Optimal BRA based electric demand prediction strategy considering instance‐based learning of the forecast factors

Abstract

With the grid's evolution, the end-users demand becomes more vital for demand side management (DSM). Accurate load forecasting (LF) is critical for power system planning and using advanced demand response (DR) strategies.To design efficient and precise LF, information about various factors that influence end-users demand is required. In this paper, the impact of different factors on electrical demand and capacity of climatic factors existence and their variation is discussed and analysed. The Pearson correlation coefficient (PCC) is utilized to express the degree of electric demand correlation with metrological and calendar factors. Then, the optimal-Bayesian regularization algorithm (BRA) based on ANN for LF is presented. The effect of the number of neurons in hidden layers on output is observed to select the most appropriate option. Additionally, heating degree days (HDDs) and cooling degree days (CDDs) indices are investigated to consider the impact of air conditioners' (ACs) loads in different seasons. Case studies on data from Dallas, Texas, USA, are used to

The progress, impact analysis, challenges and new perceptions for electric power and energy sectors in the light of the COVID-19 pandemic

“…Electrical demand requirements vary depending upon the temperature variations above or below the base temperature. Several methods have been explored to observe degree days in literature, whereas the degree hour or hourly method is the most effective method for these indices’ computation [127] . Daily values of the CDDs can be given by (1) , (2) as: where and are the base temperature and daily hourly temperature, respectively.…”

Artificial Intelligence Enabled Demand Response: Prospects and Challenges in Smart Grid Environment

“…In addition, [18], explored the use of smart meter and its data analysis for DR application while [19], [20] examined AI based load prediction, concentrating mostly on deep learning and artificial neural networks (ANNs) [21]. aggregation of thermal inertia, particularly from district heating networks is emphasized in [22] and [23] highlights the emerging concept of integrated demand response, which integrates multiple energy types and vectors (including electricity, natural gas, and heat).…”

An Experimental Study on Speech Enhancement Based on a Combination of Wavelets and Deep Learning

“…The feedforward deep neural network, or multi-layer perceptron (MLP) with more than three hidden layers, is a typical example of a deep learning algorithm. The architecture of a MLP organized with multiple units, inputs, outputs, and weights can be represented graphically [44], as shown in Figure 3. Each layer performs a function from the inputs (or the outputs of the previous layer) to the outputs, using activation functions defined in each unit and the value of the weight of the connections.…”