Short-Term Load-Forecasting Method Based on Wavelet Decomposition With Second-Order Gray Neural Network Model Combined With ADF Test

Short-term electricity load forecasting is one of the most important operations in electricity markets. The success in the operations of electricity market participants partially depends on the accuracy of load forecasts. In this paper, three grey prediction models, which are seasonal grey model (SGM), multivariable grey model (GM (1,N)) and genetic algorithm based multivariable grey model (GAGM (1,N)), are proposed for short-term load forecasting problem in day-ahead market. The effectiveness of these models is illustrated with two real-world data sets. Numerical results show that the genetic algorithm based multivariable grey model (GAGM (1,N)) is the most efficient grey forecasting model through its better forecast accuracy.

In order to solve the problems of insufficient accuracy of long-term power load forecasting and poor applicability of the model, this paper considers the coupling of a number of macro indicators, such as regional economic development and social development indicators, with the time series data of regional power load. BP neural network and Autoregressive integrated moving average model (ARIMA) are used to integrate and improve the forecasting model, so as to improve the trend forecasting ability of annual load forecasting model. The non parametric function method is used to forecast the periodic load data in the monthly load data, the annual load forecast is combined with the monthly load forecast to improve the overall forecasting accuracy of the model. Finally, through the comparison of grey prediction and other models and the verification of MAPE error analysis method, the prediction accuracy of the model method considering the combination of data periodicity and trend is significantly improved, which is suitable for the long-term prediction of regional power load.

A short-term load forecasting model based on mixup and transfer learning

Short-term electricity load forecasting provides a basis for day-ahead energy scheduling. To improve the accuracy of short-term electricity load forecasts and deeply explore the temporal characteristics of load sequences, a method is proposed to extract predictable components of load sequences based on the secretary bird optimization algorithm (SBOA)-optimized successive variational mode decomposition (SVMD). This method decomposes the electricity load sequence into multiple subsequences under different time series. The combined forecasting architecture of the temporal convolutional network (TCN) and the bidirectional long short-term memory network (BiLSTM) is introduced to mine the temporal characteristics of each load component, resulting in short-term load forecasting outcomes. A case study is conducted using the annual electricity load data for the year 2018 from a specific region in Belgium. The experimental results show that the mean absolute error (MAE) of the TCN–BiLSTM model is reduced by 47.8%, 32.8%, and 11.5%, respectively, compared to other models. The root mean square error (RMSE) is reduced by 42.9%, 39.2%, and 11.3%, respectively, and the average goodness of fit R2 is reduced by 9.81%.

In this paper, an artificial neural network (ANN) based methodology is proposed to forecast electricity load and price. The performance of an ANN forecast model depends on appropriate input parameters. Parameter tuning of ANN is very important to increase the accuracy of electricity price and load prediction. This is done using mutual information and decision tree. After selecting best features for forecasting, these features are given to forecasting engine working on principles of recurrent neural network (RNN). For simulations, dataset is taken from national electricity market (NEM), Australia. Results show that the methodology has increased the accuracy of electricity load and price forecast. Whereas, the error rate of forecasting is lower than the other models for electricity load and price.

Accurate load forecasting is of great significance to ensure the safety and stable operation of the smart grid's power system. In this paper, we study this problem of making an accurate short-term load prediction for an electricity system. Due to its inherent nonlinear properties, our proposed solution is based on the nonlinear model, and the power load sequence is also random, non-stationary and periodic. The original historical load sequence is decomposed into a series of modal functions by using the variational mode decomposition (VMD) technique, and a load forecasting model is established for each modal function. A load forecasting model combining the beetle swarm optimisation(BSO) algorithm and extreme learning machine(ELM) is put forward. The BSO finds the optimal input weight and hidden layer threshold in the ELM network. In the end, the VMD-BSO-ELM prediction model is established. The experimental results demonstrate that the proposed method is better than other individual methods and their combinations.

Day-ahead load and wind power forecasts provide useful information for operational decision making, but they are imperfect and forecast errors must be offset with operational reserves and balancing of (real time) energy. Procurement of these reserves is of great operational and financial importance in integrating large-scale wind power. We present a probabilistic method to determine net load forecast uncertainty for day-ahead wind and load forecasts. Our analysis uses data from two different electric grids in the US with similar levels of installed wind capacity but with large differences in wind and load forecast accuracy, due to geographic characteristics. We demonstrate that the day-ahead capacity requirements can be computed based on forecasts of wind and load. For 95% day-ahead reliability, this required capacity ranges from 2100 to 5700 MW for ERCOT, and 1900 to 4500 MW for MISO (with 10 GW of installed wind capacity), depending on the wind and load forecast values. We also show that for each MW of additional wind power capacity for ERCOT, 0.16–0.30 MW of dispatchable capacity will be used to compensate for wind uncertainty based on day-ahead forecasts. For MISO (with its more accurate forecasts), the requirement is 0.07–0.13 MW of dispatchable capacity for each MW of additional wind capacity.

