Search results

Times Series Building Energy Systems data Imputation

Completeness of data is vital for the decision making and forecasting on Building Management Systems (BMS) as missing data can result in biased decision making down the line. This study creates a guideline for imputing the gaps in BMS datasets by comparing four methods: K Nearest Neighbour algorithm (KNN), Recurrent Neural Network (RNN), Hot Deck (HD) and Last Observation Carried Forward (LOCF). The guideline contains the best method per gap size and scales of measurement. The four selected methods are from various backgrounds and are tested on a real BMS and meteorological dataset. The focus of this paper is not to impute every cell as accurately as possible but to impute trends back into the missing data. The performance is characterised by a set of criteria in order to allow the user to choose the imputation method best suited for its needs. The criteria are: Variance Error (VE) and Root Mean Squared Error (RMSE). VE has been given more weight as its ability to evaluate the imputed trend is better than RMSE. From preliminary results, it was concluded that the best K‐values for KNN are 5 for the smallest gap and 100 for the larger gaps. Using a genetic algorithm the best RNN architecture for the purpose of this paper was determined to be Gated Recurrent Units (GRU). The comparison was performed using a different training dataset than the imputation dataset. The results show no consistent link between the difference in Kurtosis or Skewness and imputation performance. The results of the experiment concluded that RNN is best for interval data and HD is best for both nominal and ratio data. There was no single method that was best for all gap sizes as it was dependent on the data to be imputed.

EV charging plaza_ A data-driven case study

This paper presents data-driven insights from a case study that was carried out in an University EV charging plaza where EV charging demand is met with the combination of the University campus grid and installed solar capacity. First, we assessed the plaza dependency on the grid for meeting EV charging demand and intake of excess solar energy using the available dataset. By modifying the plaza network to accommodate a small approx. 50 kWh battery storage can significantly reduce the grid dependency of the plaza by approx. 30% compared to the present situation and can also increase the green energy utility for EV charging by 10-20%. Having an battery storage could also help overcome the limitations due to the campus grid capacity during EV charging peak demand by means of scheduling algorithms. Second, we assessed the utility rate of the plaza which indicated that the average utility of charging infrastructure is about 30% which has an increasing trend over the analysed period. The low utility and EV charging peak demand may be the result of current EV user behavior where the average idle time during charging sessions is found to be approx. 90 minutes. Reduction in idle time by one third may increase the capacity and utility of plaza by two to two and half times the forecasted daily demand. By having the campus grid capacity and user information may further help with effect EV demand forecasting and scheduling.

Towards Destination Stewardship

This paper presents four Destination Stewardship scenarios based on different levels of engagement from the public and private sector. The scenarios serve to support destination stakeholders in assessing their current context and the pathway towards greater stewardship. A Destination Stewardship Governance Diagnostic framework is built on the scenarios to support its stakeholders in considering how to move along that pathway, identifying the key aspects of governance that are either facilitating or frustrating a destination stewardship approach, and the required actions and resources to achieve an improved scenario. Moreover, the scenarios and diagnostic framework support stakeholders to come together to debate and scrutinise how tourism is managed in a way that meets the needs of the destination, casting new light on the barriers and opportunities for greater destination stewardship.

The Future of Backpacking

By use of a literature review and an environmental scan four plausible future scenarios will be created, based on the research question: How could the future of backpack tourism look like in 2030, and how could tourism businesses anticipate on the changing demand. The scenarios, which allow one to ‘think out of the box’, will eventually be translated into recommendations towards the tourism sector and therefore can create a future proof company strategy.

Individual intuition and communicative charisma as enablers of futures envisioning: ‘genius forecasting’ vs ‘forecasting geniuses’.

Changing teacher perspectives

A group of Dutch teachers, as part of their Master’s programme, developed a game that allows teachers to break free from their day-to-day affairs and reflect on futures by designing scenarios about the future of their school. In this game-based approach the journey of scenario exploration is composed of seven steps: (1) choice of a theme and timeframe, (2) selection of key dilemmas on which two scenario axes will be based, (3) understanding the content and context of a “matrix” provided for the game, (4) setting up scenario groups, (5) developing four scenarios, (6) sharing scenarios, and (7) reflection on the scenarios.