This paper focuses on the state estimation of a specific class of state-intermittent dynamical systems evolving in a high-dimensional state-space. As the dimension is large, a classical estimator such as a Kalman filter would require a large observation horizon to converge. To overcome this limitation, a mixed-integer formulation is proposed and solved by using a Genetic Algorithm. We also propose a reduced-order state estimation as a variant of this approach under some mild assumptions, which reduces the observation window size even more. In particular, we show, through a case study in finance, that the reduced model and its associated genetic algorithm can reduce the observation window size needed by almost 75% and that this method is faster than the non-reduced mixed integer optimization problem. We also show that the reduced-order state estimation approach can be used to discover a mutual fund portfolio composition at each date of a given period.

Electricity consumption forecasting stands as a critical research domain within electrical engineering, with myriad of traditional forecasting models and artificial intelligence techniques undergoing rigorous examination. This paper is devoted to a comparison of three Machine Learning approaches to surrogate modelling and forecasting of the daily electricity consumption in Tirana, Albania: A Radial Basis Function (RBF) approach, a feed forward Neural Network approach and a Recurrent Neural Network approach. Through meticulous experimentation across four distinct scenarios encompassing variations in training/testing splits, historical data utilization, and hyper parameter optimization, we thoroughly evaluate the performance of each model. Comparative analysis is conducted based on model fit, computational efficiency, and error measurement metrics. Our findings highlight the remarkable performance of the RBF ARX approach, underscoring its effectiveness in accurately forecasting electricity consumption.

Forecasting electricity consumption remains essential, necessitating the application of recent, hybrid, and classical models. Traditional approaches often fall short in capturing nonlinear and irregular data patterns. This paper compares three distinct approaches for surrogate modeling and forecasting daily electricity consumption across five regions in Albania: a Radial Basis Function approach, a feedforward Neural Network approach, and a Recurrent Neural Network approach. Our aim is to develop a generalized model for these regions and provide highly accurate one-day-ahead predictions, considering daily average temperature as an exogenous variable. We conduct a comparative analysis based on model fit, computational efficiency, and error measurement metrics. Our findings underscore the exceptional performance of the RBF ARX approach, showcasing its efficacy in accurately forecasting electricity consumption based on daily data. Daily mean temperature is identified as a key factor influencing model performance.

This paper introduces the dynamic mode decomposition (DMD) for the prediction of the air quality and the precipitation in the presence of high rain as an application of environment prediction tasks by forecasting the appropriate index parameters for each field. The forecasting procedure is based on the use of two real data bases containing the pollutant concentration, and the precipitation for the flooding forecasting. Moreover, the temporal evolution of the DMD modes, can be used to reconstruct the desired components and perform forecasting at the same time using the eigenvalues and eigenvectors. This task of the DMD is already known by the literature, the new in this paper is the application of the DMD for forecasting tasks on the environment issues which present appreciated results that are discussed and well analysed in this paper using different performance indexes to prove its efficiency.

In this paper, we consider the optimal control problem for complex irrigation systems, using a receding horizon. The idea of decomposition is introduced for the goal of both reducing the computational complexity, to comply with the system topology and the monitoring architecture. A decomposition-coordination algorithm based on the use of both an augmented Lagrangian and the duplication of variables is developed which is suitable for the optimal control of complex irrigation systems, composed of water retention systems, water supply/distribution systems using canals and pipe networks. In some conventional decomposition-coordination approaches, such as the price decomposition-coordination algorithm, the coupling constraints between subsystems or the associated Lagrange multipliers are used as coordination variables. In our case, some physical variables, such as water flow rates, are duplicated in each subsystem, where they appear. Some compatibility constraints are then introduced and their associated Lagrange multipliers are used as coordination variables. In this paper, we present the application of this approach to to the Canal de la Bourne irrigation network, which irrigates the agricultural plain of Valence (south-east of France).

The paper deals with the modelling and the automatic control of a dam-river system, where the action variable is the upstream flow rate and the controlled variable the downstream flow rate. The system is modeled with a linear model (second order transfer function with delay). Two control methods (pole placement and Smith predictor) are compared in terms of performance and robustness. The pole placement is done on the sampled model, whereas the Smith predictor is based on the continuous model. Robustness is estimated with the use of margins, and also with the use of a bound on multiplicative uncertainty for variable reference discharges. Simulations are carried out on a nonlinear model of the river, and performance of both controllers are compared to the one of a continuous-time PID controller.