« Retour

Roduit Pierre

Professeur-e HES Ordinaire, Responsable de l'institut Energie et environnement

Compétences principales

Professeur-e HES Ordinaire, Responsable de l'institut Energie et environnement

Téléphone: +41 58 606 87 39

Bureau: ENP.23.N205

HES-SO Valais-Wallis - Haute Ecole d'Ingénierie
Rue de l'Industrie 23, 1950 Sion, CH

Domaine
Technique et IT

Filière principale
Energie et techniques environnementales

Institut
Institut Energie et environnement

BSc HES-SO en Energie et techniques environnementales - HES-SO Valais-Wallis - Haute Ecole d'Ingénierie

Informatics
Information Systems

En cours

Industrialisation of energy services for small buildings

Rôle: Co-requérant(s)

Financement: Innosuisse

Description du projet :

This project will develop an energy management ecosystem promoting the large-scale deployment of efficiency and flexibility services in small buildings. The ecosystem enables a low-cost straightforward deployment of multiple services and novel business models.

Equipe de recherche au sein de la HES-SO: Revaz Frédéric , Roduit Pierre , Gabioud Dominique

Partenaires professionnels: Riva Frédéric, WAGO Contact AG

Durée du projet: 02.01.2023 - 01.01.2025

Montant global du projet: 941'813 CHF

Statut: En cours

Development of a handheld non-intrusive cavitation detector using ML for hydropower and a new independent maintenance service offer.

AGP

Rôle: Collaborateur/trice

Requérant(e)s: VS - Institut Energie et environnement

Financement: Hydro Exploitation; Innosuisse

Description du projet : Avec l'intégration massive des nouvelles énergies renouvelables, la flexibilité des centrales hydroélectriques est cruciale pour maintenir la stabilité du réseau. Pour augmenter cette flexibilité, les machines hydrauliques sont utilisées en dehors de leur plage de fonctionnement optimale où des phénomènes complexes apparaissent. Parmi eux, la cavitation qui provoque une usure importante et impose des révisions régulières et coûteuses. Afin de compléter la surveillance des machines qui seront de plus en plus sujets à ce type d'usure, HYDRO Exploitation, responsable de l'exploitation et de la maintenance de 20% du parc hydroélectrique suisse, a approché la HES SO VS pour développer une solution de monitoring de la cavitation afin de compléter leurs outils de surveillance et fournir un service d'assessment du fonctionnement flexible d'une centrale. Un module de détection sonore de la cavitation, peu coûteux et facilement transportable, sera développé. Le spectre fréquentiel du signal sonore sera traité par une adaptation innovante des « Point Distribution Model au distribution cumulative », permettant d'identifier et de visualiser les différents régimes de cavitation. Les données d'analyse découvertes seront utilisées, afin d'identifier précisément les points de fonctionnement responsables de défauts et de pannes potentielles et faciliter la maintenance predictive. L'usage d'algorithmes de Machine Learning et de Deep Learning permettront ensuite de construire des modèles prédictifs à partir des données acquises lors de l'utilisation de ce nouveau module en continu. Le traitement et la visualisation des données seront directement intégrés dans l'infrastructure IT d'HYDRO Exploitation qui souhaite une indépendance dans le traitement du signal et une certaine souveraineté des données récoltées, leur permettant d'offrir une nouvelle gamme de services et de développer une nouvelle expertise avec un potentiel de commercialisation important en Suisse et à l'international

, , , , , , , , , , , , , , , , , , Equipe de recherche au sein de la HES-SO: Genoud Dominique Münch-Alligné Cécile Wannier David Hasmatuchi Vlad Constantin Vianin Jérémie Maître Gilbert Pereira Helena Arbellay Olivier Alder Jean-Marie Ferreira Da Silva João Carlos Cosandey Solène Pacot Olivier Gustin Gwenaëlle Chianella Nicolas Lenoir Cédric Treboux Jérôme Amini Ali Neveu Emilie Roduit Pierre

Partenaires académiques: VS - Institut Systèmes industriels; VS - Institut Informatique; VS - Institut Energie et environnement

Durée du projet: 01.03.2022 - 28.02.2025

Montant global du projet: 443'797 CHF

Statut: En cours

domOS

Rôle: Co-requérant(s)

Financement: EU

Description du projet :

H2020 project on Operating System for Smart Services in Buildings.

