The paper proposes a data-based approach in control of building temperature for the case of a single floor of an office building. Several obtained datasets are exploited to identify a mathematical model of building thermal dynamics. Input-output data mapping is performed by multiple linear regression to identify a linear model in form of a vector of coefficients related to historical variables of temperatures of the considered and neighboring offices, external variables and user behavior as disturbances. The model is exploited for temperature setpoint tracking optimal problem formulation and put as trade-off of comfort and energy efficiency. Such data predictive control approach is implemented to a case study and realistic simulations are performed with real data, proving the soundness of the approach. The concept is motivated by easy replication of both hardware and software to be efficiently implemented in the buildings, driven by time-effectiveness of the proposed structure and identification method of the model.

This paper deals with distributed control of variable efficiency heterogeneous battery storage systems connected in a microgrid. The nonlinear efficiency of battery charging is taken from converters’ datasheet and identified battery internal resistance, and a corresponding nonlinear model is derived dependent on state of energy. Individual battery control, as a local nonlinear problem, is solved by using a sequential linear program. Distributed control with the central supervisor is then used to coordinate individual batteries within the storage system and ensure improved overall system operation while respecting the joint constraint of the grid connection power capacity. Asymmetric projection algorithm is used for distributed control, based on iterative convergence of individual battery control actions towards the optimal operation of the whole system. The algorithm is implemented in a realistic simulation scenario of six different batteries with their corresponding characteristics, real electricity prices and measured load consumption. Presented results show that distributed control satisfies global constraint, while obtaining better cost than the decentralized approach with previously reported 7% of increased savings of nonlinear over constant efficiency.

Travel time duration and traffic forecasting in urban environments is of critical importance for efficient supply chain logistics and accurate navigation services. The paper compares data-driven statistical and machine learning approaches for urban traffic travel times forecasting on a 15-minute resolution for the next 24 hours. A detailed analysis of the available historical data is performed, including historical floating car data for a one-year period. Data analysis is followed by development and evaluation of baseline, ARIMAX, neural network and gradient boosting models. The predictions are generated on a day-ahead forecasting horizon where the machine learning models are propagated in a recursive strategy. Recursive approach implies more accurate short-term forecasts that are crucial in the context of nowcasting, while maintaining good accuracy on long-term horizons necessary for daily operation planning. The evaluation of the models accuracy is conducted on four main arterial urban routes in the city of Zagreb, Croatia, with travel times data obtained from a commercial navigation service. A detailed analysis of the results is performed, with a special focus put on the accuracy of near future predictions, as well as different models and model structures.

This paper presents a microgrid energy flow optimization algorithm with variable battery storage efficiency in order to achieve energy savings and expand the lifespan of the components. The converter efficiency curve is deduced from converter’s datasheets and approximated with mathematical functions. The power loss on the battery internal resistance is also included in order to achieve a more accurate model of the complete storage system. The obtained nonlinear model is used in model predictive control formulation and solved by using a sequential linear program (SLP) algorithm. The SLP algorithm iteratively linearizes the model around the current solution and uses corresponding efficiencies over the prediction horizon. Simulations in MATLAB are performed for a 7-day period and compared with a conventional, constant-efficiency battery system model. The results show an improved performance regarding the charging and discharging battery power and the overall savings of 7% in comparison with the conventional model used in model predictive control.

The control system for energy-efficient train operation with the inclusion of a detailed train motion model and train traction system energy efficiency is presented in the paper. A piecewise affine train model is constructed with the parameters obtained for the electromotive train of an industrial manufacturer. The model encompasses intrinsic features of the train system such as linearized resistance force, a set of traction and braking force physical limitations and passengers comfort constraints. The resulting quadratic optimization problem is solved parametrically through dynamic programming giving the off-line precomputed optimal control law that is a function of train speed and traversed path. The on-line computed traction force profile is then tuned with respect to the traction system energy efficiency. The developed control system is evaluated on a detailed real case study scenario put together with a railway operator and the train manufacturer. The presented results show the possibility of significant energy consumption reductions achieved by energy-efficient train control.

Predictive control and optimization in buildings proved to be a promising approach in increasing energy efficiency of the sector as one of the largest energy consumer. Zone digitalization is still one of the ongoing issues in older buildings, and has only recently started to be interesting in the residential sector due to high prices of required expert knowledge and automation equipment. However, buildings systems digitalization and networking also brought to fore the system security issues. Distributed approach to zone digitalization and predictive control, enabled by recent advances in embedded technology, implies both hardware topology and control algorithm structure. The paper focuses on a case where each zone holds a separate controller with tailored temperature setpoint prediction and model predictive control algorithm, which independently calculate the optimal heating control laws of the corresponding zones. Furthermore, the controllers are mutually and iteratively bidding toward the joint energy efficiency goal of the whole building. Such control structure enables fast digitalization and optimal joint operation of the building while keeping the independency of the users and retaining the data privacy. Only essential data is transmitted to the central coordinator in form of a summed information, which cannot extrapolate particular user data. Additionally, single zone controller security breach does not inflict damage to the whole system. System resiliency to security issues is therefore strongly increased.

The paper presents a railway energy management system based on hierarchical coordination of electric traction substation energy flows and on-route trains energy consumption. The railway system is divided into energy-efficient individual trains energy consumption management as lower level, and the price-efficient electric traction substation energy flows management as higher level. The levels are coordinated through parametric hierarchical model predictive control with the main goal of additionally increasing the energy efficiency and decreasing the operational costs of the overall system. Through interactions with the power grid on the higher level, the system is able to provide ancillary services and respond to various grid requests. At the same time, lower level trains driving profiles are adjusted to attain the minimal cost of system operation with timetables and on-route constraints respected. The developed algorithm is verified on a detailed real case study scenario put together with a railway operator and a trains manufacturer. The presented results show significant cost and energy consumption reductions achieved by simultaneous coordination of several trains supplied from the same traction substation.

This paper presents a predictive control method for power variation reduction and maximum power limitation in building heating systems. A case study with heating supply pipeline of a skyscraper floor with 13 zones is chosen. Simulation environment is developed to simulate floor thermal dynamics with fan coils as heating elements. Fan coils operation in different zones is orchestrated via model predictive control in order to achieve as smooth as possible cumulative heating power consumption profile while respecting individual comfort requirements in zones. The approach inherently limits the maximum power measured on a calorimeter. Compared to conventional decentralized hysteresis-based temperature control in zones, simulation results show that the heating power variance is successfully reduced and fan coils smooth operation is ensured while the overall energy efficiency increased. By replicating the presented control system through all the segments of a building, this approach yields important benefits of smoothing the building power consumption curve and significant savings in contracted heating power.