Stanislav Misak

Off-grid power systems

This paper deals with problems of off-grid power systems, in particular off-grid power systems with wind power plants and photovoltaic systems. The paper describes a hybrid off-grid power system built at the VSB-TUO campus. This system comprises a wind power plant, a photovoltaic system, a battery bank, a control unit and a streetlight as a connected appliance. The text also discusses possible applications of off-grid power systems.

Genetically Evolved Fuzzy Predictor for Photovoltaic Power Output Estimation

Fuzzy sets and fuzzy logic can be used for efficient data mining, classification, and value prediction. We propose a genetically evolved fuzzy predictor to estimate the output of a Photovoltaic Power Plant. Photovoltaic Power Plants (PVPPs) are classified as power energy sources with unstable supply of electrical energy. It is necessary to back up power energy from PVPPs for stable electric network operation. An optimal value of back up power can be set with reliable prediction models and significantly contribute to the robustness of the electric network and therefore help in the building of intelligent power grids.

Supervised learning of photovoltaic power plant output prediction models

This article presents an application of evolutionary fuzzy rules to the modeling and prediction of power output of a real-world Photovoltaic Power Plant (PVPP). The method is compared to artificial neural networks and support vector regression that were also used to build predictors in order to analyse a time-series like data describing the production of the PVPP. The models of the PVPP are created using different supervised machine learning methods in order to forecast the short-term output of the power plant and compare the accuracy of the prediction.

Testing of a Covered Conductor’s Fault Detectors

The majority of medium-voltage overhead lines are currently operated with AlFe conductors which have a simple construction and which rank among the cheapest versions of overhead lines from the point of view of initial investments. These overhead lines can be susceptible, however, to faults primarily in mountain and wooded areas, with an ensuing decrease in safety and operations reliability, as well as with limitations to the electric power supply. This draws attention to outdoor overhead lines with covered conductors, which are relied upon for use for connecting “defined” systems (SMART GRIDS) with an external electric power system. These conductors, with mostly XLPE and PE basic insulation, are able to resist both mechanical and electric strain caused by falling trees or branches and consequently their total number of faults is significantly lower. Massive usage of overhead lines with covered conductors is currently contradicted by prevailing difficulties in detecting faults. This article describes the possibility of detecting covered conductor faults and verifying the methodology under both laboratory and real conditions.

Irradiance prediction using Echo State Queueing Networks and Differential polynomial Neural Networks

This paper investigates the estimation of a real time-series benchmark: the solar irradiance forcasting. The global solar irradiance is an important variable in the production of renewable energy sources. These variable is very unstable and hard to be predicted. For the prediction, we use two new models for time-series modeling: Echo State Queueing Networks and Differential polynomial Neural Networks. Both tools have been proven to be efficient for forecasting and time-series modeling. We compare their performances for this particular data set.

Optimal design of neural tree for solar power prediction

Today renewable energy sources are integral part of energy mix in most of countries in the world. Carbon reduction issues and other ecological activity provide a wide possibility to progressive increase of installed capacity of renewable energy sources. Huge distribution of instable renewable energy sources like wind and photovoltaic plants brings new tasks in power system control and power system reliability. Prediction of power production is one of the ways to mitigate negative impact of operation of instable energy sources. This work presents application of a neural tree method from the group of soft computing method for renewable energy prediction. In this work we focus on photovoltaic power plant production prediction.

Evolutionary prediction of photovoltaic power plant energy production

This paper presents an application of genetic programming to the evolution of fuzzy predictors based on fuzzy information retrieval. The fuzzy predictors are used to estimate the output of a Photovoltaic Power Plant (PVPP). The PVPPs are energy sources with an unstable production of electrical energy. It is necessary to back up the energy produced by the PVPPs for stable electric network operations. An optimal value of backup power can be set with advanced prediction models that can contribute to the robustness of the electric network within the framework of an intelligent power grid. This work extends previous research on evolutionary design of fuzzy PVPP output predictors by the evaluation of the method on a larger data set describing the operations of a real PVPP.

Power quality dependence on connected appliances in an Off-Grid system

Power quality is one of the most important subjects in the field of power engineering. Especially in the Off-Grid systems, isolated networks, the power quality (PQ) is highly observed aspect. The fundamental Off-Grid feature can be intended an ability to operate regardless external power system, operation with an equal balance of energy production and consumption and as well as the ability of energy storage and energy conversion, mainly from renewable sources. This paper describes the relations between PQ and appliances connected into the Off-Grid system. The measurement and analysis are performed by the Off-Grid monitoring system and PQ analyser. Results of analysis will lead to consideration of how to maintain the power quality within desired range. The high PQ level is required in power systems during steady-state conditions as well as during non-stationery situations (i.e. interconnection of various appliances) to ensure the long lifespan af electrical equipment.

Artificially evolved soft computing models for photovoltaic power plant output estimation

Renewable energy sources are becoming a significant part of todays energy mix. The unstable production of many renewable energy sources including photovoltaic and wind power plants puts increased demands on power transmission systems and on the power grid as a whole. Soft computing methods can contribute to the prediction of electric energy production of renewable resources and therefore to the reliability of the power transmission networks. This work compares two soft computing methods that utilize genetic programming to evolve predictors of a selected renewable energy resource that meets the real world criterion of high output variance and relatively large installed power (in context of the power distribution system of the Czech Republic).

Integrating renewable energy sources using a smart household system

The energy independence, security and reliability of operating energy distribution systems, along with the use of renewable energy sources (RES), are the most important topics of energy-related research and development in recent years.