Load Forecasting Based on LSTM Neural Network and Applicable to Loads of “Replacement of Coal with Electricity”

With the complete implementation of the “Replacement of Coal with Electricity” policy, electric loads borne by urban power systems have achieved explosive growth. The traditional load forecasting method based on “similar days” only applies to the power systems with stable load levels and fails to show adequate accuracy. Therefore, a novel load forecasting approach based on long short-term memory (LSTM) was proposed in this paper. The structure of LSTM and the procedure are introduced firstly. The following factors have been fully considered in this model: time-series characteristics of electric loads; weather, temperature, and wind force. In addition, an experimental verification was performed for “Replacement of Coal with Electricity” data. The accuracy of load forecasting was elevated from 83.2 to 95%. The results indicate that the model promptly and accurately reveals the load capacity of grid power systems in the real application, which has proved instrumental to early warning and emergency management of power system faults.

Three zone detection and distance relay co-ordination of power system protection

To secure the transmission lines against power system faults, the distance relays are mostly used. Distance relay has its own Resistance (R)–Reactance (X) characteristics. Co-ordination of different distance relays is necessary for the fast operation of circuit breaker. Various distance relays which are being tripped with respect to circuit breakers which are attached at individual buses faraway from each other. These relays will be operated with respect to the distance between the occurred fault and relay location. In this paper, detection of three zones using relay characteristics, co-ordination of distance relays and circuit breakers are shown with the faults placed at different locations of an IEEE Nine bus system using MATLAB/Simulink GUI environment. A comparison also made between the relays performance and circuit breaker tripping operation with respect to severe faults at different locations on IEEE Nine bus system.

Fuzzified time-frequency method for identification and localization of power system faults

In this work, different types of power system faults at various distances have been identified using a novel approach based on Discrete S-Transform clubbed with a Fuzzy decision box. The area under the maximum values of the dilated Gaussian windows in the time-frequency domain has been used as the critical input values to the fuzzy machine. In this work, IEEE-9 and IEEE-14 bus systems have been considered as the test systems for validating the proposed methodology for identification and localization of Power System Faults. The proposed algorithm can identify different power system faults like Asymmetrical Phase Faults, Asymmetrical Ground Faults, and Symmetrical Phase faults, occurring at 20% to 80% of the transmission line. The study reveals that the variation in distance and type of fault creates a change in time-frequency magnitude in a unique pattern. The method can identify and locate the faulted bus with high accuracy in comparison to SVM.