![]() ![]() Considering the stochastic nature of blackouts, their performance was found to be fair in short-term blackout predictions of the test site’s weak grid using limited input data from the point of coupling of the user. Furthermore, the efficacy analysis of the short-term blackout prediction of the formulated RF, ASD, and RF-ASD regression and classification algorithms was compared. The model was composed of an adaptive similar day (ASD) module that predicts 15 minutes ahead from a sliding window lookup table spanning 2 weeks prior to the prediction target day, after which ASD prediction was fused with RF prediction, giving a final optimised RF-ASD blackout prediction model. Input data sampled at a 15-minute interval included day of the month, weekday, hour, supply voltage, utility line frequency, and previous days’ blackout profiles. A very short-term power outage prediction model framework based on a hybrid random forest (RF) algorithm was developed using open-source Python machine learning libraries and using a dataset generated from the pilot project’s experimental microgrid. A pilot project was implemented in Arusha-Tanzania it mainly comprised of a PV-inverter and a lead-acid battery bank connected to the local electricity utility company, Tanzania Electric Supply Company Limited (TANESCO). This paper proposes an approach for very short-term blackout forecast in grid-tied PV systems operating in low reliability weak electric grids of emerging countries. Sub-Saharan emerging countries experience electrical shortages resulting in power rationing, which ends up hampering economic activities. Unfortunately, there was still a minor power unbalance, due to power plant trippings, that resulted in a slow decrease of the frequency and in the activation of more load shedding which is spaced at 0.1 Hz intervals. At 49.1 Hz, the first set of automatic load shedding of domestic and industrial loads took place changing the frequency rate of decrease to-0.05 Hz/s: it has been assessed that the load shed at this stage plus 3500 MW of pumping load was enough to allow a stabilization of the frequency. During this phase, all the pumps were automatically disconnected. The trip (3:25.35) of the double circuit RondissoneAlbertville and the separation of the North-West interconnection caused a frequency decay, with a rate of decrease of about 1 Hz/s until f=49.1 Hz. At 3:25.33, corresponding to the trip of the French line Albertville-La Coche-La Praz, the frequency starts decreasing (about0.5 Hz/s) causing the disconnection of about 880 MW of pumps. 4 shows the frequency transient until the blackout took place. Total import (Greece DC link is not considered). Some issues related to the operation of the Italian defense plan and to the restoration process are also discussed, along with some countermeasures already in place The focus is put on some issues that have been identified as the main causes that resulted in the separation of the Italian system and in the blackout. This paper provides a short description of the system operation right before the incident, and reports the main events that led to the blackout. The incident affected the whole peninsula (about 45 million people) full restoration took almost 19 hours. ![]() Unfortunately, the automatic load shedding procedure and the regulating action of generators were not able to avoid the blackout. Due to the large power unbalance following the separation, the Italian electrical system and a small part of the Swiss system, suffered an under-frequency transient. The interconnecting lines were already heavily loaded and the operator action was not sufficient in controlling the situation. During the night of September 28th, 2003 the European interconnected grid faced a series of outages, which started with line flashovers to trees and line trips on the Swiss electricity transmission grids, close to the Italian border, and ended with the separation of the entire Italian system from the UCTE (Union for the Co-ordination of the Transmission of Electricity) grid. ![]()
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |