NILM 2015 @ London discussion

Jack Kelly and I are thinking about organising another NILM meet up in London this summer, and would love to get your thoughts on what you would find most useful. Jack has started an Energy Disaggregation Discussion Group which seems like a great place to throw some ideas around. I'd encourage everyone to head over to the forum and add your voice to the discussion! And don't forget to subscribe to the group so you receive updates!

DECC Workshop: Specifying and Costing Monitoring Equipment for a Longitudinal Energy Study

Yesterday I attended a DECC workshop aiming to specify and estimate the costs of monitoring equipment for a longitudinal energy study. The scale of the study would be to use questionnaires and monitoring equipment to study energy use in 10,000s of homes. However, only £500 per household could be spent on hardware at such scale. It was concluded that this budget would not go very far beyond aggregate gas, electricity and water monitoring equipment.

In contrast to this, the LUKES project proposes aggregate monitoring of 10,000s of homes, while extensively monitoring up to 400 homes for up to 4 years. Although not the primary aim of the study, such a data set would have considerable impact for the energy disaggregation community. I was keen to point out that such uses have arisen due to the Household Energy Study, and it is important to take this data set as a case study when designing new surveys.

However, it is also important that lessons are learned from HES, such that the same mistakes are not repeated. In particular, I’d hope that a new data set would:

• Collect both aggregate-level and circuit-level data as well as appliance level data
• Specify and maintain each household’s metering hierarchy and appliance names using a consistent metadata schema, such as the NILM Metadata project
• Collect aggregate data at a higher resolution than 2 minute energy readings. Ideally, I believe 1 second power data would be best trade-off between cost and frequency

Joining the data science team at British Gas Connected Homes

I joined the data science team at British Gas Connected Homes at the start of this year, who focus on extracting meaningful insight from smart meter data to help their customers better understand their energy consumption. The plan is to split my time roughly 50/50 between my current research fellowship at the University of Southampton and my new role with British Gas. The good news for you is that this means I'll continue to maintain this blog for at least the next year. This partnership with British Gas is particularly natural given my PhD research in energy disaggregation, and I am looking forward to the new challenges this role will bring. Below is a photo of one of Connected Homes' London offices, which is probably not what you might expect from the UK's largest gas and electricity supplier!

JAIR paper published: A Hidden Markov Model-Based Acoustic Cicada Detector for Crowdsourced Smartphone Biodiversity Monitoring

We recently had a paper published in the Journal for Artificial Intelligence Research based on our work searching for the New Forest Cicada with the aid of a smartphone app.

The full abstract is:

In recent years, the field of computational sustainability has striven to apply artificial intelligence techniques to solve ecological and environmental problems. In ecology, a key issue for the safeguarding of our planet is the monitoring of biodiversity. Automated acoustic recognition of species aims to provide a cost-effective method for biodiversity monitoring. This is particularly appealing for detecting endangered animals with a distinctive call, such as the New Forest cicada. To this end, we pursue a crowdsourcing approach, whereby the millions of visitors to the New Forest, where this insect was historically found, will help to monitor its presence by means of a smartphone app that can detect its mating call. Existing research in the field of acoustic insect detection has typically focused upon the classification of recordings collected from fixed field microphones. Such approaches segment a lengthy audio recording into individual segments of insect activity, which are independently classified using cepstral coefficients extracted from the recording as features. This paper reports on a contrasting approach, whereby we use crowdsourcing to collect recordings via a smartphone app, and present an immediate feedback to the users as to whether an insect has been found. Our classification approach does not remove silent parts of the recording via segmentation, but instead uses the temporal patterns throughout each recording to classify the insects present. We show that our approach can successfully discriminate between the call of the New Forest cicada and similar insects found in the New Forest, and is robust to common types of environment noise. A large scale trial deployment of our smartphone app collected over 6000 reports of insect activity from over 1000 users. Despite the cicada not having been rediscovered in the New Forest, the effectiveness of this approach was confirmed for both the detection algorithm, which successfully identified the same cicada through the app in countries where the same species is still present, and of the crowdsourcing methodology, which collected a vast number of recordings and involved thousands of contributors.

and the full reference is:

D. Zilli, O. Parson, G. V. Merrett and A. Rogers (2014) "A Hidden Markov Model-Based Acoustic Cicada Detector for Crowdsourced Smartphone Biodiversity Monitoring", Volume 51, pages 805-827

infer-hmm: An Infer.NET implementation of the hidden Markov model

The hidden Markov model is a popular statistical tool for modelling sequential data, and as such has received much attention from the field of non-intrusive load monitoring. However, the community has lacked general tools to perform scalable approximate Bayesian inference in HMMs, which has limited the speed of research in this field. For this reason, today I'm open sourcing infer-hmm: An Infer.NET implementation of the hidden Markov model. The aim of the project is to make it easy to run approximate Bayesian inference over both the model parameters and states of a hidden Markov model. The model is built using the Infer.NET framework for Bayesian inference in graphical models, and as such can make use of industry strength algorithms for running approximate inference. Special thanks go to Microsoft Research for adding support for chain models, and to Matteo Venanzi for his expertise in increasing the efficiency of the model.

NILMTK Survey

We've seen some really encouraging adoption of NILMTK (our open-source toolkit for non-intrusive load monitoring) since we started work on it a year ago. However, it's quite hard to keep track of how people our using the toolkit, what features they'd like to see, and what direction the toolkit should be heading in. For this reason, we've created a NILMTK Survey, which will hopefully solve these problems. Please fill out the survey if you have any interest in energy disaggregation research, and let us know what's important to you. Thanks!

Energy disaggregation bloggers

There's a great amount of blogging going on in the NILM research field, so this post aims to collect all these resources together in a single hub. As always, please let me know if I've missed anyone!

Nipun Batra

Nipun is a final year student at IIIT Delhi, who writes about energy disaggregation research, as well as some more general programming solutions he has come across. Nipun also kicked off the NILMTK project.

Mario Bergés

Mario is an assistant professor at CMU, who mostly writes about upcoming workshops and conferences which are highly relevant to NILM. Mario is an incredibly busy person, which somewhat explains why he describes his own blog as having a tendency to remain silent.

Kyle Bradbury

Kyle is a postdoctoral energy fellow at Duke University, who writes about a broad spectrum of energy issues beyond that of just NILM. Kyle is involved with a number of interdisciplinary energy projects at Duke, which draw from disciplines such as engineering, economics, policy, and behavioural science to solve energy problems.

Suman Giri

Suman is one of Mario's students at CMU, who writes about recent developments at their Intelligent Infrastructure Research Laboratory. Suman has done some great work around high-frequency NILM, and has released code for both data collection and disaggregation.

Jack Kelly

Jack is a final year student at Imperial College London, who frequently writes on his energy disaggregation blog. He's very active in the community, and has released a UK data set as well as open sourcing his metadata project. Jack is also a collaborator (and chief architect) on the NILMTK project.

Stephen Makonin

Stephen is a postdoctoral research fellow at Simon Fraser University. Stephen has completed a large amount work in the domain of smart meter data analytics, as well as releasing the AMPds data set.