The paper addresses the problem of predicting hourly load demand using adaptive artificial neural networks (ANNs). A particle swarm optimization (PSO) algorithm is employed to adjust the network's weights in the training phase of the ANNs. The advantage of using a PSO algorithm over other conventional training algorithms such as the back-propagation (BP) is that potential solutions will be flown through the problem hyperspace with accelerated movement towards the best solution. Thus the training phase should result in obtaining the weights configuration associated with the minimum output error. Data are wavelet transformed during the preprocessing stage and then inserted into the neural network to extract redundant information from the load curve. This results in better load characterization which creates a more reliable forecasting model. The transformed data of historical load and weather information were trained and tested over various periods of time. The generalized error estimation is done by using the reverse part of the data as a ldquotestrdquo set. The results were compared with traditional BP algorithm and offered a high forecasting precision.

Applying Wavelets to Short-Term Load Forecasting Using PSO-Based Neural Networks

In this paper, we discuss the compression of waveforms obtained from measurements of power system quantities and analyze the reasons why its importance is growing with the advent of smart grid systems. While generation and transmission networks already use a considerable number of automation and measurement devices, a large number of smart monitors and meters are to be deployed in the distribution network to allow broad observability and real-time monitoring. This situation creates new requirements concerning the communication interface, computational intelligence and the ability to process data or signals and also to share information. Therefore, a considerable increase in data exchange and in storage is likely to occur. In this context, one must achieve an efficient use of channel communication bandwidth and a reduced need of storage space for power system data. Here, we review the main compression techniques devised for electric signal waveforms providing an overview of the achievements obtained in the past decades. Additionally, we envision some smart grid scenarios emphasizing open research issues regarding compression of electric signal waveforms. We expect that this paper will contribute to motivate joint research efforts between electrical power system and signal processing communities in the area of signal waveform compression.

The Compression of Electric Signal Waveforms for Smart Grids: State of the Art and Future Trends

Long-term demand forecasting presents the first step in planning and developing future generation, transmission and distribution facilities. One of the primary tasks of an electric utility accurately predicts load demand requirements at all times, especially for long-term. Based on the outcome of such forecasts, utilities coordinate their resources to meet the forecasted demand using a least-cost plan. In general, resource planning is performed subject to numerous uncertainties. Expert opinion indicates that a major source of uncertainty in planning for future capacity resource needs and operation of existing generation resources is the forecasted load demand. This paper presents an overview of the past and current practice in long- term demand forecasting. It introduces methods, which consists of some traditional methods, neural networks, genetic algorithms, fuzzy rules, support vector machines, wavelet networks and expert systems.

/pdf/different-methods-of-long-term-electric-load-demand-54n0niu85u.pdf

Different Methods of Long-Term Electric Load Demand Forecasting a Comprehensive Review

Properly designing a wavelet neural network (WNN) is crucial for achieving the optimal generalization performance. In this paper, two different approaches were proposed for improving the predictive capability of WNNs. First, the types of activation functions used in the hidden layer of the WNN were varied. Second, the proposed enhanced fuzzy c-means clustering algorithm—specifically, the modified point symmetry-based fuzzy c-means (MSFCM) algorithm—was employed in selecting the locations of the translation vectors of the WNN. The modified WNN was then applied to heterogeneous cancer classification using four different microarray benchmark datasets. The comparative experimental results showed that the proposed methodology achieved an almost 100% classification accuracy in multiclass cancer prediction, leading to superior performance with respect to other clustering algorithms. Subsequently, performance comparisons with other classifiers were made. An assessment analysis showed that this proposed approach outperformed most of the other classifiers.

Reliable multiclass cancer classification of microarray gene expression profiles using an improved wavelet neural network

Long-term demand forecasting presents the first step in planning and developing future generation, transmission and distribution facilities. One of the primary tasks of an electric utility accurately predicts load demand requirements at all times, especially for long-term. Based on the outcome of such forecasts, utilities coordinate their resources to meet the forecasted demand using a least-cost plan. In general, resource planning is performed subject to numerous uncertainties. Expert opinion indicates that a major source of uncertainty in planning for future capacity resource needs and operation of existing generation resources is the forecasted load demand. This paper presents an overview of the past and current practice in longterm demand forecasting. It introduces methods, which consists of some traditional methods, neural networks, genetic algorithms, fuzzy rules and wavelet networks.

