FG Thermische Energietechnik
Load forecasting is an essential part of the operational management of combined heat and electrical power units, since a reliable hour- and day-ahead estimation of their thermal and electrical load can significantly improve their technical and economic performance, as well as their reliability. Among different types of prediction techniques, data-driven machine learning methods appear to be more suitable for load estimation in operational systems, compared to the classical forward approach. Research so far has been concentrated mainly on the magnitude of buildings with single load types. It has only been extended to a limited degree on the level of a district heating network where several end users with different characteristics merge into one bigger scale heat consumer (city or group of communities). In this study, artificial neural networks are utilized, to develop a load prediction model for district heating networks. A segmented analytical multi-phase approach is employed, to gradually optimize the predictor by varying the characteristics of the input variables and the structure of the neural network. The comparison against the load prediction time series generated by a local communal energy supplier using a commercial software reveals that, although the latter is enhanced by manual human corrections, the optimized fully automatic predictors developed in the present study generate a more reliable load forecast.
In the last two decades, a rapid expansion of photovoltaic (PV) power plants of different sizes has taken place. Along with this, the interest from science and industry is growing, exploring the strengths and weaknesses of this technology as well as further developing the efficiency in its production and operation. For planning and operating of PV power plants, valid energy yield forecasts are desirable. These forecasts are also important to draw conclusions for the monitoring of future PV technologies. The analysis, evaluation and processing of meteorological and technical measurement datasets play an essential role.
In this article, high-resolution measurement data sets of a mobile, autarkic test system are analyzed firstly. The measured data are checked for plausibility and validity with the corresponding methods. After this observations and phenomena with meteorological cause are described. In a second step, a practicable procedure for the preparation of the measurement data is presented, in order to make it suitable for further calculations, e.g. identification of photovoltaic module parameters for energy yield calculations. The focus is particularly on the flexibility, adaptability and code performance of the processing procedure. Results, evaluations and outlooks on the methods used, measurement data and selected software packages are made.