Search

The paper presents the results of the research on the comparative study of the methods of cluster analysis and conditions, which was carried out from the point of view of their use, on the example of data concerning the operation of the National Power System. Two algorithms were used for the clustering analysis, i.e. the Ward algorithm and the algorithm of self-organizing two-dimensional maps. Cluster analysis was preceded by a review of hierarchical and non-hierarchical methods of data analysis and a description of the prepared experiment. The obtained results were interpreted. The work consists of two parts published under the same main title with different subtitles. This part 1 presents the results of the conducted review of selected methods of cluster analysis and the research conditions resulting from the adopted data on the operation of the National Power System. Part 2 presents the cluster analysis process and selected research results and their discussion.

The article presents selected results of research on the modeling of humanoid robots, including the results of neural modeling of human gait and its implementation in the environment MATLAB and Simulink with the use of Deep Learning Toolbox. The subject of the research was placed within the scope of the available literature on the subject. Then, appropriate research experiments on human movement along a given trajectory were developed. First, the method of measuring the parameters present in the experiment was established, i.e. input quantities (displacement of the left heel, displacement of the right heel) and output quantities (displacement of the measurement point of the human body in space). Then, research experiments were carried out, as a result of which numerical data were measured in order to use them for teaching and testing the Artificial Neural Network. The Perceptron Artificial Neural Network architecture was used to build a model of a neural human walk along a given trajectory. The obtained results were discussed and interpreted, drawing a number of important conclusions.

The work is a continuation of the article under the same main title and subtitle Part 1. Comparative study of methods and conditions. This article concerns the cluster analysis, which was carried out on the example of data concerning the operation of the National Power System, namely the total generations of nCDGUs and CDGUs listed by PSE Operator. Two algorithms were used to obtain the results of the cluster analysis, i.e. the Ward algorithm and the algorithm of self-organizing twodimensional topographic maps. The obtained results were interpreted and their discussion and interpretation were conducted.

The work contains selected research results regarding the identification modeling of the Polish Electric Power Exchange on the example of numerical data listed on the Day-Ahead Market of TGE S.A. in Poland. In order to obtain the model of Day-Ahead Market System, first identification for numerical data from the period 01.01.2013-31.04.2016 has been downloaded from TGE S.A., obtaining discrete arx parametric models in MATLAB and Simulink using the System Identification Toolbox. The resulting model was then converted to continuous parametric models, and those to continuous models in the state space for 35 conventional semi-annual measurement periods. On the basis of the obtained test results, state variables and selected model parameters were interpreted, i.e. all non-zero elements of matrix A and nine selected elements of matrix B and one parameter of matrix C.

The publication concerns the important contemporary issues of searching for the Day-Ahead Market system models, including identification and simulation models. The models were obtained as a result of the identification process based on the data listed on TGE S.A. and as a result of building the obtained identification model in Simulink in the form of a simulation model. As a result of the identification, a model of the Day-Ahead Market system was obtained, i.e. relationships were found between 24 input quantities concerning the volume of electricity supplied and sold in each hour of a day and individual output quantities for each hour of a day, i.e. the obtained volume-weighted average electricity price. On the basis of the obtained system identification model, a simulation model was built in Simulink, thanks to which it was possible to conduct, apart from simulation tests, also sensitivity tests and comparative tests. Both models, i.e. the identification model and the simulation model, were further subjected to an evaluation of the efficiency, effectiveness and robustness of the model against the system. Research in this area belongs to the original research.

The paper presents selected results of research on the use of artificial intelligence methods, which are inspired by quantum computing solutions for modelling of electric power exchange systems. Methods used in the modelling of quantum data acquisition, quantization and dequantization of information as well as the methods of performing quantum computations were emphasized. Furthermore, we have analysed the results obtained for the neural model and for the evolutionary algorithm inspired by the quantum computer science. Eventually, the model was verified on the example of the neural model of the Electric Power Exchange (EPE).

