Vincent Debusschere

Nonintrusive Load Monitoring: A Temporal Multilabel Classification Approach

The article tackles the issues related to the identification of electrical appliances inside residential buildings. Each appliance can be identified from the aggregate power readings at the meter panel. The possibility of applying a temporal multilabel classification approach in the domain of nonintrusive load monitoring is explored (nonevent-based method). A novel set of metafeatures is proposed. The method is tested on sampling rates based on the capabilities of current smart meters. The proposed approach is validated over a dataset of energy readings at residences for a period of a year for 100 houses containing different sets of appliances (water heater, washing machines, etc.). This method is applicable for the demand side management of households in the current limitation of smart meters; from the inhabitants or from the grid operators point of view.

A new approach to model energy consumption of servers in data centers

Electricity consumption of data centers increases continuously. Beside of the IT industry which tries to reduce this consumption by improving efficiency of components in data centers, there are research solutions based on an optimized energy management of data centers by acting on the IT load placement, then on cooling, start-up and shut down. In this context, this paper focus on energetic modeling of servers in data centers. In the state of art, the IT load is usually presented as a whole unit by means of the percentage CPU, while in this work, the percentage CPU is separated in two parts. The first one is the percentage CPU due to server self applications (for example a virtual machine manager), while the second part is due to services turning on the server. This classification led to a new linear model which shows that electricity consumption of data centers can be modeled as accumulated layers depending on what kind of software is running on the servers. The model is developed and then validated with experimental measurements on actual server conduct with the help of industrial partners. This modeling presents the first step of further works aim to optimize the energy consumption of data centers by knowing the IT load that is held on its servers.

Hourly server workload forecasting up to 168 hours ahead using Seasonal ARIMA model

Data center workload prediction is important to take decisions in resources management system. Seasonal ARIMA model provide a good server workload methodology for the server workload forecasting. A large set of our experiments confirm that it has high performance, scalability and reliability and will bee integrated in our system. This paper presents a general expression in development of our forecast model in the project EnergeTic-FUI, France.

Appliance usage prediction using a time series based classification approach

Energy management for residential homes and offices require the prediction of the usage(s) or service request(s) of different appliances present in the house. The hardware requirement is more simplified and practical if the task is only based on energy consumption data and no other sensors are used. The proposed model tries to formalize such an approach using a time-series based multi-label classifier which takes into account correlation between different appliances among other factors. In this work, prediction results are shown for 1-hour in the future but this approach can be extended to predict more hours in the future as per the requirement(with restrictions). The learned models and decision tree showing the important factors in the input information is also discussed.

Co-Optimization of Storage System Sizing and Control Strategy for Intelligent Photovoltaic Power Plants Market Integration

Energy storage systems (ESS) when integrated with large-scale photovoltaic (PV) plants, constituting a so-called Intelligent PV (IPV) power plant, are able to contribute to improve the economic viability of these power plants and to help them participate in the electricity markets as other traditional generators. In this paper, the sizing and control strategy co-optimization for an existing IPV power plant is proposed and implemented. A global linear programming (LP) optimization algorithm is developed, where the optimal components sizing is computed directly in the same optimization as the operating management of the storage system. In the IPV power plant design stage, the LP optimization is applied to obtain the optimal energy storage sizing parameters (capacity and power rate). In the operation stage, the same LP algorithm optimizes the control strategy to participate to electricity markets. This participation is based on the online model predictive control (MPC) to counteract PV forecast errors by participating in intraday markets. The proposed approach (optimal ESS sizing and online MPC) increases the daily economic benefits around 20%.

A load identification method for residential building applications

In this paper, the topic of electric load identification in household applications is addressed. The identification of load powers and of duty cycles is performed in a nonintrusive way from the signals flowing throughout the meter panel of electricity consumption of the building. The identification of loads is based on the detection of the on-off transitions in the active power, from which the power level, the start time, the end time, the duty cycle, and the power consumption can all be computed.

Residential appliance identification and future usage prediction from smart meter

Energy management for residential homes and/or offices requires both identification and prediction of the future usages or service requests of different appliances present in the buildings. The aim of this work is to identify residential appliances from aggregate reading at the smart meter and to predict their states in order to minimize their energy consumption. For this purpose, our work is divided in two distinct modules: Appliance identification and future usage prediction. Both identification and prediction are based on multi-label learners which takes inter-appliance co-relation into account. The first part of the paper concerns the identification of electrical appliance usages from the smart meter monitoring. The main objective is to be able to identify individual loads from the aggregate power consumption in a non-intrusive manner. In this work, high energy consuming appliances are identified at 1-hour sampling rate using novel set of meta-features for this domain. The second part of the paper concerns future usage prediction. A comparison of algorithms for future appliance usage prediction using identification and direct consumption reading is presented. This work is based on a real residential dataset, called IRISE: 100 houses monitored every 10 minutes to one hour during one year (including weather informations).

Analysis and comparison of battery energy storage technologies for grid applications

Battery Energy Storage Systems (BESSs) could contribute to the generation/consumption balance of the grid and could provide advanced functionalities at different grid levels (generation, T&D, end-user and RES integration). In this paper an analysis and comparison of Battery Energy Storage (BES) technologies for grid applications is carried out. The comparison is focused on the most installed technologies in the recent experimental BESS installations. Furthermore, the paper presents a new methodology aimed at selecting the most suitable BES technology for a specific grid application. This methodology defines a priority level for each technical and economical characteristic of the BES technologies. Finally, the proposed methodology is applied for a specific grid application confirming its contribution in the selection of the best-suited technology.

A comparative study of low sampling non intrusive load dis-aggregation

Non-intrusive load monitoring (NILM) deals with the identification and subsequent energy estimation of the individual appliances from the smart meter data. The state of the art applications typically runs once per day and reports the detected appliances. In this work, data driven models are implemented for two different sampling rates (10 seconds and 15 minutes). The models are trained for 20 houses in the Netherlands and tested for a period of 4-weeks. The results indicate that the disaggregation methods is applicable for both sampling cases but with different use-case.

Assessment of the impact of frequency containment control and synthetic inertia on intermittent energies generators integration

The increasing power generation out of intermittent renewable energy sources will result in a reduction of the grid stability if no compensatory actions are taken. This issue may lead to future obligations for energy providers. This paper studies the implication of the future obligations for generators in Europe according to the recommendations of ENTSO-E, in particular the obligation for some generators to have a synthetic (or virtual) inertia and a frequency sensitive control. These obligations will be described in details in the paper, in particular their effect on the grid management and stability. The impact of this new actions on the energy production will be discussed. The continental European grid frequency is used as an example.