Equipe de recherche au sein de la HES-SO: Roduit Pierre , Gabioud Dominique

Durée du projet: 01.09.2020 - 01.09.2023

Montant global du projet: 4'500'000 CHF

Statut: En cours

Terminés

Analyse de performance GOFLEX

AGP

Rôle: Requérant(e) principal(e)

Financement: FMV SA; ESR

Description du projet : Dans le cadre du démonstrateur ESR / Sion du projet GOFLEX, une chaîne de valorisation de la flexibilité de différents processus (chauffage / production d'eau chaude sanitaire électrique, recharge de véhicules électriques, processus industriels) a été mise en place dans le but principal de minimiser l'énergie d'ajustement. Les éléments centraux de cette chaîne ont été mis en place par d'autres partenaires du projet. Aujourd'hui, la HES-SO VS et ESR ne disposent que d'une compréhension limitée du fonctionnement de cette chaîne et ne sont pas en mesure de quantifier et de qualifier sa performance. Dans ce contexte, le projet consiste à documenter, qualifier, quantitifier, éventuellement aussi améliorer la châine de valorisation de la flexibilité GOFLEX. Les possibilités d'inégration de cette chaîne au projet en cours GBFlex sera également abordée. Les livrables seront définis lors de séances de travail ad hoc HES-SO VS, ESR et FMV.

Equipe de recherche au sein de la HES-SO: Ferrez Pierre , Gabioud Dominique , Sidqi Yousra , Roduit Pierre

Partenaires académiques: VS - Institut Energie et environnement; Roduit Pierre, VS - Institut Energie et environnement

Durée du projet: 01.10.2019 - 31.12.2020

Statut: Terminé

GOFLEX

Rôle: Requérant(e) principal(e)

Financement: EU

Description du projet :

H2020 project on demand side management.

Equipe de recherche au sein de la HES-SO: Roduit Pierre , Gabioud Dominique

Durée du projet: 01.10.2016 - 29.02.2020

Montant global du projet: 12'500'000 CHF

Statut: Terminé

SEMIAH

Rôle: Requérant(e) principal(e)

Financement: EU

Description du projet :

FP7 project on demand side management.

Equipe de recherche au sein de la HES-SO: Roduit Pierre , Gabioud Dominique

Durée du projet: 01.03.2014 - 30.04.2018

Montant global du projet: 4'000'000 CHF

Statut: Terminé

FP7-ICT-2013-11-Scalable Energy Management Infrastructure for Aggregation of Households (GA: 619560)

AGP

Rôle: Requérant(e) principal(e)

Financement: Commission européenne

Description du projet : The consortium behind the SEMIAH project aims to pursue a major technological, scientific and commercial breakthrough by developing a novel and open ICT infrastructure for the implementation of automated Demand Response (DR) in households so as to enable shifting energy consumption from high energy-consuming loads to off-peak periods with high generation of electricity from Renewable Energy Sources (RES). The project's innovative approach is based on the development of an open ICT framework that will promote a generic environment for the deployment and innovation of smart grid services in households. A DR service based on novel and cutting-edge aggregation, forecasting and scheduling techniques will be developed and validated on this infrastructure. The consortium will furthermore integrate security and privacy functions in all the elements of SEMIAH to ensure that the system cannot be compromised. Finally, the consortium will develop new business models for electricity players and residential customers to quantify costs and benefits for all players in the value chain. SEMIAH will provide benefits to residential customers, energy utilities and the society, through lower electricity bills, reduced waste of RES and higher stability of the grid; by enabling savings in CO2 emissions and fuel costs; and by reducing investments in network expansion and peak generation plants. In order to achieve project objectives and the projected impacts, a strong and determined consortium has been assembled around the technological skills and competencies needed to overcome the identified challenges. The team of 12 partners from 4 different European countries, coming from ICT (AU, CSEM, UIA and HES-SO), Energy (Fraunhofer, AEnergi, SEIC, ENALP, MIS and Develco) and Telecommunications (DEVO and NetPlus), jointly possess excellence in skills and requirements needed to drive this ambitious project to successful result.

