Short-Term Electric Load Forecasting Using Echo State Networks and PCA Decomposition

Bianchi, Filippo Maria; Santis, Enrico De; Rizzi, Antonello; Sadeghian, Alireza

doi:10.1109/access.2015.2485943

Cited by 126 publications

(66 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These problems make FNN unsuitable for the local STLF task. On the other hand, recurrent neural networks such as echo state networks and long short term memory networks are widely adopted in STLF [4]. However, these architectures are not considered in this work, as we focus on model-based approaches.…”

Section: Introductionmentioning

confidence: 99%

Local short term electricity load forecasting: Automatic approaches

Dang-Ha

Bianchi

Olsson

2017

2017 International Joint Conference on Neural Networks (IJCNN)

Self Cite

View full text Add to dashboard Cite

Short-Term Load Forecasting (STLF) is a fundamental component in the efficient management of power systems, which has been studied intensively over the past 50 years. The emerging development of smart grid technologies is posing new challenges as well as opportunities to STLF. Load data, collected at higher geographical granularity and frequency through thousands of smart meters, allows us to build a more accurate local load forecasting model, which is essential for local optimization of power load through demand side management. With this paper, we show how several existing approaches for STLF are not applicable on local load forecasting, either because of long training time, unstable optimization process, or sensitivity to hyper-parameters. Accordingly, we select five models suitable for local STFL, which can be trained on different time-series with limited intervention from the user. The experiment, which consists of 40 time-series collected at different locations and aggregation levels, revealed that yearly pattern and temperature information are only useful for high aggregation level STLF. On local STLF task, the modified version of double seasonal Holt-Winter proposed in this paper performs relatively well with only 3 months of training data, compared to more complex methods.After having conducted a comprehensive survey of different STLF approaches, we selected five models, two of which are original variations of existing architectures, proposed in this paper for the first time. The models were chosen (or modified) to overcome the three aforementioned limitations and to be at the same time characterized by a high degree of automation, arXiv:1702.08025v1 [math.OC]

show abstract

Section: Introductionmentioning

confidence: 99%

Local short term electricity load forecasting: Automatic approaches

Dang-Ha

Bianchi

Olsson

2017

2017 International Joint Conference on Neural Networks (IJCNN)

Self Cite

View full text Add to dashboard Cite

show abstract

“…], [14], [25], [42], [45], [78], [101], [110], [122], [124], [132], [156], [164], [171], [178], [187], [210], [211], [213], [228], [237], [242], [256]), Support Vector Machines (SVM) (21) ( [? ], [36], [53], [57], [65], [78], [79], [106], [115], [117], [122], [157], [159], [166], [187], [193], [203], [227], [240], [253], [256]), autoregressive integrated moving average (ARIMA) (13) ( [6], [19], [32], [42], [53], [78], [90],…”

Section: Sms Resultsmentioning

confidence: 99%

Smart Grids Data Analysis: A Systematic Mapping Study

Rossi

Chren

2020

IEEE Trans. Ind. Inf.

View full text Add to dashboard Cite

Article under review. This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.The article is structured as follows. In section II, we provide an overview of Smart Grids concepts: mainly architecture and components of the SG infrastructure. In section III, we define the goals, needs, process and research questions for the Systematic Mapping Study on data analysis in the SG context. In section IV, we present the results from the overall SMS process, divided into answers to the main research questions set. In Section V, we discuss the main threats to validity of the current study. Section VI provides the final conclusions.

show abstract

“…Some adjustments done on the ESN itself include: adding white noise into internal neurons [27], introducing leaky integrator neurons [28], performing ridge regression instead of linear regression [29], clustering the internal neurons [1], etc. Meanwhile, several attempts have been made to combine ESN with other algorithms, such as decision tree [15], principal component analysis (PCA) [14], and the Bayesian method [12], and a hierarchical architecture of ESN was brought forward [30]. These improvements have been applied into numerous scenarios and achieve good results.…”

Section: Improvements In Esnmentioning

confidence: 99%

“…In most existing frameworks, the learning and training of RNN/ESN are processed in a centralized way [6,8,[12][13][14]18,19]. However, in the era of Big Data, centralized data storage becomes technologically unsuitable [20]; as a result, solutions relying on centralized training in ML could face challenges such as single point of failure, communication bottlenecks, training consistency, etc.…”

Section: Introductionmentioning

confidence: 99%

Algorithm and Implementation of Distributed ESN Using Spark Framework and Parallel PSO

Wu¹,

Zhu²,

Li³

et al. 2017

Applied Sciences

View full text Add to dashboard Cite

Abstract:The echo state network (ESN) employs a huge reservoir with sparsely and randomly connected internal nodes and only trains the output weights, which avoids the suboptimal problem, exploding and vanishing gradients, high complexity and other disadvantages faced by traditional recurrent neural network (RNN) training. In light of the outstanding adaption to nonlinear dynamical systems, ESN has been applied into a wide range of applications. However, in the era of Big Data, with an enormous amount of data being generated continuously every day, the data are often distributed and stored in real applications, and thus the centralized ESN training process is prone to being technologically unsuitable. In order to achieve the requirement of Big Data applications in the real world, in this study we propose an algorithm and its implementation for distributed ESN training. The mentioned algorithm is based on the parallel particle swarm optimization (P-PSO) technique and the implementation uses Spark, a famous large-scale data processing framework. Four extremely large-scale datasets, including artificial benchmarks, real-world data and image data, are adopted to verify our framework on a stretchable platform. Experimental results indicate that the proposed work is accurate in the era of Big Data, regarding speed, accuracy and generalization capabilities.

show abstract

Short-Term Electric Load Forecasting Using Echo State Networks and PCA Decomposition

Cited by 126 publications

References 44 publications

Local short term electricity load forecasting: Automatic approaches

Local short term electricity load forecasting: Automatic approaches

Smart Grids Data Analysis: A Systematic Mapping Study

Algorithm and Implementation of Distributed ESN Using Spark Framework and Parallel PSO

Contact Info

Product

Resources

About