Research on short-term power load forecasting based on Elman neural network with Genetic Algorithm

Short-term power load forecasting based on Elman neural network with particle swarm optimization

The Sixth International Symposium on Neural Networks (ISNN 2009)

Neural network methods are widely used in the prediction of chaos time series due to their versatility and small computation amount. In order to improve the prediction accuracy and real-time of all kinds of information in the short-term electricity load time series, four neural network methods with the ideal powerful capacity in non-linear modeling and predicting, such as back-propagation neural network (BPNN), ELMAN neural network, fuzzy neural network (FNN) and wavelet neural network (WNN), are used to realize the short-term electricity load forecast. Simulation experiments results and performance comparison analysis show the effectiveness of the proposed four time series prediction methods.

In order to estimate daily solar radiation, this paper proposes Elman (ENN) and Feed forward backpropagation (FNN) neural networks. The time series data from the location of Kenitra City, Morocco is used to train the created models. Fletcher-Powell Conjugate Gradient (CGF), Scaled Conjugate Gradient (SCG), Resilient Backpropagation (RB), Conjugate gradient with Powell-Beale restarts (CGB), Levenberg-Marquardt (LM), Polak-Ribi´ere Conjugate Gradient (CGP), and One Step Secant (OSS) are also used with both, the ENN and FNN to identify the best and effective training function for each. The models with various training algorithms are tested by using evaluation metrics root mean square error (RMSE), mean square error (MSE) and mean absolute error (MAE). The study showed that the Elman Neural Network had an excellent daily solar radiation prediction for Kenitra city. Good results have been obtained with Levenberg-Marquardt algorithm.

Accurate estimation of the state of charge (SOC) of lithium batteries is the research hotspot. As a dynamic recurrent neural network, Elman neural network has a simple structure and can adapt to time-varying characteristics, which have led to its widespread application in the field of SOC prediction. However, the simple network structure can also cause problems such as low learning efficiency, easy to fall into local extremes, and difficulty converge to the optimal weight solution. This paper proposes to combine the whale optimization algorithm (WOA) with genetic algorithm (GA) to optimize the weights and thresholds of the Elman neural network, thus improving the learning speed and prediction accuracy. We select three parameters of current, voltage and temperature as system variables, and simulate the experimental data. The experimental results show that, compared with the traditional Elman neural network and the Elman neural network optimized only by genetic algorithm, the hybrid algorithm performs best. The number of network iterations is small, and the average error drops below 1%.

Gross domestic product (GDP) can well reflect the development of the economy, and predicting GDP can help better grasp the future economic trends. In this article, three different neural network models, the genetic algorithm – back-propagation neural network model, the particle swarm optimization (PSO) – Elman neural network (Elman NN) model, and the bat algorithm – long short-term memory model, were analyzed based on neural networks. The GDP data of Sichuan province from 1992 to 2020 were collected to compare the performance of the three models in predicting GDP. It was found that the mean absolute percentage error values of the three models were 0.0578, 0.0236, and 0.0654, respectively; the root-mean-square error values were 0.0287, 0.0166, and 0.0465, respectively; and the PSO-Elman NN model had the best performance in GDP prediction. The experimental results demonstrate that neural networks were reliable in predicting GDP and can be used for further applications in practice.

Currently, traditional electricity consumers are now shifting to a new role of prosumers since more integration of renewable energy to demand side. Accurate short-term load demand forecasting is significant to safe, stable, and reliable operation of a renewable energy-dominated power system. In this paper, a short-term load forecasting model based on a bidirectional long short-term memory network (Bi-LSTM) using kernel transfer operator is proposed to achieve short-term load demand forecasting. To consider the influence of seasonality, holiday effects and weather on load demand forecasting, and simultaneously to improve the accuracy and performance of the forecasting model, this paper implements the dimensionality reduction of the input data by introducing an improved kernel transfer operator based on the Perron-Frobenius method. On this basis, a Bayesian Bi-LSTM for short-term load demand forecasting is formulated to obtain the probability prediction interval of load demand. To verify the validity of the proposed method, the actual historical load demand in a certain region in China was used for model training and verification. The forecasting results are compared with several conventional load demand methods using probability prediction technics. Simulation analysis shows that the proposed method can effectively reflect the short-term uncertainty of load demand, and is superior to the conventional methods in terms of forecasting accuracy and computational performance.

The Back Propagation (BP) neural network genetic algorithm was used to identify alphabet, and the new algorithm combine the advantages of both genetic algorithm and the BP neural network. Genetic learning algorithm was used for the global optimization and BP training algorithm to accurately optimize the neural network weights and training the neural network to learn letter recognition algorithm. Add-noise alphabet of MATLAB simulation results show that the new network error recognition rate reduced by 10% compared to BP neural network and the recognition speed is also faster than the traditional BP neural network with accuracy and fast convergence.

Closely connected to human carbon emissions, global climate change is affecting regional economic and social development, natural ecological environment, food security, water supply, and many other social aspects. In a word, climate change has become a vital issue of general concern in the current society. In this study, the carbon emission data of Chinese provinces in 1999–2019 are collected and analyzed, so as to identify the carbon emission of direct consumption per 10,000 residents in each province (including each municipal city and autonomous region) and the entire nation based on population data. The Arc Geographic Information Science Engine (ArcGIS Engine) and C#.NET platform are employed to call the MATLAB neural network toolbox. A model is selected and embedded in the prediction system to develop the entire system. This study demonstrates that the carbon emissions per resident in Northern China are significantly higher than those in Southern China, with the rate of carbon emissions continuing to increase over time. Compared with other models, the Elman neural network has a higher carbon emission prediction accuracy, but with more minor errors. For instance, its accuracy and prediction performance are improved by 55.93% and 19.48%, respectively, compared with the Backpropagation Neural Network (BPNN). The prediction results show that China is expected to reach its peak carbon emission in around 2025–2030. The above results are acquired based on the concept of carbon emissions and neural network model theories, supported by GIS component technology and intelligent methods. The feasibility of BPNN, Radial Basis Function (RBF) and Elman neural network models for predicting residential carbon emissions is analyzed. This study also designs a comprehensive, integrated and extensible visual intelligent platform, which is easy to implement and stable in operation. The trend and characteristics of carbon emission changes from 2027 to 2032 are explored and predicted based on the data about direct carbon emissions of Chinese provincial residents from 1999 to 2019, purposed to provide a scientific basis for the control and planning of carbon emissions.