Equipe de recherche au sein de la HES-SO: Clausen Michael , Maret Yann , Ferrez Pierre , Gabioud Dominique , Roduit Pierre , Seppey Pierre-André , Pignat Marc

Partenaires académiques: VS - Institut Systèmes industriels

Durée du projet: 01.03.2014 - 31.05.2017

Montant global du projet: 562'920 CHF

Statut: Terminé

2020

Flexibility quantification in households :

Article scientifique ArODES

a swiss case study

Yousra Sidqi, Pierre Ferrez, Dominique Gabioud, Pierre Roduit

Energy Informatics, 2020, vol. 3, no. 23, suppl. no. 1

Lien vers la publication

Résumé:

In this paper, a thorough analysis of quantification of the heating appliances’ flexibility provided by 200 households located in the Sion area (Switzerland) is presented. An extended evaluation of the available flexibility throughout the year as well as a correlation analysis between the outside temperature and flexibility is performed. The influence of pooling households in the prediction process is assessed. The impact of cutting the power to heating appliances and the incurred rebound effect are also described.

Flexibility Quantification in Households: A Swiss Case Study

Article scientifique

Sidqi Yousra, Ferrez Pierre, Gabioud Dominique, Roduit Pierre

Energy Informatics, 2020 , vol. 3

2019

Methods for personalised delivery rate computation for IV administered anesthetic propofol

Chapitre de livre ArODES

Alena Simalastar, Monia Guidi, Pierre Roduit, Thierry Buclin

Automated Reasoning for Systems Biology and Medicine (28 p.). 2019, Cham : Springer

Lien vers la publication

cloud.iO: A Decentralised IoT Architecture to Control Electrical Appliances in Households

Chapitre de livre

Roduit Pierre, Gabioud Dominique, Gillian Basso, Maître Gilbert, Ferrez Pierre

, Smart Cities, Green Technologies and Intelligent Transport Systems. 2019, Switzerland : Springer

Résumé:

Demand Response (DR) systems exist since decades in most industrialised countries. It started with phone calls to big industrial plants to reduce their consumption in time of need. Gradually, other solutions were installed by distributors to control the electricity consumption in their grid. Two well-known systems are the two-tariff system and ripple control. The second was installed to shave the consumption peak, sending telegrams on the distribution grid to cut some high consumption loads, such as heating appliances, water boilers, or white appliances. This solution is mainly open loop as the same command is sent to multiple households at the same time and only the global utility load curve is monitored. This blind switching of mass of appliances at the same time has also side effects, such as synchronising the restart of most appliances when the controlling relays are simultaneously released, provoking a rebound effect in the form of a power surge that can exceed the shaved peak.

2018

Robustness analysis of personalised delivery rate computation for IV administered anesthetic

Article scientifique ArODES

Alena Simalatsar, Monica Guidi, Pierre Roduit, Thierry Buclin

Smart Health, 2018, vol. 9-10, pp. 101-114

Lien vers la publication

Résumé:

Controlled delivery of intravenous (IV) anesthetics aims at fast and safe achievement and maintenance of a suitable depth of hypnosis (DOH), by ensuring appropriate effect site (i.e. brain) exposure to the drug. Today, such drugs are regularly injected by Target Controlled Infusion (TCI) systems, piloted by an open-loop algorithm based on Pharmacokinetic (PK) models. Yet the inaccuracy of concentration prediction of current TCI can reach up to 100%. The situation could be improved by closing the loop with sensors providing regular real measurements of the anesthetic concentration in body fluids. In this paper we present a closed-loop algorithm based on the classic open-loop algorithm combined with a Kalman filter. The latter estimates plasma drug concentration based on PK model and sensor measurements. The estimates are then used in the open-loop algorithm. To validate our approach measurements are generated by means of modulating the population-based plasma concentration values with the maximum inter- and intrapatient variability of the statistical Eleveld׳s (Eleveld et al., 2014) PK model. This allows us to stress the system to a maximum level prior to testing it on patients. We also perform robustness analysis of this algorithm by accounting for realistic measurement periods and delays.

