Download as pdf or txt
Download as pdf or txt
You are on page 1of 3

MORED: a Moroccan Buildings’ Electricity

Consumption Dataset

M. Aymane Ahajjam, Daniel B. Licea, Mounir Ghogho, Abdellatif Kobbane


TICLab, International University of Rabat - Mohammed V University, Rabat
{aymane.aha j jam, daniel.bonilla −
licea, mounir.ghogho}@uir.ac.ma, abdellati f .kobbane@um5.ac.ma

Abstract
We propose the Moroccan Buildings’ Electricity Consumption Dataset, a first of
its kind, coined as MORED. This new dataset comprises electricity consumption
data and their metadata from various Moroccan premises monitored for extended
durations of time.

1. Introduction
Public datasets are published to help advance research fields by overstepping the laborious tasks of data
acquisition and data management, and providing researchers with valuable data. The lack of energy
consumption datasets has long hindered the field’s progression. The last decade has seen a collective
effort towards alleviating this issue. Since the publication of REDD [1] in 2011, several datasets, mainly
intended for energy disaggregation purposes, have been published every year [2–6]. Yet, there is a lack

emonPi emonPi

INDIVIDUAL LOAD INDIVIDUAL LOAD WHOLE-PREMISES


SIGNATURES GROUND-TRUTH CONSUMPTION

DATA SERVER

Fig. 1. MORED’s acquisition architecture of WP and IL electricity consumption.


of such datasets from under-represented developing countries. This paper introduces MORED and the
methodology used for its acquisition (see Figure 1). The rest of this paper is organized as follows:
Section 2 sheds light on the data acquisition campaign. A summary of MORED is presented in Section
3. Finally, Section 4 gives a conclusion of the paper.

2. Data Acquisition Campaign


Since spring 2019, a data acquisition campaign was conducted to collect data reflecting the electricity
consumption of different urban premises in three Moroccan cities: Rabat, Sale, and Tetuán. We note that
the consent and anonymity of all participating residents was respected throughout the whole process.

3. Dataset Summary
MORED is available as an open dataset at https://moredataset.github.io/MORED. Al-
though not limited to these fields, it is intended for energy-related research fields such as load disag-
gregation and energy forecasting.
The main features of the MORED dataset are:
• WP electricity consumption: they were acquired from a total of 19 households of different
socio-economic statuses. They comprise V and P extracted at 1/5[S/s] for affluent neighborhood
premises and at 1/10[S/s] for disadvantaged neighborhood premises.
• Labeled IL ground-truth electricity consumption: they were acquired from 10 residential premises
comprising V and P extracted at 1/5[S/s]. Events corresponding to IL ground-truth data only
describe on/off operational states of the monitored loads and are all reported in a CSV file.
• IL signature electricity consumption: IL signature data were acquired from 37 classes of loads (a
total of 52 loads) comprising i and v sampled at 50k[S/s] (which is a higher rate than those of most
datasets), and I, V , P, and Q extracted at 4[S/s].
• Metadata: They offer detailed information for all three sets of data following the NILM Metadata
schema [7]. They are reported in YAML text files.
Figure 2 illustrates the organization of the dataset directory. Data are divided into three main subdirecto-
ries, each corresponding to a specific type of data (i,e., WP and IL ground-truth (WPILGT), WP, and IL
signature (ILS)).
MORED

WPILGT ILS WP
Premises_1 Blender Premises_1.csv

Mains.csv Premises_2.csv
Refrigerator
Refrigerator.csv Premises_...csv
...
...
metadata
Events.csv metadata

Premises_.. Events.csv

metadata

Fig. 2. Tree describing the content of the MORED directory.

4. Conclusion
In this paper, we presented MORED: the first public dataset of Moroccan buildings’ electricity consump-
tion. The aim for acquiring such a dataset is to make a contribution to the field of energy management
and smart grids, and promote the development of techniques that can suit the energy needs of under-
represented communities.
References
1. J. Z. Kolter and M. J. Johnson, “REDD: A public data set for energy disaggregation research,” in Proceed-
ings of the SustKDD workshop on Data Mining Applications in Sustainability, 2011, pp. 59–62.
2. K. Anderson, A. Ocneanu, D. Benitez, D. Carlson, A. Rowe, and M. Berges, “BLUED: a fully labeled
public dataset for Event-Based Non-Intrusive load monitoring research,” in Proceedings of the 2nd KDD
Workshop on Data Mining Applications in Sustainability (SustKDD), Beijing, China, August 2012, pp. 1–5.
3. S. Makonin, B. Ellert, I. V. Bajic, and F. Popowich, “Electricity, water, and natural gas consumption of a
residential house in canada from 2012 to 2014,” Scientific Data, vol. 3, no. 160037, pp. 1–12, 2016.
4. L. De Baets, C. Develder, T. Dhaene, D. Deschrijver, J. Gao, and M. Berges, “Handling imbalance in an
extended PLAID,” in 2017 Sustainable Internet and ICT for Sustainability (SustainIT). IEEE, 2017, pp.
1–5. [Online]. Available: https://ieeexplore.ieee.org/document/8379795
5. S. Makonin, Z. Wang, and C. Tumpach, “RAE: The rainforest automation energy dataset for
smart grid meter data analysis,” Data, vol. 3, no. 1, p. 8, Feb 2018. [Online]. Available:
http://dx.doi.org/10.3390/data3010008
6. F. Jazizadeh, M. Afzalan, B. Becerik-Gerber, and L. Soibelman, “Embed: A dataset for energy monitoring
through building electricity disaggregation,” in Proceedings of the Ninth International Conference on
Future Energy Systems, ser. e-Energy ’18. New York, NY, USA: Association for Computing Machinery,
2018, p. 230–235. [Online]. Available: https://doi.org/10.1145/3208903.3208939
7. J. Kelly and W. Knottenbelt, “Metadata for energy disaggregation,” in 2014 IEEE 38th International Com-
puter Software and Applications Conference Workshops, 2014, pp. 578–583.

You might also like