Operations and planning of power systems significantly rely on accurate load forecasts specifically after the
penetration of renewable energy resources. However, temporal relationships in load data are challenging to capture using
traditional statistical and machine learning methods. The application of recurrent neural networks, and more specifically
long short-term memory (LSTM) networks, to the modeling of sequence data with extensive temporal relationships has
yielded promising results. In this paper, we present a model for predicting future loads using a recurrent neural network
with long short-term memory.Effective demand response and distributed renewable energy sources can be better integrated
with this technology, which is crucial for the smart grid's stability and power demand estimation. However, it is
difficult to perform energy prediction with high accuracy because of influencing elements like climate, society, and
seasonality. We evaluate the accuracy of the model by using demand data collected from the German utility. The proposed
LSTM-RNN model exhibits significantly lower error rates in 1-24 hours and yearly load forecasts than conventional machine
learning techniques. In addition, the model is able to make accurate predictions despite receiving inadequate or noisy
inputs. Our findings imply that LSTM-RNN could be used in practice for effective load forecasting.
Electrical energy capacity mismatch and immense power shortages due to energy deficit in the power system keep on increasing because of inadequate power capacity, insufficient investment, demand growth, and the rise in living standards. To maintain a balanced relationship between production and consumption, several load shedding schemes have been implemented for load management in the last few years, but their inconsistency poses a challenge. This research work will apply the fuzzy logic algorithm (FLA) and optimise the existing conventional power systems with and without dispersed generators (DGs). In critical circumstances, the algorithm will find node sets or desired locations where limits are violated and system operators may request the utility or industrial customer to shed a required amount of load by operating distributed generators to maintain its system integrity. The performance and suitability of the proposed scheme are demonstrated and proved by testing on a standard 33-bus radial distribution system in MATLAB Simulink having an objective function of minimising its total load curtailed and reducing power system losses by improving its system stability.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.