2024

NILM-Based solutions for the automation of energy services in residential buildings

Conférence ArODES

Pierre Ferrez, Dominique Gabioud, Pierre Roduit

Proceedings of the 13th International Conference on Smart Cities and Green ICT Systems - SMARTGREENS, 2-4 May 2024, Angers, France

Lien vers la conférence

Résumé:

In Switzerland, about 40 % (90 TWh) of the energy needs are due to buildings and about 70 % of these needs come from heating. Therefore, improving the efficiency of buildings has a high potential for energy savings. This paper presents innovative solutions for the automation of energy services in residential buildings, based solely on the disaggregation of the centralized electricity consumption measurement of the household. The developed method was successfully used on electricity consumption data recorded in 14 households over a year to (1) extract the heat pump consumption from the aggregated consumption, (2) split the heat pump consumption into space heating and domestic hot water consumption and (3) split the remaining consumption into four categories: base load, low power, medium power, and high power. With a daily average error on the prediction of the heat pump consumption below 3.5 % and daily average errors on the prediction of the number of cycles and the operating time of the heat pump both around 1 %, the described method can be used for the development of energy service prototypes allowing to better understand and optimize the energy functioning of residential buildings with potential savings for the residents.

2022

Development of a novel cavitation monitoring system for hydro turbines based on machine learning algorithms

Conférence ArODES

Ali Amini, Olivier Pacot, Dominique Voide, Vlad Hasmatuchi, Pierre Roduit, Cécile Münch-Alligné

IOP Conference Series: Earth and Environmental Science ; Proceedings of the 31st IAHR Symposium on Hydraulic Machinery and Systems, 26 June-1st July 2022, Trondheim, Norway

Lien vers la conférence

Résumé:

Operating hydro turbines in off-design conditions increases the risk of cavitation occurrence, which in turn, leads to numerous problems such as performance degradations, structural vibrations, and most importantly, mechanical damage due to erosion. It is therefore crucial to develop a monitoring system that detects the occurrence and severity of cavitation in real time. For this purpose, a cavitation detection methodology has been developed that is based on the analysis of acoustic emissions of a turbine with machine learning algorithms. In this method, a conventional microphone is used to record the airborne noise emitted from a turbine under different working conditions, and then, a supervised learning algorithm is trained to classify the recorded noise signals into cavitating and non-cavitating categories. The detection system was developed based on laboratory tests and was validated in Ernen hydropower plant located in Canton of Wallis in southeast of Switzerland. This power plant consists of two identical double-flux Francis turbines each having a maximum power of 16 MW and a net head of 270 mWC. The preliminary results obtained from a two-day experimental campaign in the Ernen powerplant are very promising in terms of cavitation detection with a classification accuracy of more than 90 %. The system could be implemented either for real-time monitoring of cavitation occurrence allowing the operators to avoid such a condition or as a post processing tool to evaluate the number of hours a turbine has worked under severe conditions. Work is still ongoing to deploy more complex learning algorithms for this task to minimize expert intervention and/or interpretation during the setup process.

2021

GOFLEX: Towards a New Integrated Solution for a Cost- Effective Use of Demand Response in Distribution Grids

Conférence

Sidqi Yousra, Ferrez Pierre, Gabioud Dominique, Roduit Pierre

CIRED 2020 Berlin Workshop, 23.09.2021 - 04.06.2020, 05/06/2020

2020

GOFLEX :

Conférence ArODES

towards a new integrated solution for a cost-effective use of demand response in distribution grids

Yousra Sidqi, Pierre Ferrez, Dominique Gabioud, Pierre Roduit

Proceedings of CIRED 2020 Berlin workshop, 22-23 September 2020, Berlin, Germany

Lien vers la conférence

Résumé:

In the past decade, the planning of urban networks, in particular power grids, went through a paradigm shift. The increasing share of intermittent renewable energy generation and the required load capacity led to a major focus on demand side management (DSM) to deal with the continual evolution of the energy market. Multiple research programs were established to study and quantify the benefits of large-scale implementation of DSM solutions. In this paper, we investigate a new solution for demand response in the housing sector. This research is conducted within the framework of the GOFLEX project, whose main objective is to develop and demonstrate an integrated solution which will significantly contribute in the cost-effective use of demand response in distribution grids and increase the available flexibility of loads/generation included in demand response schemes. This paper briefly introduces the GOFLEX integrated solution. We present the results of prosumers flexibility quantification over a period of one year. We also investigate the influence of outdoor temperature, consumption period (weekdays, weekends, holiday seasons) and consumption time during the day (morning and evening peaks). Finally, we explore control solutions to maximize flexibility use.

