson and Kelouwani, Sousso},

  journal={IEEE Access}, 

  title={A Probabilistic Model to Predict Household Occupancy Profiles for Home Energy Management Applications}, 

  year={2021},

  volume={9},

  number={},

  pages={38187-38201},

  doi={10.1109/ACCESS.2021.3063502}}

@ARTICLE{9491101,

  author={Rueda, Luis and Agbossou, Kodjo and Henao, Nilson and Kelouwani, Sousso and Oviedo-Cepeda, Juan C. and Le Lostec, Brice and Sansregret, Simon and Fournier, Michaël},

  journal={IEEE Access}, 

  title={Online Unsupervised Occupancy Anticipation System Applied to Residential Heat Load Management}, 

  year={2021},

  volume={9},

  number={},

  pages={109806-109821},

  doi={10.1109/ACCESS.2021.3098631}}

@INPROCEEDINGS{9621744,

  author={Toquica, David and Agbossou, Kodjo and Henao, Nilson and Malhamé, Roland and Kelouwani, Sousso and Oviedo-Cepedaz, Juan C.},

  booktitle={2021 IEEE Electrical Power and Energy Conference (EPEC)}, 

  title={Market-Clearing Mechanism for Demand Aggregation at the distribution level through Transactive Energy}, 

  year={2021},

  volume={},

  number={},

  pages={334-339},

  doi={10.1109/EPEC52095.2021.9621744}}

@INPROCEEDINGS{9632002,

  author={Parrado-Duque, A. and Kelouwani, S. and Agbossou, K. and Hosseini, S. and Henao, N. and Amara, F.},

  booktitle={2021 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm)}, 

  title={A Comparative Analysis of Machine Learning Methods for Short-Term Load Forecasting Systems}, 

  year={2021},

  volume={},

  number={},

  pages={270-275},

  doi={10.1109/SmartGridComm51999.2021.9632002}}

@article{TOQUICA2021100019,
title = {Prevision and planning for residential agents in a transactive energy environment},
journal = {Smart Energy},
volume = {2},
pages = {100019},
year = {2021},
issn = {2666-9552},
doi = {https://doi.org/10.1016/j.segy.2021.100019},
url = {https://www.sciencedirect.com/science/article/pii/S2666955221000198},
author = {David Toquica and Kodjo Agbossou and Nilson Henao and Roland Malhamé and Sousso Kelouwani and Fatima Amara},
keywords = {Agents interaction, Forward market, Multi-agent system, Price-elasticity, Prosumer, Smart energy markets, Stackelberg game, Transactive energy, Utility function},
abstract = {Transactive Energy (TE) has brought exciting opportunities for all stakeholders in energy markets by enabling management decentralization. This new paradigm empowers demand-side agents to play a more active role through coordinating, cooperating, and negotiating with other agents. Nevertheless, most of these agents are not used to process market signals and develop optimal strategies, especially in the residential sector. Accordingly, it is indispensable to create tools that automate and facilitate demand-side participation in TE systems. This paper presents a new methodology for residential automated agents to perform two key tasks: prevision and planning. Specifically, the proposed method is applied to a forward market where agents' planning is a fundamental step to maintain the dynamic balance between demand and generation. Since planning depends on future demand, agents' prevision of consumption is an inevitable part of this step. The procedures for automating the targeted tasks are developed in a general way for residential prosumers and consumers, interacting at the distribution level. These players are managed by a demand aggregator as the leader by means of the Stackelberg game. The suggested process results in a TE setup for multi-stage single-side auctions, useful to manage future Smart Energy Markets. Through simulated transactions, this paper examines the market clearing mechanism and the convenience of agents' planning. The results show that customers with higher price-elasticity leverage lower costs periods. However, they make it harder to reduce the peak-to-average ratio of the aggregated demand profile since a unique price signal can create prisoner's dilemma conditions.}
}

