A Bayesian Approach for Forecasting Heat Load in a District Heating System

The growing population in cities increases the energy demand and affects the environment by increasing carbon emissions. Information and communications technology solutions which enable energy optimization are needed to address this growing energy demand in cities and to reduce carbon emissions. District heating systems optimize the energy production by reusing waste energy with combined heat and power plants. Forecasting the heat load demand in residential buildings assists in optimizing energy production and consumption in a district heating system. However, the presence of a large number of factors such as weather forecast, district heating operational parameters and user behavioural parameters, make heat load forecasting a challenging task. This thesis proposes a probabilistic machine learning model using a Naive Bayes classifier, to forecast the hourly heat load demand for three residential buildings in the city of Skellefteå, Sweden over a period of winter and spring seasons. The district heating data collected from the sensors equipped at the residential buildings in Skellefteå, is utilized to build the Bayesian network to forecast the heat load demand for horizons of 1, 2, 3, 6 and 24 hours. The proposed model is validated by using four cases to study the influence of various parameters on the heat load forecast by carrying out trace driven analysis in Weka and GeNIe. Results show that current heat load consumption and outdoor temperature forecast are the two parameters with most influence on the heat load forecast. The proposed model achieves average accuracies of 81.23 % and 76.74 % for a forecast horizon of 1 hour in the three buildings for winter and spring seasons respectively. The model also achieves an average accuracy of 77.97 % for three buildings across both seasons for the forecast horizon of 1 hour by utilizing only 10 % of the training data. The results indicate that even a simple model like Naive Bayes classifier can forecast the heat load demand by utilizing less training data.

Developing asset management in district heating and cooling business in a large energy company

The purpose of this Master´s Thesis is to develop asset management and its practices in case company. District heating and cooling systems operated by case company around Finland, Sweden, Poland and the Baltics form an enormous-sized asset base where some parts are starting to reach their end of life-cycles. Large-sized asset renewal actions are under discussion and maintenance spending is increasing. Financially justified decisions in changing business environment are needed. Asset management is one of the most important concepts for production organization which operates with capital-intensive production assets. Organizations profitability is highly dependent on assets´ performance. Such assets, like district heating and cooling systems, should be utilized as efficiently as possible within their life-cycles but also maintained and renewed optimally. In this qualitative thesis, empirical interview study was conducted to describe the current situation on how the assets are managed in the case company and to examine the readiness to implement a new, risk-based solution. Asset management revealed to be a very well-known concept. From proposed risk-based asset management point of view, several key observations were made. It was seen as a suitable solution, but further development will be needed. Based on the need and findings, several key processes and frameworks were created and also tested with a case study. Assets` condition monitoring should be improved, which would have a positive impact on event probability assessment. Risk acceptance is also a thing to be discussed further. When the evaluation becomes fluent in single investment cases, portfolio-level expansion should be considered and started. As a result, thesis proposes a solution how risk-based asset management could be performed practically in a capital-intensive case company in order to optimize the maintenance spending in a long run. Created practical framework is made universal: similar principles can be applied into multiple cases in case company but also in other energy companies. Risk-based asset management`s benefits could be utilized best in portfolio-level optimization where the capital would be invested to the most important objects from total risk point of view. Eventually, such approach would allow case company to optimize capital spending in a situation where funds are not adequate to cover all the mandatory needs and prioritization between the investment alternatives will truly be needed.

Le Mois scientifique et industriel : revue internationale d'information

1901/06 (A3,N1)-1901/07.

Le Mois scientifique et industriel : revue internationale d'information

1919/12 (A21).

Le Mois scientifique et industriel : revue internationale d'information

1901/12 (A3,N6)-1902/02.

Le Mois scientifique et industriel : revue internationale d'information

1903/01/25 (A5,N41).

Le Mois scientifique et industriel : revue internationale d'information

1906/04 (A8,N80).

Le Mois scientifique et industriel : revue internationale d'information

1910/12 (A12,N136).

Le Mois scientifique et industriel : revue internationale d'information

1904/07/25 (A6,N59).

Le Mois scientifique et industriel : revue internationale d'information

1906/04 (A8,N28).

Le Mois scientifique et industriel : revue internationale d'information

1914/06 (VOL16,N178).

Le Mois scientifique et industriel : revue internationale d'information

1914/02 (VOL16,N174).

Le Mois scientifique et industriel : revue internationale d'information

1903/02/25 (A5,N42).

Le Mois scientifique et industriel : revue internationale d'information

1904/05/25 (A6,N57).