Medium-and-long-term load forecasting plays an important role in energy policy implementation and electric department investment decision. Aiming to improve the robustness and accuracy of annual electric load forecasting, a robust weighted combination load forecasting method based on forecast model filtering and adaptive variable weight determination is proposed. Similar years of selection is carried out based on the similarity between the history year and the forecast year. The forecast models are filtered to select the better ones according to their comprehensive validity degrees. To determine the adaptive variable weight of the selected forecast models, the disturbance variable is introduced into Immune Algorithm-Particle Swarm Optimization (IA-PSO) and the adaptive adjustable strategy of particle search speed is established. Based on the forecast model weight determined by improved IA-PSO, the weighted combination forecast of annual electric load is obtained. The given case study illustrates the correctness and feasibility of the proposed method.

Accurate load forecasting can bring economic benefits and scheduling optimization. The complexity and uncertainty arising from the coupling of different energy sources in integrated energy systems pose challenges for simultaneously predicting multiple target load sequences. Existing data-driven methods for load forecasting in integrated energy systems use multi-task learning to address these challenges. When determining the input data for multi-task learning, existing research primarily relies on data correlation analysis and considers the influence of external environmental factors in terms of feature engineering. However, such feature engineering methods lack the utilization of the characteristics of multi-target sequences. In leveraging the characteristics of multi-target sequences, language generation models trained on textual logic structures and other sequence features can generate synthetic data that can even be applied to self-training to improve model performance. This provides an idea for feature engineering in data-driven time-series forecasting models. However, because time-series data are different from textual data, existing transformer-based language generation models cannot be directly applied to generating time-series data. In order to consider the characteristics of multi-target load sequences in integrated energy system load forecasting, this paper proposed a generative tractive network (GTN) model. By selectively utilizing appropriate autoregressive feature data for temporal data, this model facilitates feature mining from time-series data. This model is capable of analyzing temporal data variations, generating novel synthetic time-series data that align with the intrinsic temporal patterns of the original sequences. Moreover, the model can generate synthetic samples that closely mimic the variations in the original time series. Subsequently, through the integration of the GTN and autoregressive feature data, various prediction models are employed in case studies to affirm the effectiveness of the proposed methodology.

This paper first introduces modeling theory of GM (1,1) grey equidimensional filling vacancies, and establishes GM (1,1) grey forecasting model of equidimensional filling vacancies by using power demand load of Shan Dong Province from 2004 to 2011, then forecasts power load demand of Shan Dong Province in 2012 and 2013 for two years. When compared with the actual electricity load, that grey forecasting model of equidimensional idling vacancies has high accuracy in long-term power load forecasting.

The accuracy of power load forecasting is sensitive to various characteristic factors. For the massive historical load data, how to mine the correlation between different attributes in the characteristic data set is the key to improve the accuracy of load forecasting. In this paper, a load forecasting method based on Bi-LSTM network considering data feature analysis is proposed. Firstly, the attribute correlation feature analysis of massive historical load data is realized by using random forest algorithm, and the features with strong correlation with load are selected as the input of the model; Secondly, Bi-LSTM network with good data fitting accuracy is used for load forecasting modeling. Finally, the actual load data of a city is used for simulation analysis. The simulation results show that this method has more advantages in accuracy than traditional forecasting methods, which verifies the effectiveness and practicability of this method.KeywordsMultidimensional characteristicsLoad forecastingRandom forestBi-LSTMFeature selection

To improve the accuracy of load forecasting, the temperature factor was introduced into the load forecasting in this paper. This paper analyzed the characteristics of power load variation, and researched the rule of the load with the temperature change. Based on the linear regression analysis, the mathematical model of load forecasting was presented with considering the temperature effect, and the steps of load forecasting were given. Used MATLAB, the temperature regression coefficient was calculated. Using the load forecasting model, the full-day load forecasting and time-sharing load forecasting were carried out. By comparing and analyzing the forecast error, the results showed that the error of time-sharing load forecasting method was small in this paper. The forecasting method is an effective method to improve the accuracy of load forecasting.

In this paper, a short-term power load forecasting model based on feature similarity was proposed. The model can comprehensively consider the short-term load forecasting under the condition of multiple factors, such as meteorological information, holiday/workday information and other factors in a unified framework. Different values of the same characteristic have great influence on load forecasting. Therefore, hierarchical clustering algorithm is used to analyse the value of each feature dimension. Feature distance is used as feature mapping value to establish feature mapping relation table. Because different factors have different weights for load forecasting, a weighted feature similarity measurement strategy is designed. Taking the minimum residual sum of squares as the optimization objective, particle swarm optimization algorithm is used to solve the optimal characteristic weight. The validity of the model and the accuracy of load forecasting are verified by comparing the numerical simulation with the existing models.

Based on the features of both distributed artificial intelligence and load forecasting techniques, a distributed problem-solving system for short-term load forecasting is proposed. Such a distributed paradigm is a multi-agent system, each processing agent of which can compute autonomously and cooperate with other agents to reason an accurate and satisfactory solution for load forecasting. The designed load forecasting system solves problems using three basic moduli: blackboard module, knowledge sources, and control mechanism. In addition, to achieve a high degree of accuracy in load forecasting, the techniques are embedded in the domain knowledge source. The system was implemented by an expert system and tested. It was found that the developed distributed system is a valuable tool to system operators for short-term load forecasting. >

Electricity load forecasting and feature extraction in smart grid using neural networks