The best way to decide whether the problem has been solved is clearly to first unravel what we mean by the term solved. The two most important factors in my opinion have got to be the scenario and and the accuracy, which I've picked apart below.
Scenario
The most compelling scenarios are the ones in which the software does as much of the hard work as possible, allowing the hardware to remain simple and inexpensive. Furthermore, the installation process should also be free from any dedicated training phase in which the temporary control of appliances is required or additional monitoring equipment is deployed. This style of approach clearly affords the maximum scalability, which is essential if disaggregated data is ever to reach the masses. While approaches are still being proposed that don't address this scenario, there's still quite a way to go yet.
Accuracy
It's very easy to get carried away when reading papers how one approach has achieved X% accuracy, while another achieved Y% accuracy. However, I'm fairly sure that aiming for 100% disaggregation accuracy is not only unrealistic, but also unnecessary too. I think it's far more important that energy disaggregation is used as a platform from which personalised, actionable, energy-saving suggestions can be derived. Therefore, disaggregation only needs to be accurate enough to convincingly determine the bigger picture, and any effort beyond this is likely to be a waste of time.
On a final note, even if there exists an approach that's managed to address the above scenario to a suitable level of accuracy, this is still only only piece of the disaggregation puzzle. The diversity of electricity consumption means that different countries and buildings require different approaches, and there will always be a niche sub-area of disaggregation just waiting to be found.
Great post. This is a question that has depressed me in the past (and, in fact, is slightly troubling me at the moment too!)
ReplyDeleteAs you've said in the past, it's also the case that even if disaggregation were a completely "solved" problem within the closed walls of industry, us academics still have a valuable role to play in terms of inventing good disaggregation systems in the public domain.
And there's definitely plenty of work to be done "around" disaggregation. Just yesterday I was talking to someone from DECC who was talking about the need for a common, public database of appliance models, for example.
And, finally, if I look around at other PhD students at Imperial then quite a few appear to be working on nominally "solved" problems. e.g. quite a few are working on some aspect of face recognition. These students are making very valuable contributions to a subject which is so "solved" that it's a feature on mobile phones and cameras!
One final thought: one definition of "solved" for disaggregation would be along the lines of "if I weren't working on disaggregation for a PhD, would I be able to disaggregate my own home's meter data?" to which the answer appears to be "no" for UK residents (unless you trick PlotWatt's website by giving it a US address!).
also, of course, disaggregation is a fun problem on which to learn so interesting techniques like HMMs etc. which will hipefully be useful in future jobs / research problems.
ReplyDelete