There is a function of dynamic mapping when processing non-linear complex data with Elman neural networks. Because Elman neural network inherits the feature of back-propagation neural network to some extent, it has many defects; for example, it is easy to fall into local minimum, the fixed learning rate, the uncertain number of hidden layer neuron and so on. It affects the processing accuracy. So we optimize the weights, thresholds and numbers of hidden layer neurons of Elman networks by genetic algorithm. It improves training speed and generalization ability of Elman neural networks to get the optimal algorithm model. It has been proved by instance analysis that new algorithm was superior to the traditional model in terms of convergence rate, predicted value error, number of trainings conducted successfully, etc. It indicates the effect of the new algorithm and deserves further popularization.

Accurate short-term electrical load forecasting is crucial for the stable operation of power systems. Given the nonlinear, periodic, and rapidly changing characteristics of short-term power load forecasts, this paper introduces a novel forecasting method employing an Extreme Learning Machine (ELM) enhanced by an improved Dwarf Mongoose Optimization Algorithm (Local escape Dwarf Mongoose Optimization Algorithm, LDMOA). This method addresses the significant prediction errors of conventional ELM models and enhances prediction accuracy. The enhancements to the Dwarf Mongoose Optimization Algorithm include three key modifications: initially, a dynamic backward learning strategy is integrated at the early stages of the algorithm to augment its global search capabilities. Subsequently, a cosine algorithm is employed to locate new food sources, thereby expanding the search scope and avoiding local optima. Lastly, a “madness factor” is added when identifying new sleeping burrows to further widen the search area and effectively circumvent local optima. Comparative analyses using benchmark functions demonstrate the improved algorithm’s superior convergence and stability. In this study, the LDMOA algorithm optimizes the weights and thresholds of the ELM to establish the LDMOA-ELM prediction model. Experimental forecasts utilizing data from China’s 2016 “The Electrician Mathematical Contest in Modeling” demonstrate that the LDMOA-ELM model significantly outperforms the original ELM model in terms of prediction error and accuracy.

Tool wear conditions monitoring is an important mechanical processing system that can improve the processing quality of wood plastic composite furniture and reduce industrial energy consumption. An appropriate signal, feature extraction method, and model establishment method can effectively improve the accuracy of tool wear monitoring. In this work, an effective method based on discrete wavelet transformation (DWT) and genetic algorithm (GA) – back propagation (BP) neural network was proposed to monitor the tool wear conditions. The spindle power signals under different spindle speeds, depths of milling, and tool wear conditions were collected by power sensors connected to the machine tool control box. Based on the feature extraction method, the approximate coefficients of spindle power signal were extracted by DWT. Then, the extracted approximate coefficients, spindle speeds, depths of milling, and tool wear conditions were taken as samples to train the monitoring model. Threshold and weight of BP neural network were optimized by GA, and the accuracy of monitoring model established by the GA – BP neural network can reach 100%. Thus, the proposed monitoring method can accurately monitor tool wear conditions with different milling parameters, which can achieve the purpose of improving the processing quality of wood plastic composite furniture and reducing energy consumption.

Short-term load forecasting in power system is necessary for management and control of power system. A new method for short-term load forecasting was presented based on neural networks optimized by genetic algorithm (GA) is proposed in this paper, short-term load forecasting model for power system was setup as sample sets for Elman neural network (Elman NN), with GA's optimizing and Elman NN's dynamic feature, the higher forecasting pricision was realized and the simulation indicates the method is feasible and effective.

In the distributed load frequency control (DLFC) scheme, the compromised areas by attackers may endanger the stable and reliable operation of the entire power system. A credibility‐based secure DLFC strategy is in this work proposed to sustain the stable operation of the power system under false data injection attacks. In this secure DLFC method, the gradient‐variation‐based credibility metrics are defined to detect potential attacked measurements. Then, the communication isolation decisions are made based on the adaptive thresholds. To compensate the impact of the communication isolation of misbehaving areas, predictions of future measurements by using the average gradient variation of stored healthy data are feeded back to the area controller. Simulation results of a four‐area power system show the proposed secure DLFC can identify and cut off the communication of the misbehaving areas and still maintain the stability of the power system.

This paper presents an approach of position sensorless control for permanent magnet linear synchronous motors (PMLSM) based on Elman neural network. The Elman neural network observer can be considered as a special kind of feed-forward neural network with additional memory neurons and local feedback. Because of the context neurons and local recurrent connections between the context layer and the hidden layer, it facilitates the nonlinear states estimation for the sensorless control of PMLSM. The Elman neural network is trained both off-line and on-line. In the off-line training process with the training data, the connective weights of the Elman neural network are trained by the Levenberg-Marquardt algorithm, while on-line learning, the connective weights of the Elman neural network are trained using supervised gradient decent method. The effectiveness of the proposed observer is confirmed by the digital simulations results.