Load Prediction Method Research Articles

A bottom-up approach for community load prediction based on multi-agent model

Accurate prediction of community load is a prerequisite for community-scale demand matching and energy management. However, community-scale load prediction methods are challenging in characterizing complex energy-use scenarios caused by different building types and complicated occupant behaviors. The occupant behavior is the primary source of discrepancy between the predicted and realistic building performance, and this discrepancy will further widen on the community scale. This paper established the community occupant agent model (COAM) to generate occupancy data. The model delineates the agent system boundary from the perspective of complex adaptive systems (CAS). Anylogic was used to randomize and represent the decision behavior of community occupants. The bottom-up community building energy modeling (CBEM) workflow was applied to the case community of Xi'an (China). The measured and simulated values of the community building occupancy were compared, indicating the model's ability to reflect the interactions between single occupants and community building. The case community heating loads under different heating patterns were analyzed, and the workflow performance was evaluated. The proposed method might guide the district energy system to formulate the management strategy in the energy planning stage.

Numerical study of trimaran wave load based on time-domain Rankine method

Due to the complex fluid interference between outrigger and main hull, it is difficult to predict the trimaran load fluctuation accurately in different marine environments. Therefore, a time-domain Rankine method is developed to improve the accuracy of trimaran load prediction. This method successfully adds the nonlinear load components in time-domain load simulation by taking into account the factors such as instantaneous hull wetted surface, steady ship waves, green wave and slamming. Additionally, the nonlinear growth of green wave and slamming is also observed at outrigger and wet deck, with the increasing of speeds and wave heights. Finally, the relatively smaller errors in the Rankine method are confirmed by comparison with the values from a trimaran model test and linear time-domain load prediction method. Furthermore, the weakly nonlinear Rankine method is considered to be more suitable for trimaran load prediction under harsh marine environment.

A multivariate time series graph neural network for district heat load forecasting

Heat load prediction is essential for energy efficiency and carbon reduction in district heating systems. However, heat load is influenced by many factors, such as building characteristics, consumption behavior, and climate, making its prediction challenging. Traditional methods based on physical models are complex and insufficiently accurate, whereas most data-driven statistical methods ignore customer energy consumption behaviors and their correlation, and do not account for the temporal inertia of consumption. This paper proposes a graph ambient intelligence (GAIN) method for heat load prediction, which classifies customers based on their load profiles and uses collaborative attention on temporal graphs to capture their associations and the weather impact on heat loads. GAIN also incorporates recursive and autoregressive methods to model the temporal inertia of consumption. The proposed method is evaluated on four metrics and compared with fifteen baseline methods. The results show that GAIN achieves the lowest daily forecasting errors in terms of RMSE, MAE, and CV-RMSE, with values of 6.972, 4.442, and 0.191, respectively. Besides, the proposed method achieves a maximum reduction of 25%, 29%, and 25% in RMSE, MAE, and CV-RMSE, respectively, compared to other methods when taking meteorological factors into account.

The installation load prediction method of interference fit between the submarine elliptical pipeline and mechanical connector

For damaged submarine pipelines, interference fit is necessary for the repair technology by the mechanical connector. Due to manufacturing error and asymmetric load, the ovality occurs on pipeline and increases the difficulty to install the connector. For ensure safety, it is necessary to consider the interference and ovality of pipeline to predict the installation load. In this paper, the software ANSYS was used to establish the finite element model of the connector and pipeline, then the contact characteristics on the contact surface were analyzed. According to the static equilibrium equation, the installation load of interference fit is equivalent to the friction force and is proportional to the contact pressure, it could be predicted according to the contact pressure. The results indicate that, on the premise of the same equivalent interference, the contact force and contact area on the contact surface were independent of the ovality of pipeline. For the pipelines with different ovality, the installation load can be predicted based on contact force of the circular pipeline. Some cases are conducted to verify the accuracy of the established prediction formula. The load prediction formula effectively solves the problem of submarine pipeline repair connection and has high engineering application value.

