Individualized Short-Term Electric Load Forecasting Using Data-Driven Meta-Heuristic Method Based on LSTM Network

Abstract

Short-term load forecasting is viewed as one promising technology for demand prediction under the most critical inputs for the promising arrangement of power plant units. Thus, it is imperative to present new incentive methods to motivate such power system operations for electricity management. This paper proposes an approach for short-term electric load forecasting using long short-term memory networks and an improved sine cosine algorithm called MetaREC. First, using long short-term memory networks for a special kind of recurrent neural network, the dispatching commands have the characteristics of storing and transmitting both long-term and short-term memories. Next, four important parameters are determined using the sine cosine algorithm base on a logistic chaos operator and multilevel modulation factor to overcome the inaccuracy of long short-term memory networks prediction, in terms of the manual selection of parameter values. Moreover, the performance of the MetaREC method outperforms others with regard to convergence accuracy and convergence speed on a variety of test functions. Finally, our analysis is extended to the scenario of the MetaREC_long short-term memory with back propagation neural network, long short-term memory networks with default parameters, long short-term memory networks with the conventional sine-cosine algorithm, and long short-term memory networks with whale optimization for power load forecasting on a real electric load dataset. Simulation results demonstrate that the multiple forecasts with MetaREC_long short-term memory can effectively incentivize the high accuracy and stability for short-term power load forecasting.

Interval Load Forecasting for Individual Households in the Presence of Electric Vehicle Charging

“…Short-term load forecasting has been investigated by Sun et al [8]: they proposed a framework based on LSTM and an enhanced sine cosine algorithm (SCA). The authors enhanced the performance of the SCA, a meta-heuristic method for optimization problems, by incorporating a chaos operator and multilevel modulation factors.…”

“…There have been extensive efforts to create predictive load forecasting models using machine learning (ML) with historical energy consumption data collected by smart meters or similar technologies, often combined with meteorological information [6,7]. In recent years, deep learning techniques, especially those based on Recurrent Neural Networks (RNNs) have been outperforming other techniques [8,9]. While these studies had great successes in terms of accuracy for a variety of use cases, they do not specifically address short-term forecasting for individual households in presence of EV charging [10] which introduces challenges due to variations of charging patterns.…”

Trust-Based Beacon Node Localization Algorithm for Underwater Networks by Exploiting Nature Inspired Meta-Heuristic Strategies

“…The connectivity of any ad hoc network is highly dependent on the mobility model it follows. As per the previous study mentioned in [41][42][43], the random way mobility model is widely used to simulate the performance of any mobile ad hoc network such as [44][45][46], fixing the source and sink nodes at the bottom and surface of the water, respectively, with coordinates (80, 90,100) and (10,20,30). To calculate the value of energy consumption, we use the 'Tx' Power 'Rx' Power and 0.007 W, respectively.…”

Prediction accuracy improvement of pressure pulsation signals of reversible pump‐turbine: A LSTM and VMD‐based optimization approach

“…LSTM networks exhibit exceptional memory and temporal modeling capabilities. 29 By adaptively learning and capturing long-term dependencies in time series data, the LSTM network effectively utilizes the features of pressure pulsation signals over time. This enables the model to learn and predict the future distribution of pressure pulsation signals while utilizing their temporal characteristics.…”

“…One popular type of recurrent neural network (RNN) model that has gained prominence in time series prediction is the long short‐term memory (LSTM) network. LSTM networks exhibit exceptional memory and temporal modeling capabilities 29 . By adaptively learning and capturing long‐term dependencies in time series data, the LSTM network effectively utilizes the features of pressure pulsation signals over time.…”