Forecasting with artificial neural networks: the state of the art

Load forecasting has become one of the major areas of research in electrical engineering, and most traditional forecasting models and artificial intelligence techniques have been tried out in this task. Artificial neural networks (NNs) have lately received much attention, and a great number of papers have reported successful experiments and practical tests with them. Nevertheless, some authors remain skeptical, and believe that the advantages of using NNs in forecasting have not been systematically proved yet. In order to investigate the reasons for such skepticism, this review examines a collection of papers (published between 1991 and 1999) that report the application of NNs to short-term load forecasting. Our aim is to help to clarify the issue, by critically evaluating the ways in which the NNs proposed in these papers were designed and tested.

Neural networks for short-term load forecasting: a review and evaluation

Energy is vital for sustainable development of any nation – be it social, economic or environment. In the past decade energy consumption has increased exponentially globally. Energy management is crucial for the future economic prosperity and environmental security. Energy is linked to industrial production, agricultural output, health, access to water, population, education, quality of life, etc. Energy demand management is required for proper allocation of the available resources. During the last decade several new techniques are being used for energy demand management to accurately predict the future energy needs. In this paper an attempt is made to review the various energy demand forecasting models. Traditional methods such as time series, regression, econometric, ARIMA as well as soft computing techniques such as fuzzy logic, genetic algorithm, and neural networks are being extensively used for demand side management. Support vector regression, ant colony and particle swarm optimization are new techniques being adopted for energy demand forecasting. Bottom up models such as MARKAL and LEAP are also being used at the national and regional level for energy demand management.

Energy models for demand forecasting—A review

With the fast-paced changing technologies in the power industry, new power references addressing new technologies are coming to the market. So there is an urgent need to keep track of international experiences and activities taking place in the field of modern unit-commitment (UC) problem. This paper gives a bibliographical survey, mathematical formulations, and general backgrounds of research and developments in the field of UC problem for past 35 years based on more than 150 published articles. The collected literature has been divided into many sections, so that new researchers do not face any difficulty in carrying out research in the area of next-generation UC problem under both the regulated and deregulated power industry.

Unit commitment-a bibliographical survey

Electrical load forecasting plays a vital role in order to achieve the concept of next generation power system such as smart grid, efficient energy management and better power system planning. As a result, high forecast accuracy is required for multiple time horizons that are associated with regulation, dispatching, scheduling and unit commitment of power grid. Artificial Intelligence (AI) based techniques are being developed and deployed worldwide in on Varity of applications, because of its superior capability to handle the complex input and output relationship. This paper provides the comprehensive and systematic literature review of Artificial Intelligence based short term load forecasting techniques. The major objective of this study is to review, identify, evaluate and analyze the performance of Artificial Intelligence (AI) based load forecast models and research gaps. The accuracy of ANN based forecast model is found to be dependent on number of parameters such as forecast model architecture, input combination, activation functions and training algorithm of the network and other exogenous variables affecting on forecast model inputs. Published literature presented in this paper show the potential of AI techniques for effective load forecasting in order to achieve the concept of smart grid and buildings.

A review on artificial intelligence based load demand forecasting techniques for smart grid and buildings

A multilayer feedforward neural network is proposed for short-term load forecasting. To speed up the training process, a learning algorithm for the adaptive training of neural networks is presented. The effectiveness of the neural network with the proposed adaptive learning algorithm is demonstrated by short-term load forecasting of the Taiwan power system. It is found that, once trained by the proposed learning algorithm, the neural network can yield the desired hourly load forecast efficiently and accurately. The proposed adaptive learning algorithm converges much faster than the conventional backpropagation-momentum learning method. >

Short term load forecasting using a multilayer neural network with an adaptive learning algorithm

Heuristic search algorithms based on some heuristic rules are proposed to reach the desired switching operations through which power transformer and distribution feeder load balancing can be achieved. The proposed method can be applied to changing load conditions as well as constant load conditions. The effectiveness of the approach is demonstrated by conducting feeder reconfiguration on a distribution system within the Taipei South District Office of the Taiwan Power Company. It is found that the desired switching operations can be reached in a very efficient manner by using the proposed algorithms. >

Transformer and feeder load balancing using a heuristic search approach

An approach is presented for multiarea unit commitment which takes the power system dynamic stability limit into account. Dynamic programming is employed to perform unit commitment on the whole system. The eigenvalues for the resultant hourly generation schedules are examined to see if they satisfy the prespecified dynamic security criterion. If the requirement is not met at certain hours, an iterative algorithm is employed to reduce the interarea line flows gradually and to perform area redispatch and, if necessary, area unit commitment, in order for the resultant generation schedule to satisfy the requirement. The goal is to achieve a multiarea generation schedule which meets the conventional requirements of having lowest fuel costs with the spinning reserves and steady-state transmission capacity limits satisfied, and offers good dynamic performance through the enforcement of dynamic security constraints. >

Dynamic security constrained multi-area unit commitment

A study is made of the control method for the simultaneous assignment of eigenvalues and eigenvectors, which is often referred to as eigenstructure assignment. The motivation for eigenstructure assignment is that system damping can be improved by means of eigenvalue assignment and that the system dynamic behavior can be altered using eigenvector assignment. The proposed control scheme is of the decentralized output feedback supplementary excitation control configuration which is most desirable in practice. Results obtained from the application of the proposed controller to the system studied, which is of longitudinal structure, show that exact assignment of the eigenstructure associated with the worst-damped electromechanical mode can be achieved. The effect of eigenvector assignment on the participation factor is also investigated. >

Eigenstructure assignment in a longitudinal power system via excitation control

The application of a stabilizer to a power system with a pumped-storage plant is investigated. Eigenvalue-eigenvector analysis and time-domain transient stability simulation are used to identify the optimum stabilizer parameters, and are verified by field test results. It is found that for the system considered, the pumped-storage plant is not necessarily the best location for the stabilizer application if the goal is to damp out tieline oscillations. Suitable stabilizer parameters for the pumping and generating mode operations are recommended. >

Y.-Y. Hsu

Papers

Short term load forecasting using a multilayer neural network with an adaptive learning algorithm

Transformer and feeder load balancing using a heuristic search approach

Dynamic security constrained multi-area unit commitment

Eigenstructure assignment in a longitudinal power system via excitation control

Application of power system stabilizer on a system with pumped storage plant