2018

IoT architecture for decentralised heating control in households

Conférence ArODES

Gillian Basso, Dominique Gabioud, Pierre Roduit

Proceedings of the 7th International Conference on Smart Cities and Green ICT Systems

Lien vers la conférence

Résumé:

Over the last two decades, electrical energy generation has become more sustainable (photovoltaic, wind energy, etc.), but also more distributed, less predictable, and less controllable. Besides storage and flexible production, Demand Response (DR) offers great opportunities to help stabilizing the electrical grid. This paper presents how the flexibility of space and domestic hot water heating in existing residential buildings can be controlled for grid services. It focuses on the Internet of Things (IoT) framework including both hardware and software to connect existing buildings to a central Virtual Power Plant (VPP) intelligence. It also presents field experiments that were performed during the European FP7 SEMIAH project.

2016

Local algorithm for the open loop control of thermostatically controlled loads

Conférence ArODES

Gilbert Maître, Dominique Gabioud, Pierre Roduit

Proceedings of 2016 IEEE PES Innovative Smart Grid Technologies Conference Europe (ISGT-Europe), 9-12 October 2016, Ljubljana, Slovenia

Lien vers la conférence

Résumé:

Recently, much research in demand response has been devoted to the global control of a population of local thermostatically controlled loads (TCLs), especially by modifying the temperature setpoints of programmable communicating thermostats (PCTs). It is now well known that shifting simultaneously and instantaneously the thermostat temperature setpoints of a homogeneous population of TCLs induces oscillations. To avoid this, closed loop control solutions have been proposed, which however necessitate real-time communication from local loads to central controller. Very recently, open loop solutions requiring only particular capabilities of the PCTs have been put forward. This paper shows how exactly simple hysteresis band shift introduces synchronization in a population of homogeneous TCLs and proposes a modification of the simple hysteresis band shift to avoid oscillations by circumventing thermostat synchronization. The algorithm's success is proved theoretically for a homogeneous TCL set. The improvement brought by the algorithm in a moderately heterogeneous case is shown by simulation. The algorithm is also compared to another recently proposed open loop solution.

2015

Contact-less palm/finger vein biometrics

Conférence ArODES

Alexandre Sierro, Pierre Ferrez, Pierre Roduit

Proceedings of 2015 International Conference of the Biometrics Special Interest Group (BIOSIG). 9-11 September 2015, Darmstadt, Germany

Lien vers la conférence

Résumé:

Finger and palm vein recognition, based on near infra-red images of the vein pattern of the finger or the palm, are promising biometric authentication methods. The main advantage of vein recognition over fingerprints is its touch-less nature, making it more robust to spoofing and more comfortable to the user. To this point, vein recognition has mainly been developed by private companies rather than by academic institutions and there are only a relatively limited number of scientific publications on the topic. This paper presents two palm vein and one finger vein imaging prototypes developed in our institution. An image database has also been acquired with each of these three prototypes.

Contact-Less Palm/Finger Vein Biometrics

Conférence

Alexandre Sierro, Ferrez Pierre, Roduit Pierre

2015 International Conference of the Biometrics Special Interest Group (BIOSIG), 10.09.2015 - 11.09.2015, Darmstadt, Germany

An Extensible Simulator for Dynamic Control of Residential Area: Case Study on Heating Control

Conférence

GIllian Basso, Ferrez Pierre, Gabioud Dominique, Roduit Pierre

2015 Euromicro Conference on Digital System Design (DSD), 26.08.2015 - 28.08.2015, Madeira, Portugal

Distributed grid storage by ordinary house heating variations :

Conférence ArODES

a swiss case study

Gilbert Maître, Gillian Basso, Claudio Steiner, Dominique Gabioud, Pierre Roduit

Proceedings of 2015 Euromicro Conference on Digital System Design, 26-28 August 2015, Madeira, Portugal

Lien vers la conférence

Résumé:

