User-Based Load Visualization of Categorical Forecasted Smart Meter Data Using LSTM Network

Abstract

Electrical load forecasting is an essential feature in power systems planning, operation and control. The non-linearity and non-stationary nature of the data, however, poses a challenge in terms of accuracy. This article explores a deep learning technique, a long short-term memory recurrent neural network-based framework to tackle this tricky issue. The proposed machine learning model framework is tested on real time residential smart meter data showing promising results. A web application has also been developed to allow consumers to have access to greater levels of information and facilitate decision-making at their end. The performance of the proposed model is also comprehensively compared to other methods in the field of load forecasting showing more accurate results for the function of forecasting of load on short term basis.

Forecasting Stock Market Volume Price Using Sentimental and Technical Analysis

“…The prediction can be performed using machine learning models. LSTM is special kind of RNN that has the capability to learn the long dependencies (Hochreiter, & Schmidhuber, 1997;kumar, toorang & bali 2020;bali, kumar, & gangwar, 2020). In a LSTM a cell state is added along with the hidden state to store the long term memory.…”

Blockchain Application Design and Algorithms for Traceability in Pharmaceutical Supply Chain

“…Sometimes healthcare professionals do not have complete access to patient's data, which hinders the succeeding process of diagnosis and therapy. Kumar, Toorang, and Bali (2020) developed web applications for better data visibility and trend forecasting. These applications further enable users to obtain a higher level of information and make better decisions.…”