Short-Term Power Load Forecasting Based on Feature Filtering and Error Compensation under Imbalanced Samples

There are many influencing factors present in different situations of power load. There is also a strong imbalance in the number of load samples. In addition to examining the problem of low training efficiency of existing algorithms, this paper proposes a short-term power load prediction method based on feature selection and error compensation under imbalanced samples. After clustering the load data, we expand some sample data to balance the sample categories and input the load data and filtered feature sequences into the improved GRU for prediction. At the same time, the errors generated during the training process are used as training data. An error correction model is constructed and trained, and the results are used for error compensation to further improve prediction accuracy. The experimental results show that the overall prediction accuracy of the model has increased by 80.24%. After expanding a few samples, the prediction accuracy of the region where the samples are located increased by 59.41%. Meanwhile, due to the improvement of the algorithms, the running time was reduced by approximately 14.92%.

Physics-guided LSTM model for heat load prediction of buildings

The thermal process of heating buildings is characterized by the multivariable, nonlinear, and large time lag. Accurately predicting building heat loads is crucial for regulating building heating systems. However, the current black-box method of heat load prediction has challenges such as extensive data usage and weak integration with the building's heat transfer process. To address these challenges, a physics-guided long short-term memory (LSTM) model for dynamic heat load prediction in the next seven days based on data-driven and mechanism analysis was proposed. The data for the model were collected from in-situ measurement and numerical simulation. Specifically, the thermal mechanism was introduced to the training loss function of LSTM and the selection of input variables. The influence of the adaptive data time step on prediction accuracy was investigated. The main conclusions obtained from the current data in this paper are drawn as follows. 1) Refining solar radiation intensity calculation for each orientation reduced mean absolute percentage error (MAPE) of heat load prediction results by 0.02%–1.8% compared to horizontal solar radiation intensity. 2) Improving the training loss function decreased MAPE of heat load prediction results by 0.04%–0.43% compared with the original loss function. 3) Adaptive data time step lowered the MAPE of heat load prediction results by 0.08%–1.8% compared with fixed time step. 4) Mean absolute errors corresponding to those three aspects decreased by 25 kJ–558 kJ, 6 kJ–157 kJ, and 41 kJ–1881 kJ. In the future, wider promotion and application of the prediction model will lead to better performance and be more beneficial to energy saving and carbon reduction of the heating system.

Link load prediction in an optical network with restoration mechanisms

Knowledge about the future link load is an essential issue for optical network operators, especially in the case of network failure and the restoration of affected traffic. In this paper, we study the dynamic operation of an optical network in its normal non-failure state and the situation of a link failure followed by the restoration process. Data obtained during the simulation are used for link load prediction. We propose dynamic methods for multistep link load prediction. The analyzed link load is expressed in two ways: the bitrate of the overall traffic allocated to the link and the number of frequency slots occupied. The proposed prediction methods are expanded to include additional mechanisms that improve the forecasting quality expressed by the mean absolute percentage error metric. We evaluate developed methods on a dataset collected using a representative European network topology with realistic traffic containing diverse types of network transmissions. In broad numerical experiments, we prove the high prediction quality of regression algorithms aided by the proposed additional features.

Study on fast prediction method of hydrodynamic load of floating horizontal axis tidal current turbine with pitching motion under free surface

The floating horizontal-axis tidal current turbine (HATCT) moves with the floating carrier while rotating, resulting in a change in its relative inflow velocity at any time. If the rotating speed of the HATCT is fixed, the HATCT cannot work at the optimum tip speed ratio, resulting in the failure to achieve the optimum power generation efficiency. Therefore, this paper proposes a control strategy for the rotating speed of the HATCT, and obtains the hydrodynamic loads of the HATCT with variable speed rotation and pitching motion under free surface conditions based on the CFD method. Compared with the hydrodynamic load of the HATCT under the same situation but with fixed speed control, the variable speed control can effectively improve the power coefficient of the HATCT, but the load fluctuation in terms of the inflow direction load, power, and pitch moment coefficients are more significant than those with fixed speed control. On this basis, according to the variation law of the damping coefficient with pitch period, pitch amplitude, and tip speed ratio, the hydrodynamic load prediction method of the HATCT with pitching motion is established. The validity of this prediction method is verified by comparing the results with those of CFD calculation.