The work contains results of research on the possibility to improve the neural model of the Electric Power Exchange (polish: Towarowa Giełda Energii Elektrycznej – TGEE) in MATLAB and Simulink environment using evolutionary algorithm inspired by quantum computer science. The developed artificial neural network was trained using data for the Day Ahead Market, assuming the joint volume of supplied and sold electrical energy [MWh] as the input quantities in each hour of the 24-hour day, and average prices [PLN/MWh] as output quantities. The obtained model of the exchange system was improved using the evolutionary algorithm, and further improvement in the accuracy of the model by supplementing the evolutionary algorithm using quantum solutions, related to the initial population, crossover and mutation operators, selection, etc. were proposed.

In the paper the concept of Shared Service Center (SSC) for public administration is introduced. Processes and models of SSC are defined, but from the point of view of one of the main purpose of public administration– delivering public services. It is proposed to, while planning and implementing SSC, not only focus on designing services for organizational units participating in the SSC, but also to design solution for e-services for citizens. So the emphasis should be put, not only on modelling supporting processes just like for planning the implementation of commercial SSC, but also on core processes. Specific legal solutions are also pointed out, which are supporting this concept, from the point of view of organization of SSC (new Polish legislation) and from the point of view of funding the development of SSC (European Union operational programs supporting e-services for A2A and A2C).

The paper contains selected results of metaidentification of the control system of the Polish Power Exchange using numerical data quoted on the Day-Ahead Market obtained in the form of a MISO metamodel. Identification methods, including methods leading to parametric models, have been used for many years, especially in technical sciences, including management and control of the power system and its subsystems. Various methods of obtaining metamodels depending on the test object are used. There are no available methods of metaidentification of technical and technical-economic systems leading directly to the metamodel of systems such as the system of the Polish Power Exchange, and the models obtained so far have been prognostic, planning or programming models.

In order to identify the system of the Polish Power Exchange on the basis of numerical data quoted on the Day Ahead Market of Towarowa Gielda Energii S.A. in the period from 1st January 2013 to 30th April 2016, 24 input variables were discriminated in relation to the total volume of electricity delivered and sold for all transactions concluded during the trading session in each hour of the 24-hour day (24 input variables) and 24 single output values related to the obtained average price weighted by the volume of electrical power sold for all transactions concluded during the trading session for a given hour of the 24-hour day. In this way, 24 models were obtained with 24 input variables (volumes for individual hours of the 24-hour day) and individual output variables - MISO models. A total of 35 periods of a six-month data range covering 184 days of quotations on the Day Ahead Market were identified.

The paper contains selected results of research on the Domestic Power System (DPS) as an unmanned factory. Models of the DPS system of the MISO type, obtained as a result of identification for 14 inputs and 4 outputs were presented. Particular attention was given to the identification and the assessment of the DPS development based on the systems and control theory. The obtained models of the DPS development were analyzed and discussed. The studies were obtained model of the development of the DPS, and on the basis of is knowledge of the structural and parametrical changes of system development. The model can be used to analyze the design and development of the system from the point of view of the growth of internal organization system and the transition to higher levels of control.

The paper contains selected results of research related to the nature and the implementation of the neural model supported by the evolutionary algorithm inspired by quantum calculations for determination of prices at the Polish Power Exchange. Numeric data quoted at the Day Ahead Market in the period of 1st January 2015 to 30th June 2015 were used to train the artificial neural network in the model of the system. Attention was paid to quantization method, dequantization method and the method of quantum calculations. Significant improvement of the neural model supported by the quantum-inspired evolutionary algorithm was obtained compared with the model without quantum inspiration.

The paper presents the results of research concerning the Polish Power Exchange as a management system, obtained using the data quoted on the Day-Ahead Market. As a result of identification, 24 arx discrete linear parametric models of MISO type were obtained (with 24 input quantities and single output quantities). Input quantities are the volume of electrical energy supplied and sold in each hour of the 24-hour day, and output quantities are average prices weighted by the volume of electrical energy obtained in each hour of the 24-hour day. These models were converted to continuous parametric models, and further into continuous models in the states space. The results of the discussion were also presented, including the interpretation of state variables, as well as the model's parameters and the conclusions together with directions for further research.

