Short-term Power Load Forecasting Based on Balanced KNN

Lv, Xianlong; Cheng, Xin; YanShuang,; Tang, Yanmei

doi:10.1088/1757-899x/322/7/072058

Cited by 13 publications

(8 citation statements)

References 2 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the variable decomposition in Section III-B.1, the method proposed for TF variable analysis is presented mainly from 4 aspects, i.e., variable selection, traffic factor analysis, spatial analysis, and temporal analysis. To this end, we apply ANOVA decomposition to the source nodes in a single-layered EHHNN, where the relative importance of all candidate input variables is revealed by the σ values in (9). We unify the vector of complete input variables as z = [y t o i , s t o i , p t o i ] T with o i ∈ I i and t ∈ T .…”

Section: B Interpretation Towards Tf Datamentioning

confidence: 99%

“…In summary, the experiments mainly contain two parts, i.e., -Performance Evaluation and Comparisons: The candidate variables in Table I are considered, and the more important ones are selected based on the σ values in (9) to train the EHHNN. Then, the prediction performance of the EHHNN is compared with 5 related methods; -Variable Analysis: To interpret the EHHNN predictor, variable analysis is conducted mainly concerning the aspects of network components, traffic factors, spatial influence and spatial influence based on the σ values (9).…”

Section: B Tf Prediction and Analysis On Road Segmentsmentioning

confidence: 99%

“…However, the accuracy remains unsatisfactory and the computational burden is high. Non-parametric methods developed rapidly and gained wide attention, since they have been found to provide stronger representability and flexibility to capture the nonlinearities of TF data, including support vector regression (SVR) [7], [8], k-nearest neighbor methods [9], etc. Parametric models include Kalman filtering models [10], historical average (HA), and time-series models relating to the autoregressive integrated moving average (ARIMA) [11]- [14], etc.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Short-Term Traffic Flow Prediction Based on the Efficient Hinging Hyperplanes Neural Network

Tao

et al. 2022

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

Traffic flow (TF) prediction is an important and yet a challenging task in transportation systems, since the TF involves high nonlinearities and is affected by many elements. Recently, neural networks have attracted much attention for TF prediction, but they are commonly black boxes with complex architectures and difficult to be interpreted, e.g., the contributions of specific traffic elements are not explicit, hardly providing informative guidance. In this paper, we aim at addressing more interpretable short-term TF prediction with joint consideration to high accuracy, and thus introduces a pragmatic method by applying the efficient hinging hyperplanes neural network (EHHNN) simply built upon sparse neuron connections. In the proposed method, different traffic factors are incorporated into the inputs, including their spatial-temporal information. Besides the pursuit of accuracy, we further extend the ANOVA decomposition of EHHNNs to the interpretation analysis with specifications to traffic data, in which the contributions concerning specific traffic variables are detected quantitatively. As such, the proposed method firstly applies the EHHNN to filter out more important traffic variables for dimensionality reduction while maintaining accurate prediction. Then, variable interpretation analysis is performed from different perspectives, e.g. to quantitatively investigate the influence of traffic factors and also their spatialtemporal impacts. Therefore, a predictor and an analyzing tool can both be attained for the TF by exerting the flexibility and extending the interpretability of EHHNNs, which is promising to provide informative guidance to future traffic control. Numerical

show abstract

Section: B Interpretation Towards Tf Datamentioning

confidence: 99%

Section: B Tf Prediction and Analysis On Road Segmentsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Short-Term Traffic Flow Prediction Based on the Efficient Hinging Hyperplanes Neural Network

Tao

et al. 2022

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

show abstract

“…• K-Nearest Neighbor works on the measured Euclidean distances between the query and the data points and then operating on a particular number (K) of data samples then finds the most suitable class for it in case of classification or takes the average of the points in case of regression. We train the dataset many times with different values of k and find those values of k at which the error is minimum when the algorithm is subjected to unseen data [10]. • MLP regressor is a multi-layer perceptron supervised learning, non-linear training technique that uses backpropagation to update weights.…”

Section: Description Of the Various Kinds Of Regressorsmentioning

confidence: 99%

Load Forecasting Using LSTM and Its Comparison with Other Machine Learning Techniques and Their Implementation

Mishra

2021

Lecture Notes in Electrical Engineering

View full text Add to dashboard Cite

This paper presents hourly electrical load forecasting as time series forecasting model using Multilayer deep learning and Long Short-Term Memory neural network Technique and their detailed comparative study with various machine learning techniques based on their mean Squared Error (MSE), mean absolute percentage error (MAPE), root mean squared error (RMSE) and training time. Load Forecasting has immense potential to help in modulating the generation and distribution potentials of our smart grids in accordance to the requirement so that optimum power is generated and supplied through various channels which would be effective in grid management and operations.

show abstract

“…When each node assigns itself to the processing of the data subset after completion, the respective results are summarized and merged, and the final result is the processing result of the entire data set. Compared with a single processor, the parallel data processing mode of multiple computing nodes on multiple processors can significantly improve the efficiency of Internet marketing forecasting [6][7][8].…”

Section: Introductionmentioning

confidence: 99%

Analysis of Internet Marketing Forecast Model Based on Parallel K-Means Algorithm

Chen¹,

Ge²

2021

Journal of Mathematics

View full text Add to dashboard Cite

Based on the parallel K-means algorithm, this article conducts in-depth research on the related issues of marketing node detection under the Internet, including designing a new Internet marketing node detector and a location summary network based on FCN (Full Convolutional Network) to input the preprocessing of the node and verify its performance under the data sets. At the same time, to solve the problem of insufficient data sets of Internet marketing nodes, the Internet data sets are artificially generated and used for detector training. First, the multiclass K-means algorithm is changed to two categories suitable for Internet marketing node detection: marketing nodes and background categories. Secondly, the weights in the K-means algorithm are mostly only applicable to target detection tasks. Therefore, when processing Internet marketing node detection tasks, the K-means algorithm is used to regress the training set and calculate 5 weights. During the simulation experiment, the weight calculation formula is used to calculate the weight of the feature term. The basic idea is that if a feature word appears more often in this document but less frequently in other nodes, the word will be assigned higher. At the same time, this article focuses on k. Some shortcomings of the mean clustering algorithm have been specifically improved. By standardizing the data participating in the clustering, the data participating in the clustering is transformed from an irregular distribution to a cluster-like distribution, thereby facilitating the clustering process. The density is introduced to determine the initial center of the cluster, and the purity metric is introduced to determine the appropriate density radius of the cluster center, to achieve the most effective reduction of the support vector machine training samples.

show abstract

Short-term Power Load Forecasting Based on Balanced KNN

Cited by 13 publications

References 2 publications

Short-Term Traffic Flow Prediction Based on the Efficient Hinging Hyperplanes Neural Network

Short-Term Traffic Flow Prediction Based on the Efficient Hinging Hyperplanes Neural Network

Load Forecasting Using LSTM and Its Comparison with Other Machine Learning Techniques and Their Implementation

Analysis of Internet Marketing Forecast Model Based on Parallel K-Means Algorithm

Contact Info

Product

Resources

About