A PT-DA-Based electric taxi charging load prediction method considering environmental factors

The electric taxis (ETs) charging load is of great importance for the normal and the stable operation of power systems. A prediction model for the ET spatio-temporal charging load is proposed, which considers the drivers’ subjective decision-making and the ET travel patterns. First, an improved Gaussian mixture model with a genetic algorithm is developed based on the real ET data. Besides, a prospect theory based on the Dijkstra algorithm for choosing charging stations is put forward. Then, considering the ambient temperature, a calculation method for the remaining energy in the ET battery is utilized. Based on the refined travel patterns and the Monte Carlo method, the charging load in three scenarios are analyzed, which studies the influence of temperature. ET charging loads of different scales are obtained and the influence of charging load on the typical daily load profile is discussed. The simulation results show that the prediction models can combine the drivers’ psychology with the objective traveling time, and the average error between the real load and the predicted load is less than 1%.

Fast prediction of hydrodynamic load of floating horizontal axis tidal turbine with variable speed control under surging motion with free surface

For floating HATT11HATT: horizontal axis tidal turbine with variable speed control, a numerical model based on CFD22CFD: Computational fluid dynamics method is proposed to predict the surge force. Compared with the hydrodynamic load of the HATT under the same condition but with fixed speed control, the variable speed control can effectively improve the power coefficient of the HATT. When the surge period is 1.5 s and the surge amplitude is D/8, the average power coefficient increases by 36.36%. But the load fluctuation in terms of the axial load and power coefficients are significantly larger than those with fixed speed control. Based on the hydrodynamic load decomposition model of the HATT with fixed speed rotation and surging motion and the variation law of damping coefficient, the hydrodynamic load prediction method of the HATT with variable speed rotation and surging motion is established. By comparing with the CFD results, it is evidenced that this prediction method can effectively predict the axial load and power coefficients of the HATT. The research findings can provide a reference for the rapid prediction of the hydrodynamic load of the HATT during the actual operation of the floating tidal power station.

Buckling failure mechanism and critical buckling load prediction method of super-long piles in soft-clay ground in deep water

Buckling may be a possible failure mode of super-long piles in soft-clay ground in deep water as concerned by several researchers. Although there are many studies on the failure mode of super-long piles in sands or silts deposits, few studies have been carried out thoroughly on mechanical mechanism of buckling instability in soft-clay ground in deep water and the corresponding calculation method. In this paper, first, the Riks Arc-Length method in ABAQUS was evaluated and verified using the FEM simulation and the analytical results from Bhattacharya. It is observed that buckling failure is indeed one of failure modes of super-long piles in soft-clay ground. And then, the buckling capacities of super-long piles were assessed due to various influential parameters. The results show that the critical buckling load of super-long piles increases with the increase of elastic modulus and embedding rates of piles, and the increase of elastic modulus and cohesion of soil, while decreases with the increase of slenderness ratios of piles and horizontal loads. Finally, a prediction method of the critical buckling load for super-long piles was presented based on the above sensitivity analysis for influential parameters and the Euler buckling formula, and the criterion for buckling instability for super-long piles was proposed as well.

A Flight Parameter-Based Aircraft Structural Load Monitoring Method Using a Genetic Algorithm Enhanced Extreme Learning Machine

High-precision operational flight loads are essential for monitoring fatigue of individual aircraft and are usually determined by flight parameters. To tackle the nonlinear relationship between flight loads and flight parameters for more accurate prediction of flight loads, artificial neural networks have been widely studied. However, there are still two major problems, namely the training strategy and sensitivity analysis of the flight parameters. For the first problem, the gradient descent method is usually used, which is time-consuming and can easily converge to a local solution. To solve this problem, an extreme learning machine is proposed to determine the weights based on a Moore–Penrose generalized inverse. Moreover, a genetic algorithm method is proposed to optimize the weights between the input and hidden layers. For the second problem, a mean impact value (MIV) method is proposed to measure the sensitivity of the flight parameters, and the neuron number in the hidden layer is also optimized. Finally, based on the measured dataset of an aircraft, the proposed flight load prediction method is verified to be effective and efficient. In addition, a comparison is made with some well-known neural networks to demonstrate the advantages of the proposed method.

