Saving energy with ICT
This website has been developed as part of a European project called smartspaces. The project aims to save energy in public buildings using ICT. It is a collaboration between eleven pilot sites in eleven cities across Europe. The Leicester pilot site is a partnership between Leicester City Council and De Montfort University and this website is part of our solution.
The website provides a simple, user-friendly view of energy performance across the smartspaces buildings. Performance is visualised as a simple scale of smiley or not so smiley faces. Good performance is reflected as a happy, green face. Poor performance is reflected as a sad, red face. Yellow faces represent neutral performance.
The website is composed of three main pages. The home page shows a simple overview of multiple buildings as a league table of performance averaged over a week. The building overview page provides a bit more detail, performance is shown for each day of the week. The building detail page provides a more advanced half-hourly breakdown of performance.
The home page
The home page can be found at http://smartspaces.dmu.ac.uk/ and can be reached from anywhere in the application by clicking on the logo in the top left corner. It provides a simple league table of buildings where each building is listed in order of performance as calculated based on the lastest complete seven-day period.
From this simple table it is possible to identify at a glance:
- Which buildings are performing well
- Which buildings are performing poorly
- How any particular building is performing
- Which utilities (gas, electricity, water) are contributing to the performance in each building.
The building overview page
The building overview page can be found at http://smartspaces.dmu.ac.uk/building_1 and can be reached by clicking on any building listed on the home page. It provides a daily breakdown of performance over the last seven complete days.
The daily breakdown is useful for identifying the onset of changes in performance and shows problems or improvements more quickly than the home page.
The building detail page
The final page is the building detail page, it can be found at http://smartspaces.dmu.ac.uk/building_1/detail and can be reached from the building overview page by clicking on the 'details' tab. The building detail page provides a more technical view of the available data. Half-hourly consumption data are presented as as line chart covering initially one week of consumption (the latest available data). Three zones of expected consumption are also shown.
- The red zone represents 'high' consumption.
- The yellow zone represents 'normal' consumption.
- The green zone represents 'low' consumption.
This figure provides an overview of performance. It can be interpreted by observing where actual consumption relative to the baseline period as indicated by the coloured zones. Typically the consumption pattern is very clear, following a weekly cycle related to occupancy in line with the baseline.
This demonstrates the approach taken in this project. Consumption in a building is never compared to that in another building. The zones are calculated from the last 365 days of consumption data for the same building. The target is always to reduce wastage and this is indicated by a reduction in consumption levels compared to the baseline period.
Feedback for continuous improvement
The data underpinning this website are energy and water consumption values and outside air temperature readings recorded at half hourly intervals. These data are combined to generate a performance indicator that compares consumption in the current half hour to expected consumption levels. As mentioned above, expected consumption is determined based on a 365-day baseline period. The baseline period used is updated every week so that new data are rolled into the baseline and older data are discarded. This approach leads to a system that continuously 'learns' the pattern of consumption.
Users are presented with feedback that indicates on average, whether their building is using more or less energy than expected. If energy performance in a building improves then the feedback system will very quickly identify and visualise the change. Changes to the way the building operates or to how occupants use the building will be flagged up within a day. This makes it possible to experiment with different approaches to reducing energy and water wastage. At the same time, if a problem such as a water leak or heating control failure leads to increased consumption, this will also be flagged up very quickly. In this way, the system is intended to be improve transparency and raise awareness of energy performance and to support continuous improvement.
But how does it work?
The result of this complex approach is that the indicator represents energy performance as a comparison of current consumption with that of the latest 365 days. If consumption is exactly in the middle of the expected range then the indicator is equal to 50. If consumption is higher than the expected range then the indicator is equal to 100. If consumption is lower than the expected range then the indicator is equal to 0. An indicator value of 35, for example, can be interpreted as meaning that 35% of equivalent baseline consumption (i.e. that occuring at the same time of week) was below this value and 65% was above this value.
The smiley face scale provides a user-friendly way to understand energy performance. The indicator is calculated on a half hourly basis. These raw indicator values are then averaged over a day or a week to generate aggregated values. The resulting values are then converted into simple smiley faces shown on the home page and building overview page.
The faces shown in the introduction tab indicate the full range of values. A value of fifty produces a yellow, neutral looking face representing no change over time. A value of zero produces a green, happy looking face representing a significant reduction over time. A value of one hundred produces a red, sad looking face representing a significant increase over time.
Determining the expected level of consumption is a complex process. Data are divided into subsets, one for each 'time of the week'. For example, one subset will include only data recorded at 09:00 on Wednesday mornings. A linear regression model is then fitted to all data (consumption vs outside air temperature) in each subset. No model fits perfectly, for each point of data, the residual consumption (i.e. the difference between actual consumption and that predicted by the model) is recorded. This set of residuals captures how far consumption diverged from the baseline model and so represents the expected scatter around the baseline model. The indicator is calculated by observing how far current consumption diverges from the baseline model and expressing that as a percentile score with respect to the baseline residuals.
Thus, consumption that exceeds the model prediction by more than any experienced in the baseline period would achieve a percentile of 100. Similarly, consumption that falls below the model prediction by more than any experienced in the baseline period would achieve a percentile of 0. Between these values, the percentile score represents the proportion of historical residuals that fell below the current residual. A value of 50 would be achieved for consumption that diverged from the model by more than (and less than) 50% of historic consumption values. This can be summarised by saying that the indicator reflects both the value and spread of historic consumption patterns. If a building is highly predictable then consumption need only shift slightly for an effect to be registered. Less predictable buildings will have a wider spread of residuals and so will be less sensitive to changes in consumption patterns.