In Switzerland, the daily and annual profiles of electrical energy supply are deeply reshaped by the increasing importance of non-flexible renewable sources, i.e. solar and wind, slowly replacing nuclear power plants. Load shifting can be a special help, adapting consumption to this new production, allowing to develop and implement new storage solutions. In this paper, we present a solution that uses existing heating facilities of residential buildings to store electrical energy as thermal energy in buildings. Charging is performed by the margin power of heating systems, i.e. the difference between installed power and the heating power that is currently necessary. It is a storage solution limited to times when heating is necessary with charging/discharging powers depending on the weather conditions. However, it has the crucial advantage to be distributed over the grid and therefore adapts especially well to expanding non-flexible renewable distributed energy sources. Based on the Swiss Federal Statistical Office (FSO) buildings and dwellings statistics, this paper shows that in Switzerland, this solution could deliver a storage capacity above 6 GWh (for 1° change in room temperature) with peak charging/discharging powers at balance (i.e. when they are equal) of about 2.3 GW. The storage potential is hence in the same order of magnitude as large pump-storage hydroelectric power stations like Nant de Drance.

An extensible simulator for dynamic control of residential area :

Conférence ArODES

case study on heating control

Gillian Basso, Pierre Ferrez, Dominique Gabioud, Pierre Roduit

Proceedings of 2015 Euromicro Conference on Digital System Design, 26-28 August 2015, Madeira, Portugal

Lien vers la conférence

Résumé:

The energy world is quite complex: energy is moved, stored and transformed using a heterogeneous and vastly distributed infrastructure. The move towards a cleaner and more sustainable energy system, which is favoured by people, has major implications on the energy system. Large controllable plants will be replaced by small distributed units featuring most of the time a stochastic behaviour. To accommodate these changes, the energy system as a whole must become more flexible. Many processes like building heating or cooling feature some level of flexibility. This potential flexibility is mostly unused today. To make the energy system more flexible, some of its elements must be orchestrated so they interact harmoniously. In this context, simulation is an appropriate approach to test and evaluate distributed control strategies. Indeed, it avoids the deployment of real, costly infrastructures and complaints of users. This paper presents a simulator based on statistical information simulating behaviours of consumers, building properties, and implications of external data in energy management.

Load shifting for tertiary control power provision

Conférence

Hanmin Cai, Andreas Hutter, Elisa Olivero, Roduit Pierre, Ferrez Pierre

2015 IEEE 5th International Conference on Power Engineering, Energy and Electrical Drives (POWERENG), 11.05.2015 - 13.05.1902, Riga, Latvia

2014

Test set validation for home electrical signal disaggregation

Conférence ArODES

Antonio Jara, Luc Dufour, Dominique Genoud, Gianluca Rizzo, Pierre Roduit, Jean-Jacques Bezian, Bruno Ladevie

Proceedings of the 8th International Conference on Innovative Mobile and Internet Services in Ubiquitous Computing 2014

Lien vers la conférence

Résumé:

In order to enable demand response schemes for residential and industrial users, it is crucial to be able to predict and monitor each component of the total power consumption of a household or of an industrial site over time. We used the cross-validation method which is a model validation technique for assessing how the results of a statistical analysis will generalize to an independent data set. It is mainly used in settings where the goal is prediction, and one wants to estimate how accurately a predictive model will perform in practice. We exploit Non-Intrusive Load Monitoring (NILM) techniques in order to provide behavior patterns of the variables identified. This work presents a review Non-Intrusive Load Monitoring (NILM) techniques and describe the results of recognition patterns used for the identification of electrical devices. The proposed method has been validated on an experimental setting and using direct measurements of appliances consumption, proving that it allows achieving a high level of accuracy in load disaggregation.

