This research aims to develop an algorithm that estimates the future values of production demands. Demands are necessary to address the production process and resource inventory management. Difficulties in estimating demands stem from their stochastic nature. The lack of deterministic demand values can increase production costs depending on the lack or excess of inventory or lost profits due to lost production requests. An algorithm with a combination of demand forecasting and predictive model control approach is derived. The latter has been applied for consistent assessments of future needs and improvement of forecast parameters for animal feed consumption. An estimate of the accuracy and error between actual and predicted requirements is presented.

Profit management contains a task related to the allocation of resources. In this way, decision-making can be supported by quantifying and predicting the change in profit by changing the category of resources used in the production business entity. Quantitative modeling of the relationships between resource reallocations and profit management can benefit production and business revenue growth. This research applies formal modeling to a forecasting procedure and estimates the potential income that can be achieved by changing a production resource. The study applies a multiple linear regression formalization to derive a quantitative relationship between income and the amount of feed used as a major component of cow farm management. The regression relationship is used to predict potential increases in livestock income. A model predictive approach for operational management of dairy production is applied. A sensitive analysis is applied to the developed model for comparison and assessment. Testing is done empirically with real livestock data.

The store-and-forward traffic model is widely used because of its simplicity and reasonable comprehension. Its results determine the duration of the green light according to a preset cycle. This paper builds further on the currently existing model: it expands the definitional domain of the optimization problem by adding additional probabilistic requirements regarding the number of vehicles in a street segment between intersections controlled by traffic lights. The defined optimization problem minimizes the probability of increasing the number of vehicles in the considered transport network. A further extension of the store-and-forward model allows the control domain to contain both green lights and cycle durations. Such optimal control allows the achievement of additional objective functions such as minimizing the number of vehicles in the network and minimizing the total time spent through the network. The definition of this control problem is done through a bi-level hierarchical formalization involving the store-and-forward model. The derived extended models are numerically tested and compared with real cases, giving preference to the derived extensions of the classical store-and-forward model.

An active policy for portfolio optimization is developed based on repetitive application of modified Black-Litterman (BL) portfolio model and new formal definition of the expert views. New subjective views are defined which are based on the differences between the historical mean asset returns and their implied return values. An algorithm for the implementation of active management with the modified BL model is derived. The active management policy allows using short time series of historical data of assets, providing portfolio optimization with limited set of assets. New market point is evaluated, because the small set of assets does not allow market index to be used as characteristics of the market. The new formalization of the expert views allows to be compared the Mean Variance and BL portfolios on common basis. The experiments and comparisons between the Mean Variance optimization and the modified BL problem give advantages to the last one.

A bi-level modeling for traffic lights optimization is presented in the paper.The bi-level modeling allows increasing the set of control influences, the number of constraints and applies two goal functions in hierarchical order.The bi-level formalism allows integration of small optimization problems in hierarchical order to a complex interconnected and complicated optimization problem.These features have been applied for optimal control of traffic lights in urban network.The bilevel problem formulation allows to minimize the queue lengths of vehicles and to maximize the outgoing flows from arterial directions.Both control influences of the green light durations and time cycles are evaluated as optimal bi-level control influences.This work is supported by Project KP06-H37/6 "Modelling and optimization of urban traffic in network of crossroads" with the Bulgarian Research Fund.