Short-term load forecasting based on AM-CIF-LSTM method adopting transfer learning

Aiming at the unreliability of historical data for short-term load forecasting caused by the sudden change of power grid load under emergencies, a short-term load prediction method adopting transfer learning is studied. The proposed transfer learning method combines the attention mechanism (AM) with the long short-term memory network coupled with input and forgetting gates (CIF-LSTM) to construct the AM-CIF-LSTM short-term load prediction model. First, the variational modal decomposition (VMD) method is used to extract the trend component and certain periodic high-frequency components of the load datasets of the scene to be predicted and similar scenes. Subsequently, the AM-encoder/decoder learning model is established based on the trend component, and the AM learnable parameters are trained and transferred to the AM-CIF-LSTM model. Furthermore, inspired by the idea of classified forecasting, the load trend component and periodic high-frequency components under the required prediction scene are predicted by AM-CIF-LSTM and deep recursive neural network (DRNN), respectively. Finally, the load forecasting results are superimposed to obtain the load forecasting value. The experimental results demonstrate that the proposed method outperformed the existing methods in multiple accuracy indicators and could predict the rapid change trend of load in the case of insufficient data accurately and stably.

Research on a Service Load Prediction Method Based on VMD-GLRT

In this paper, a deep learning-based prediction model VMD-GLRT is proposed to address the accuracy problem of service load prediction. The VMD-GLRT model combines Variational Mode Decomposition (VMD) and GRU-LSTM. At the same time, the model incorporates residual networks and self-attentive mechanisms to improve accuracy of the model. The VMD part decomposes the original time series into several intrinsic mode functions (IMFs) and a residual part. The other part uses a GRU-LSTM structure with ResNets and Self-Attention to learn the features of the IMF and the residual part. The model-building process focuses on three main aspects: Firstly, a mathematical model is constructed based on the data characteristics of the service workload. At the same time, VMD is used to decompose the input time series into multiple components to improve the efficiency of the model in extracting features from the data. Secondly, a long and short-term memory (LSTM) network unit is incorporated into the residual network, allowing the network to correct the predictions more accurately and improve the performance of the model. Finally, a self-focus mechanism is incorporated into the model, allowing the model to better capture features over long distances. This improves the dependence of the output vector on these features. To validate the performance of the model, experiences were conducted using open-source datasets. The experimental results were compared with other deep learning and statistical models, and it was found that the model proposed in this paper achieved improvements in mean absolute percentage error (MAPE).

Load Forecasting Combining Phase Space Reconstruction and Stacking Ensemble Learning

Electric power load forecasting used to rely on some key information such as weather or socioeconomic development data. However, it is usually difficult to obtain accurate data on all the contributing factors. A rolling load prediction method based on phase space reconstruction of chaos theory and stacking ensemble learning is proposed. First, we adopted phase space reconstruction method to process the historical load series to avoid collecting some key data. The rolling forecasting method is used to predict a forecast length in advance, and the test data of learning model is obtained by shifting a forecast length of training data. And then we build a stacking ensemble learning model for load forecasting giving full play to the advantage of various algorithms such as Random Forest, Adaptive Boosting, Gradient Boosting Regression, Decision Tree, eXtreme Gradient Boosting and Long Short Term Memory, etc. Finally, the PJM power grid data set of the United States is used to verify the effectiveness of the proposed method, and the performance of the ensemble model is evaluated. Results show that comparing with single model forecasting, the proposed stacking ensemble learning method based on multi model fusion has higher forecasting accuracy.

Forecasting method for sources and loads in virtual power plant considering uncertainties of multiple sources and loads

Because of to the lack of primary energy and the deteriorating global environment, the key to getting rid of the existing difficulties is the development of clean and pollution-free new energy. On the one hand, to reduce the use of fossil energy, and on the other hand, to reduce emissions of polluting gases. So with the development of technology, more and more distributed power and load began to access the virtual power plant. This paper introduces PV and EVs(EVs) from the perspective of new energy applications and expounds on the background and significance of load forecasting and output power prediction. This paper introduces a variety of load prediction methods. Finally, Monte Carlo simulation is used to predict the EVs’ charging load, and BP neural network is used to build a photovoltaic power forecasting model. Based on the MATLAB R2017a simulation platform, this paper analyzes the EVs’ travel features in Beijing and takes the historical data and meteorological information of a photovoltaic power plant in Australia as an instance to analyze the influencing factors of PV.