Methods for long-term electric load demand forecasting; a comprehensive investigation

This paper investigates the application of wavelet packet in power load forecasting, and it proposes a novel forecasting algorithm based on wavelet packet decomposition and reconstruction. The algorithm uses the biorthogonal wavelet that has linear phase to decompose the load data to extract load components of different frequencies, and then neural network is used to predict the load component of each wavelet packet space. Finally, the load forecasting values of all the spaces are added up to produce the load forecasting result. It is advantageous in analyzing the load characteristics in each time-frequency zone to achieve accurate modeling and forecasting. Case study shows that the proposed algorithm improves forecasting accuracy and it is superior to traditional back-propagation neural network.

Power load forecasting algorithm based on wavelet packet analysis

The increasing application of power quality data acquisition devices produces large amount of data that should be compressed. The paper investigates the characteristics of power quality data and delta modulation technique, and it proposes a lossless power data compression algorithm based on high-order delta modulation. The compression algorithm carries on multiple differential operations on power quality data, so it could reduce the magnitude of data and requires fewer bits for coding. The proposed algorithm has high compression ratio and little computation requirements. Furthermore, it is suitable for dealing with the power quality data measured at high sampling frequency, and it can work well with traditional compression methods such as Huffman coding. Simulations for several kinds of power quality data confirm its effectiveness and advantages over traditional Huffman coding method.

A new data compression algorithm for power quality online monitoring

To improve the accuracy of power load forecasting, this paper analyzes the defects as well as merits of artificial neural network (ANN) and grey prediction method, and it combines the two methods to propose a novel forecasting method called grey neural network (GNN). GNN utilizes the accumulation generation operation (AGO) of grey prediction to transform the original load data to first order AGO data which has better regularity, making it easier for ANN to model and forecast. At the same time the theoretical error of traditional grey prediction method is avoided. GNN is suitable for middle and long term load forecasting, and case study shows that its forecasting accuracy is better than that of ANN and grey prediction method. The paper also reveals the importance of data transformation in load forecasting process, and it further investigates the effect of inverse transformation on forecasting error.

Power load forecasting based on grey neural network

Single-phase-to-ground fault is the most frequently occurred short-circuit fault in distribution network, and it is urgent to develop new methods to detect fault feeder correctly. The paper compares the fault-feeder selection theories using transient signals with those of using steady signals, and the application of transient signal is emphasized. By analyzing the characteristics of the Peterson-coil-grounded system, the paper proposes a novel algorithm to select fault feeder based on the transient signals and wavelet packet. It records the post-fault transient zero-sequence current of each feeder, and wavelet packet is used to extract the supply fundamental frequency and high frequency components. Finally the current and its components are used to detect fault feeder. This method is accurate and adaptive for the Peterson-coil-grounded system. Case study validates the effectiveness of the new algorithm for various fault modes in neural ineffectively grounded systems.

Single-phase-to-ground fault feeder detection based on transient current and wavelet packet

Power quality is an important index of the electrical industry, and it affects the interests of both power utilities and customers. This paper introduces the functions and methods of power quality monitoring, and it discusses the importance of on-line monitoring for power quality management. Then the paper focuses on the demand for the communication network of power quality on-line monitoring system, and it analyzes the performance of different communication networks of power quality on-line monitoring system, and OPNET simulator is used to validate the analysis. Result shows a shared 10 M Ethernet couldn't fulfill the demand of power quality on-line monitoring, and a switched 10 M Ethernet or better is required.

Dahai Zhang

Papers

Power load forecasting algorithm based on wavelet packet analysis

A new data compression algorithm for power quality online monitoring

Power load forecasting based on grey neural network

Single-phase-to-ground fault feeder detection based on transient current and wavelet packet

Research on Power Communication Network and Power Quality Monitoring Using OPNET