This work intends to improve research on artificial neural network model of the Electric Power Exchange using Date of the Day Ahead Market in MATLAB and Simulink environment using Evolutionary Algorithm inspired by quantum computer science. The developed artificial neural network was initially trained using data for the Day Ahead Market, assuming the joint volume of supplied and sold electrical energy as the input quantities in each hour of the twenty for hours day, and average prices as output quantities. The obtained model of the exchange system was then improved using the evolutionary algorithm. Lastly, we have proposed further improvement to the accuracy of the model, by supplementing the existing evolutionary algorithm with Quantum Inspired Evolutionary Algorithm as a solutions type of Hybrid Intelligent Systems, such as the initial population, crossover and mutation operators, selection, fitness function etc. The reprint shows how you can build a model of artificial neural network inspired by quantum solutions in Simulink environment, which is the purpose of further research.

The paper presents results of research on the improvement of parameters of the neural model of system of the Polish Electricity Stock Exchange in the MATLAB and Simulink environment using methods inspired by quantum computer science. The models of the Artificial Neural Network of the taught Electricity Stock Exchange System, including selected elements of quantum computing used to improve the neural model of this system, and the Electricity Stock Exchange System quantum-neural model were also shown. Particular attention has been paid to neural modeling using Neural Network Toolbox and quantum-neural modeling using Simulink. The research experiments were carried out on the basis of quotations on the Polish Electricity Stock Exchange for quotes on the Day Ahead Market. As input quantities in the learning process of the Artificial Neural Network, the volume of electricity supplied and sold at particular times of the day was used, and the average prices received at each of the 24 hours as a starting point. As a result of the learning, a neural model of Electricity Stock Exchange System in the form of an Artificial Neural Network was obtained, and on its quantum-neuronal model of Electricity Stock Exchange system, which used the quantum calculations simulated in Simulink.

The following paper contains selected results of research on modeling identification of Polish Electricity Exchange on the example of the dates quoted on the Day Ahead Market. In order to obtain a model of the Polish Electricity Exchange System in the beginning it was conducted to identify data for the period from January, 1 (2013) to December, 31 (2015). In the result discrete parametric model using arx method in MATLAB and Simulink environments with System Identification Toolbox was obtaining. The resulting model was converted to a continuous parametric model, and that one in turn into the state space model. On the basis of obtained equations of state and outputs, state variables and parameters of the selected model were interpreted, i.e. selected elements of the matrix' of the state space model. A block diagram was then constructed in Simulink, which was used for simulations and sensitivity studies using: sine, Dirac impulse and step function. Numerous interesting research results have been obtained, including the correctness of the development of the Polish Electricity Exchange.

The work contains selected results of research related to identification modelling of the Polish Power Exchange (Towarowa Gielda Energii Elektrycznej S.A. — TGEE) obtained in MATLAB and Simulink using the System Identification Toolbox and Control System Toolbox. In order to obtain a parametric arx model of the Polish Power Exchange identification was performed using data for the first half year of 2015 (184 days), i.e. for 24 input quantities related to the volume of supplied and sold electrical energy (ee) in each hour of the 24-hour day as well as for individual output quantities related to average prices of supplied and sold ee in consecutive hours of the 24-hour day. 24 discrete parametric models of MISO type were obtained, followed by their transformation into continuous parametric models, and, further, into continuous models in state space. The research was conducted in order to find out whether it was possible to generate a model of the Polish Power Exchange (TGEE) and a metamodel based on the changes of the values of the elements of the model in consecutive hours of the 24-hour day. As a result, changes of elements of matrix A related to changes in the internal organization of the system and selected elements of matrix B related to the change of the control level were analysed. Also, an attempt to analyse the obtained results including state variables was made.

