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.

The new era of customer experience in the omni-channel environment of a communication service provider

This study discusses the evolution of an omni-channel model in managing customer experience. The purpose of this thesis is to expand the current academic literature available on omni-channel and offer suggestions for omni-channel creation. This is done by studying the features of an omni-channel approach into engaging with customers and through the sub-objectives of describing the process behind its initiation as well as the special features communication service providers need to take in consideration. Theories used as a background for this study are related to customer experience, channel management, omni-channel and finally change management. The empirical study of this thesis consists of seven expert interviews conducted in a case company. The interviews were held between March and November 2014. One of the interviewees is the manager of an omni-channel development team, whilst the rest were in charge of the management of the various customer channels of the company. The organization and analysis of the interview data was conducted topically. The use of themes related to major theories on the subject was utilized to create linkages between theory and practice. The responses were also organized in two groups based on the viewpoint to map responses related to the company perspective as well as the customers´ perspective. The findings in this study are that omni-channel is among the best tools for companies to respond to the challenge induced by changing customer needs and preferences, as well as intensifying competitive environment. The omni-channel model was found to promote excellent customer experience and thus to be a source of competition advantage and increasing financial returns by creating an omni-experience for the customer. Through omniexperience customers see all of the transactions with a company presenting one brand and providing ease and effortlessness in every encounter. The processes behind omni-channel formulation were identified as customer experience proclaimed as the most important strategic goal, mapping and establishing a unified brand experience in all (service) channels and empowering the first line personnel as the gate keepers of omniexperience. Further the tools, measurement and supporting strategies were to be in accordance with the omni-channel strategy and the customer needs to become a partner in a two way transaction with the firm. Based on these findings a model for omni-channel creation is offered. Future research is needed to firstly, further test these findings and expand the theoretical framework on omni-channel, as it is quite scarce to date and secondly, to increase the generalizability of the model suggested.

Evaluation of temperatures in a refrigerated container for chilled and frozen food transport

The objective of this work was to monitor the operational conditions of the transport of chilled and frozen foods during delivery within cities and to evaluate the impact of the door openings on the alteration of the internal temperature of the refrigerated environment. Several temperature and pressure sensors were used in a refrigerated container with two compartments and they were installed in the refrigeration system unit and on the internal and external surfaces of the container. After the monitoring tests, it was verified that door openings during deliveries resulted in a disturbance that raised the internal temperature of the refrigerated container above values recommended for adequate conservation of the products transported. Moreover, increasing the number of door openings promoted a cumulative effect on the internal temperature, mainly in the chilled food compartment of the container. It was concluded that the refrigeration system unit presented serious limitations with regard to the maintenance of the container's internal temperature during the actual distribution routine, since it does not possess enough instantaneous capacity to restore the temperature set-point between deliveries.

Environment is crucial to the cooking time of beans

The objectives of this study were to understand how genotype, storage time, and storage conditions affect cooking time of beans and to indicate storage techniques that do not affect the cooking time. The grains were subjected to five different storage periods and six different storage conditions. The cooking time was estimated using the Mattson Cooker. The data were subjected to analysis of variance and a subsequent adjustment of simple linear regression for deployment of the interactions between the factors. Contrasts were used to determine the best levels of the factor storage condition. Genotype did not impact cooking time when the storage time and storage conditions were considered. Time and storage conditions affect the cooking time of beans in a dependent manner, but time of storage had the biggest influence. The best conditions for long-term storage of beans ensuring a smaller increase in cooking time is plastic storage at low temperatures. Thus, plastic freezer storage is a practical alternative for consumers.