Non-intrusive appliance load curve disaggregation for service development

Conférence ArODES

Pierre Ferrez, Pierre Roduit

Proceeding of 2014 IEEE International Energy Conference (ENERGYCON), 13-16 May 2014, Cavtat, Croatia

Lien vers la conférence

Résumé:

The popularity of reducing domestic electricity consumption is growing following the decision of several European governments to quit nuclear power in the near future. However, finding out which equipment should be replaced and more importantly which behavior should be modified to reach this goal is not a simple task, since helpful tools are not easy to find or implement. The disaggregation of the global electricity consumption could be achieved in the framework of concepts like the Internet of Things where the monitoring of each appliance is made possible using embedded power sensors. However, the implementation of such solutions in the near future will be very difficult due to the costs generated by the modification of existing appliances. Another more elegant solution to provide people with useful information about their electricity consumption consists in a single recording unit measuring the entire consumption coupled with a system able to disaggregate the appliance load curve. This is better known as non-intrusive appliance load monitoring (NIALM). The aim of this study is to investigate the feasibility of a load curve disaggregation based feedback system for consumer service development. For that purpose, a low-frequency recording unit was developed to record the global electricity consumption of fifty Swiss households. The recorded data, as well as simulated data, have been used to develop and validate a simple appliance detection technique with low computational requirements as this is a key issue for a potential future use in real-time remote feedback systems. This paper shows that the developed disaggregation technique, although simple, provides satisfactorily detection performances and could be used to provide consumers with useful information about their electricity consumption.

Non-intrusive appliance load curve disaggregation for service development

Conférence

Ferrez Pierre, Roduit Pierre

2014 IEEE International Energy Conference (ENERGYCON), 13.05.2014 - 16.05.2014, Dubrovnik, Croatia

2013

Domestic electricity consumption data for research and service development

Conférence ArODES

Pierre Ferrez, Philippe Renevey, Andreas Hutter, Pierre Roduit

Proceedings of CISBAT 2013 - Cleantech for Smart Cities Buildings - From Nano to Urban Scale, 4-6 September 2013, Lausanne, Switzerland

Lien vers la conférence

Résumé:

During the last few decades, citizens around western countries became more and more sensible to energy saving. However, while home electricity consumption is a source of concern, the means to reduce this consumption are not easy to _nd and implement for private individuals. Di_erent studies show that displaying the home consumption could lead to a reduction of electricity use. However, the global consumption doesn't provide the consumer with su_cient information about what counts for the main part of their electricity invoice. Systems able to display the energy used by the main appliances would greatly help the consumer to _nd out which equipment should be replaced and/or which behavior should be modi_ed. Implementing such systems requires the disaggregation of the consumption of the main appliances. One solution consists in measuring the global electricity consumption and extracting the most important information from the general load curve using signal processing methods and detection algorithms. The HES-SO Valais-Wallis (University of Applied Sciences Western Switzerland) and the CSEM (Swiss Center for Electronics and Microtechnology) are currently working in this direction. To develop recognition algorithms from an aggregated load curve, an acquisition system able to measure the three phases of a standard household has been built. This system has been deployed in seven households and has been acquiring data sampled at 1Hz for over two years for the _rst deployment site. In two households Ecowizz [1] plugs are used to acquire disaggregated data of the main appliances in parallel to the central measure. In parallel the HES-SO Valais-Wallis is deploying the system in _fty households for one month. The collected data allow a better understanding of the main contributors to the load curve as well as the useful characteristics to recognize them. To _rst tackle the complexity of the aggregated load curve, a simulator of the main contributors (washing machine, dishwasher, tumble dryer, oven, stove, etc.) was also created, thus allowing to initially test the disaggregation algorithms with an a priori knowledge of the contributors. Both the database of real signals and the simulator are new tools that will allow for new research and development of algorithms for the analysis of aggregated load curves.

Réalisations

PEOPLE@HES-SO
Annuaire et Répertoire des compétences

Roduit Pierre

Professeur-e HES Ordinaire, Responsable de l'institut Energie et environnement

Compétences principales

Energy

Demand Side Management

Non Intrusive Load Monitoring

Data Science

Machine Learning

Professeur-e HES Ordinaire, Responsable de l'institut Energie et environnement

PEOPLE@HES-SO Annuaire et Répertoire des compétences

Roduit Pierre

Professeur-e HES Ordinaire, Responsable de l'institut Energie et environnement

Compétences principales

Energy

Demand Side Management

Non Intrusive Load Monitoring

Data Science

Machine Learning

Professeur-e HES Ordinaire, Responsable de l'institut Energie et environnement

PEOPLE@HES-SO
Annuaire et Répertoire des compétences