Load forecast of a university building for application in microgrid power flow optimization

Abstract

Microgrid is defined as a cluster of distributed generation sources, storages and loads that cooperate together in order to improve power supply reliability and overall power system stability. Short-term power production and load profile prediction is very important for power flow optimization in a microgrid, thus enhancing the management of distributed generation sources and storages in order to improve the microgrid reliability, as well as the economics of energy trade with electricity markets. However, short-term load prediction is a complex procedure, mainly because of the highly nonsmooth and nonlinear behaviour of the load time series. In this paper we develop and verify a neural-network-based short-term load profile prediction model. Neural network inputs are lagged load data, as well as meteorological and time data, while neural network output is load at the particular moment. Neural network training and validation is performed on load data recorded at University of Zagreb Faculty of Electrical Engineering and Computing, and on meteorological data obtained from Meteorological and Hydrological Service of Croatia, in period 2011-2013.

A Review on Optimal Generation Techniques used in Microgrids

“…Since a single bad prediction at the particular moment could spoil all other predictions after that moment. In order to be able to obtain more realistic information on load profile prediction, the prediction model should be extended with its stochastic description [7].…”

“…Input candidates in local network are lagged load, meteorological and time data. These candidates are chosen heuristically, but for the more realistic information input variable selection (IVS) analysis required [7].…”

“…For NN training (i.e. parameters tuning), a gradient-based Levenberg-Marquardt algorithm is used [7].…”

Campus and community micro grids integration of building integrated photovoltaic renewable energy sources: Case study of Split 3 area, Croatia - part A

“…This work contributes to the literature by being among the first to study electrical energy consumption and production with the purpose of potentially creating a roadmap towards a 100% RES powered district and university campus in Croatia. Related previous work on the demand side was conducted by University of Zagreb, Faculty of Electrical and Computer Engineering, with the goal of load forecasting for optimising building energy usage [2]. In this research work, an integrated approach of data acquisition on the supply and demand side was applied to case study communities in Split, Croatia with the results modelled in H2RES.…”

A New Approach to Detection of Systematic Errors in Secondary Substation Monitoring Equipment Based on Short Term Load Forecasting

“…The results obtained are compared with those from other works [ 8 , 9 ] with the aim of evaluating the validity of the proposed approach. In [ 10 , 11 ], environmental variables are also employed, whereas in [ 12 , 13 ] only the historical load consumption is considered without a detrimental impact on the accuracy. The latter is the strategy adopted in this paper.…”