Resource environment load prediction method for metal material machining based on process condition similarity matching

Introduction: Resource environment load data are important for analyzing and improving the environmental performance, which are affected by the process condition of metal material machining processes. However, the environmental performance assessment in previous research focused on the results under the specific process conditions. The resource environment load data need to be re-collected when the process conditions are changed for a credible assessment, which is time- consuming and tedious.Methods: This paper proposed a process condition- oriented prediction method of resource environment load data with limited samples. The significance of process condition elements on the resource environment load data was analyzed, and then the resource environment load was predicted according to the similarity between the process condition to be predicted and the existing process conditions.Results and Dicussion: The results show that the average prediction accuracy of this method exceeds 90%, and further the accuracy for predicting the environmental performances using the predicted data is more than 93% which would help process designers to choose the better process condition for machining the metal materials.

Ultra-short-term load prediction of integrated energy system based on load similar fluctuation set classification

Due to the strong coupling characteristics and daily correlation characteristics of multiple load sequences, the prediction method based on time series extrapolation and combined with multiple load meteorological data has limited accuracy improvement, which is tested by the fluctuation of load sequences and the accuracy of Numerical Weather Prediction (NWP). This paper proposes a multiple load prediction method considering the coupling characteristics of multiple loads and the division of load similar fluctuation sets. Firstly, the coupling characteristics of multivariate loads are studied to explore the interaction relationship between multivariate loads and find out the priority of multivariate load prediction. Secondly, the similar fluctuating sets of loads are divided considering the similarity and fluctuation of load sequences. Thirdly, the load scenarios are divided by k-means clustering for the inter-set sequences of similar fluctuating sets, and the Bi-directional Long Short-Term Memory (BI-LSTM) models are trained separately for the sub-set of scenarios and prioritized by prediction. Finally, the effectiveness of the proposed method was verified by combining the multivariate load data provided by the Campus Metabolism system of Arizona State University.

Digital Twin simulation for deep learning framework for predicting solar energy market load in Trade-By-Trade data

Because users behave randomly and in a nonlinear way, predicting electrical loads proves to be a difficult procedure. Due to the development of the smart grid (SG) and advanced metering infrastructure (AMI), humans will be capable of recording, monitoring, and analyzing these non-linear behaviors. The use of electric load projection layouts is a necessity in order to make decisions, plan, and evaluate contracts in electrical systems. Consequently, there have been several load prediction methods in the research that demonstrate trade-offs among prediction precision and runtime (convergence rate). The current paper presents a method for short-term load prediction of market in trade-by-trade data that would be quick and precise. Modified mutual information (MMI) is used to extract abstractive characteristics from historic information. Learning empowers the factored conditional restricted Boltzmann machine (FCRBM) for predicting the electrical loads. Ultimately, the efficiency has been optimized using the suggested modified teaching–learning algorithm (MTLA). The suggested architecture has the advantage of improving prediction precision and convergence rate. The MMI method and FCRBM layout improve prediction precision. In addition, MTLA has been used to enhance the convergence rates. Based on simulation outcomes, the suggested quick and precise layout performs better than conventional layouts when it comes to forecasting precision and convergence rates, including Bi-level, MI-artificial neural network (MI-ANN), and accurate fast converging short-term load forecast (AFC-STLF).

Research on Power Consumption Calculation Method for Refrigerating and Space Conditioning Considering Heat Balance in a Grocery store

In grocery stores, spatial coordination and refrigerated display cases interact, making it difficult to study energy conservation through architectural ideas. The purpose of this research is to find the indoor enthalpy from the leaked heat of the display case and the space conditioning load, and to devise a method to calculate the energy of the store by combining the space conditioning load calculation and the refrigeration load calculation. In this study, we devised the following three points. 1. Store cooling load prediction method and power consumption calculation method using display case cooling load characteristics. 2. A generalized model for grocery store vertical temperature gradient using CFD analysis results. 3. Energy consumption calculation method considering the balance of the three loads of cooling, building and space conditioning. Then, we confirmed the validity by comparing with the measured values, and performed simulations under various conditions.