The paper contains selected results of research related to neural modeling of electrical power system development (EPS or EP System). Numerical data presented in paper [1, 8] were used to teach the artificial neural network (ANN) a model of EP system development. The ANN was designed in the MATLAB and Simulink environment using the Neural Network Toolbox. The generated model was used to perform simulation to examine sensitivity in Simulink. On the basis of the simulation model a comparative study was performed to compare responses of the model and the IEEE RTS test system. Sensitivity of the model was also examined by measuring the response of the model to the following input functions: sinusoid, unit step, Dirac impulse (Dirac delta function), etc. The results obtained were interpreted on the basis of the control and systems theory.

The paper proposes a new method of quantum computing using control and systems theory as well as matrix-quantum computing. The algorithm developed on the basis of the PR-02 robot’s arm’s movement was implemented in using the Neural Network Toolbox. The application of the neural model instead of the analytic model allowed for obtaining the improvement of the trajectory of the PR-02 robot’s arm movement, while the application of the quantum artificial neural network for the assumed number of quasi-parallel computations equal 1000 did not result in the improvement of the model.

The paper presents results of electrical power system identification shaped by selected values of the electrical power market, which identification is conducted using IEEE RTS test data. Development of such a model is an extremely important step of designing electrical power system development, especially as regards forecasting power of generators as well as fixed and variable costs of system development, etc. The EE system model was obtained by taking six input variables, i.a. total existing active power and forecast demand for active power increase as well as three output variables, i.a. forecast power of generators and forecast additional fixed and variable costs. Parametric models and models in state space were obtained. State variable courses were shown.

This paper presents the first observations on modern genetic algorithms, and then proposed a new algorithm called Systemic Evolution Algorithm (SEA). In the definition of the algorithm uses the concept of SEA electricity market, defined on the basis of control theory and systems. As a result of the identification system received electricity market model in MATLAB and Simulink environment, taking into account the input data such as the number of different types of transmission lines, the number of power stations, the number of transformers, and the amount of energy devoted to the transmission network, or purchased of the Transmission System Operator (TSO), etc. Obtained in this way, using the System Identification Toolbox, appropriate models of type arx, for all inputs and for each individual output and the corresponding models in the state space. Built the model of the development of the electricity market in Simulink, which in addition to simulation studies can also be used in clinical prediction. The present study used figures taken from the Polish Electricity Statistics yearbooks for the years 1946 to 2007 [17].

The paper contains selected research results related to discovery of regularities in the development of the system and the development of the electrical power system model (SEE) from the point of view of safety. Efficiency indexes were proposed based on data for the period of 1946–2007 of the SEE in Poland, a model of the system development was developed, and changes in the efficiency indexes of the system were determined. Results concerning evaluative research of the development efficiency and analysis results of development models were also presented, including estimation of efficiency margin of the SEE system development.

The paper contains a new concept and some research results as regards creating initial population for Systematical Evolutionary Algorithms (SEA). First, different models of development of Electrical Power System (EPS) obtained a result of identification such as matrix th and model in state space ss, and model in the form artificial genetic code such as a specific information development model of EPS system. A method of interconnecting the EPS system development with the movement of roots on the complex variable plane s is presented also.

The paper contains results of research concerning the search for models of Polish electrical energy stock exchange development. The research was conducted using MATLAB environment, and such toolboxes as a System Identification Toolbox and Neural Network Toolbox. Static models of Polish electrical energy stock exchange development as well as a dynamic model allowing to obtain information concerning static models of development for predicting further states of development were presented. Moreover, knowledge maps containing information on the development of GEE (Electrical Energy Stock Exchange), which were obtained by means of designing proper artificial neural networks, were also presented.

In this paper a concept of evolution of a neural network in the state space is presented. This evolution may be considered as another dimension of automated discoveries. As a base for building a model well known Evans’ line method is used.