sara ghane | University of Guilan (original) (raw)

Address: Iran, Islamic Republic of

less

Uploads

Papers by sara ghane

Research paper thumbnail of Grouped Charging of Decentralised Storage to Efficiently Control Collective Heating Systems: Limitations and Opportunities

Energies

Collective heating systems have multiple end-users with time-varying, often different temperature... more Collective heating systems have multiple end-users with time-varying, often different temperature demands. There are several concepts catering to this, e.g., multi-pipe networks and 2-pipe networks with or without decentralised booster systems. In this study, we focus on 2-pipe networks with a changing supply temperature by smart use of decentralised storage. By grouping high-temperature demands, the average supply temperature can be lowered during large parts of the day, which is beneficial for system efficiency. The actual energy-saving potential, however, can be case-specific and is expected to depend on design choices and implemented control strategies. In this paper, these dependencies are assessed and identified by implementing two optimised rule-based control strategies, providing in such a way a bench-mark for other control strategies. The results show that grouping yields energy savings of up to 36% at similar peak demand as with conventional control strategies. The energy-...

Research paper thumbnail of Disaggregation of digital meter data for synthetic load profile generation

Building Simulation Conference Proceedings

Research paper thumbnail of Supply temperature control of a heating network with reinforcement learning

2021 IEEE International Smart Cities Conference (ISC2), 2021

Heating networks are typically controlled by a heating curve, which depends on the outdoor temper... more Heating networks are typically controlled by a heating curve, which depends on the outdoor temperature. Currently, innovative heating networks connected to low heat demand dwellings ask for advanced control strategies. Therefore, the potentials of reinforcement learning are researched in a heating network connected to a central heat pump and four dwellings. The comparison between a discrete and continuous action space is made with respect to the weight factor of the reward function. The results indicate that in both cases the reinforcement learning-based controlling of the supply temperature can generally ensure energy savings while keeping the occupant's temperature requirements in comparison to the rule-based controller.

Research paper thumbnail of On-line twin independent support vector machines

Neurocomputing, 2016

The success of SVM in solving pattern recognition problems has encouraged researcher to extend th... more The success of SVM in solving pattern recognition problems has encouraged researcher to extend the development of different versions. They are well-known for their robustness and good generalization performance. In many real-world applications, the data to be trained are available on-line in a sequential fashion and because of space and time requirements, batch training methods are not suitable. This paper proposes a new fast on-line algorithm called OTWISVM. It defines two optimization problems and incremental learning is done based of them. Two hyperplanes are generated as decision functions thus each of them is closer to one of the two classes and is as far as possible from the other. The solution is constructed via two subsets of linearly independent samples seen so far, and is always bounded. Good accuracy and notable speed of the method was tested and affirmed both on ordinary and noisy data sets as opposed to similar algorithms.

Research paper thumbnail of Grouped Charging of Decentralised Storage to Efficiently Control Collective Heating Systems: Limitations and Opportunities

Energies

Collective heating systems have multiple end-users with time-varying, often different temperature... more Collective heating systems have multiple end-users with time-varying, often different temperature demands. There are several concepts catering to this, e.g., multi-pipe networks and 2-pipe networks with or without decentralised booster systems. In this study, we focus on 2-pipe networks with a changing supply temperature by smart use of decentralised storage. By grouping high-temperature demands, the average supply temperature can be lowered during large parts of the day, which is beneficial for system efficiency. The actual energy-saving potential, however, can be case-specific and is expected to depend on design choices and implemented control strategies. In this paper, these dependencies are assessed and identified by implementing two optimised rule-based control strategies, providing in such a way a bench-mark for other control strategies. The results show that grouping yields energy savings of up to 36% at similar peak demand as with conventional control strategies. The energy-...

Research paper thumbnail of Disaggregation of digital meter data for synthetic load profile generation

Building Simulation Conference Proceedings

Research paper thumbnail of Supply temperature control of a heating network with reinforcement learning

2021 IEEE International Smart Cities Conference (ISC2), 2021

Heating networks are typically controlled by a heating curve, which depends on the outdoor temper... more Heating networks are typically controlled by a heating curve, which depends on the outdoor temperature. Currently, innovative heating networks connected to low heat demand dwellings ask for advanced control strategies. Therefore, the potentials of reinforcement learning are researched in a heating network connected to a central heat pump and four dwellings. The comparison between a discrete and continuous action space is made with respect to the weight factor of the reward function. The results indicate that in both cases the reinforcement learning-based controlling of the supply temperature can generally ensure energy savings while keeping the occupant's temperature requirements in comparison to the rule-based controller.

Research paper thumbnail of On-line twin independent support vector machines

Neurocomputing, 2016

The success of SVM in solving pattern recognition problems has encouraged researcher to extend th... more The success of SVM in solving pattern recognition problems has encouraged researcher to extend the development of different versions. They are well-known for their robustness and good generalization performance. In many real-world applications, the data to be trained are available on-line in a sequential fashion and because of space and time requirements, batch training methods are not suitable. This paper proposes a new fast on-line algorithm called OTWISVM. It defines two optimization problems and incremental learning is done based of them. Two hyperplanes are generated as decision functions thus each of them is closer to one of the two classes and is as far as possible from the other. The solution is constructed via two subsets of linearly independent samples seen so far, and is always bounded. Good accuracy and notable speed of the method was tested and affirmed both on ordinary and noisy data sets as opposed to similar algorithms.

Log In