Transactive Energy (TE) has brought exciting opportunities for all stakeholders in energy markets by enabling management decentralization. This new paradigm empowers demand-side agents to play a more active role through coordinating, cooperating, and negotiating with other agents. Nevertheless, most of these agents are not used to process market signals and develop optimal strategies, especially in the residential sector. Accordingly, it is indispensable to create tools that automate and facilitate demand-side participation in TE systems. This paper presents a new methodology for residential automated agents to perform two key tasks: prevision and planning. Specifically, the proposed method is applied to a forward market where agents' planning is a fundamental step to maintain the dynamic balance between demand and generation. Since planning depends on future demand, agents' prevision of consumption is an inevitable part of this step. The procedures for automating the targeted tasks are developed in a general way for residential prosumers and consumers, interacting at the distribution level. These players are managed by a demand aggregator as the leader by means of the Stackelberg game. The suggested process results in a TE setup for multi-stage single-side auctions, useful to manage future Smart Energy Markets. Through simulated transactions, this paper examines the market clearing mechanism and the convenience of agents' planning. The results show that customers with higher price-elasticity leverage lower costs periods. However, they make it harder to reduce the peak-to-average ratio of the aggregated demand profile since a unique price signal can create prisoner's dilemma conditions.

@article{DEVIA2021110674,
title = {An evolutionary approach to modeling and control of space heating and thermal storage systems},
journal = {Energy and Buildings},
volume = {234},
pages = {110674},
year = {2021},
issn = {0378-7788},
doi = {https://doi.org/10.1016/j.enbuild.2020.110674},
url = {https://www.sciencedirect.com/science/article/pii/S0378778820334605},
author = {William Devia and Kodjo Agbossou and Alben Cardenas},
keywords = {Distributed model predictive control, Electric thermal storage, Evolutionary algorithms, Demand-side management, Thermal parameter estimation, NSGA-II},
abstract = {Home Energy Management systems are in a rapid development curve, supported by the advancements in computational intelligence, smart appliances, and new smart-grid frameworks. These systems are a fundamental part to implement demand-side management strategies and to shift local energy demand to periods of lower consumption effectively. In this paper, we explore the application of distributed co-evolutionary optimization algorithms and an agent-based architecture to reduce the consumption profile signature of the heating system during the critical peak demand periods, by reducing costs and respecting the comfort constraints of the occupants. The proposed control architecture targets the typical baseboard space heating systems and electrical thermal storage systems, as these represent a large portion of the energy usage in Nordic countries and are commonly controlled by room independent thermostats, which could be easily replaced by smart devices running an algorithm as the one presented in this work. Results prove the strategy proposed getting a cost reduction of up to 23% and a peak-to-average ratio decrease of up to 25% for reference scenarios. Also, an emulation Simulink model is developed to recreate a house and the different heating loads studied in this paper and an experimental test bed is built to model a real ETS system, two different complexity degree RC models are proposed to describe such systems.}
}

Home Energy Management systems are in a rapid development curve, supported by the advancements in computational intelligence, smart appliances, and new smart-grid frameworks. These systems are a fundamental part to implement demand-side management strategies and to shift local energy demand to periods of lower consumption effectively. In this paper, we explore the application of distributed co-evolutionary optimization algorithms and an agent-based architecture to reduce the consumption profile signature of the heating system during the critical peak demand periods, by reducing costs and respecting the comfort constraints of the occupants. The proposed control architecture targets the typical baseboard space heating systems and electrical thermal storage systems, as these represent a large portion of the energy usage in Nordic countries and are commonly controlled by room independent thermostats, which could be easily replaced by smart devices running an algorithm as the one presented in this work. Results prove the strategy proposed getting a cost reduction of up to 23% and a peak-to-average ratio decrease of up to 25% for reference scenarios. Also, an emulation Simulink model is developed to recreate a house and the different heating loads studied in this paper and an experimental test bed is built to model a real ETS system, two different complexity degree RC models are proposed to describe such systems.