Mohamed A. El-Sharkawi

Electric load forecasting using an artificial neural network

An artificial neural network (ANN) approach is presented for electric load forecasting. The ANN is used to learn the relationship among past, current and future temperatures and loads. In order to provide the forecasted load, the ANN interpolates among the load and temperature data in a training data set. The average absolute errors of the 1 h and 24 h-ahead forecasts in tests on actual utility data are shown to be 1.40% and 2.06%, respectively. This compares with an average error of 4.22% for 24 h ahead forecasts with a currently used forecasting technique applied to the same data. >

Optimal Charging Strategies for Unidirectional Vehicle-to-Grid

Vehicle-to-grid (V2G) has been proposed as a way to increase the adoption rate of electric vehicles (EVs). Unidirectional V2G is especially attractive because it requires little if any additional infrastructure other than communication between the EV and an aggregator. The aggregator in turn combines the capacity of many EVs to bid into energy markets. In this work an algorithm for unidirectional regulation is developed for use by an aggregator. Several smart charging algorithms are used to set the point about which the rate of charge varies while performing regulation. An aggregator profit maximization algorithm is formulated with optional system load and price constraints analogous to the smart charging algorithms. Simulations on a hypothetical group of 10 000 commuter EVs in the Pacific Northwest verify that the optimal algorithms increase aggregator profits while reducing system load impacts and customer costs.

Optimal Scheduling of Vehicle-to-Grid Energy and Ancillary Services

Vehicle-to-grid (V2G), the provision of energy and ancillary services from an electric vehicle (EV) to the grid, has the potential to offer financial benefits to EV owners and system benefits to utilities. In this work a V2G algorithm is developed to optimize energy and ancillary services scheduling. The ancillary services considered are load regulation and spinning reserves. The algorithm is developed to be used by an aggregator, which may be a utility or a third party. This algorithm maximizes profits to the aggregator while providing additional system flexibility and peak load shaving to the utility and low costs of EV charging to the customer. The formulation also takes into account unplanned EV departures during the contract periods and compensates accordingly. Simulations using a hypothetical group of 10 000 commuter EVs in the ERCOT system using different battery replacement costs demonstrate these significant benefits.

Identification and control of a DC motor using back-propagation neural networks

An artificial-neural-network (ANN)-based high-performance speed-control system for a DC motor is introduced. The rotor speed of the DC motor can be made to follow an arbitrarily selected trajectory. The purpose is to achieve accurate trajectory control of the speed, especially when motor and load parameters are unknown. The unknown nonlinear dynamics of the motor and the load are captured by the ANN. The trained neural-network identifier is combined with a desired reference model to achieve trajectory control of speed. The performances of the identification and control algorithms are evaluated by simulating them on a typical DC motor model. It is shown that a DC motor can be successfully controlled using an ANN. >

Pareto Multi Objective Optimization

The goal of this chapter is to give fundamental knowledge on solving multi-objective optimization problems. The focus is on the intelligent metaheuristic approaches (evolutionary algorithms or swarm-based techniques). The focus is on techniques for efficient generation of the Pareto frontier. A general formulation of MO optimization is given in this chapter, the Pareto optimality concepts introduced, and solution approaches with examples of MO problems in the power systems field are given

Swarm intelligence for routing in communication networks

Swarm intelligence, as demonstrated by natural biological swarms, exhibits numerous powerful features that are desirable in many engineering systems, such as communication networks. In addition, new paradigms for designing autonomous and scalable systems may result from analytically understanding and extending the design principles and operations inherent in intelligent biological swarms. A key element of future design paradigms will be emergent intelligence - simple local interactions of autonomous swarm members, with simple primitives, giving rise to complex and intelligent global behavior. Communication network management is becoming increasingly difficult due to the increasing network size, rapidly changing topology, and complexity. A new class of algorithms, inspired by swarm intelligence, is currently being developed that can potentially solve numerous problems of such networks. These algorithms rely on the interaction of a multitude of simultaneously interacting agents. A survey of such algorithms and their performance is presented here.

Minimum power broadcast trees for wireless networks: integer programming formulations

Wireless multicast/broadcast sessions, unlike wired networks, inherently reach several nodes with a single transmission. For omnidirectional wireless broadcast to a node, all nodes closer will also be reached. Heuristic algorithms for constructing the minimum power tree in wireless networks have been proposed by Wieselthier et al. and Stojmenovic et al. Recently, an evolutionary search procedure has been proposed by Marks et al. In this paper, we present three different integer programming models which can be used for an optimal solution of the minimum power broadcast/multicast problem in wireless networks. The models assume complete knowledge of the distance matrix and is therefore most suited for networks where the locations of the nodes are fixed.

Power System Security Assessment Using Neural Networks: Feature Selection Using Fisher Discrimination

One of the most important considerations in applying neural networks to power system security assessment is the proper selection of training features. Modem interconnected power systems often consist of thousands of pieces of equipment, each of which may have an affect on the security of the system. Neural networks have shown great promise for their ability to quickly and accurately predict the system security when trained with data collected from a small subset of system variables. This paper investigates the use of Fishers linear discriminant function, coupled with feature selection techniques as a means for selecting neural network training features for power system security assessment. A case study is performed on the IEEE 50-generator system to illustrate the effectiveness of the proposed techniques.

Optimal Combined Bidding of Vehicle-to-Grid Ancillary Services

Vehicle-to-grid (V2G) has the potential of reducing the cost of owning and operating electric vehicles (EVs) while increasing utility system flexibility. Unidirectional V2G is a logical first step because it can be implemented on standard J1772 chargers and it does not degrade EV batteries from cycling. In this work an optimal combined bidding formulation for regulation and spinning reserves is developed to be used by aggregators. This formulation takes into account unplanned departures by EV owners during contract periods and compensates accordingly. Optional load level and price constraints are also developed. These algorithms maximize profits to the aggregator while increasing the benefits the customers and utility. Simulations over a three month period on the ERCOT system show that implementation of these algorithms can provide significant benefits to customers, utilities, and aggregators. Comparisons with bidirectional V2G show that while the benefits of unidirectional V2G are significantly lower, so are the risks.

Large scale dynamic security screening and ranking using neural networks

This paper reports on the findings of a completed Canadian Electric Association (CEA) funded project exploring the application of neural network to dynamic security contingency screening and ranking. The idea is to use the information on the prevailing operating condition and directly provide contingency screening and ranking using a trained neural network. To train the two neural networks for the large scale systems of BC Hydro and Hydro Quebec, in total 1691 detailed transient stability simulation were conducted, 1158 for BC Hydro system and 533 for the Hydro Quebec system. The simulation program was equipped with the energy margin calculation module (Second Kick) to measure the energy margin in each run. The first set of results showed poor performance for the neural networks in assessing the dynamic security. However a number of corrective measures improved the results significantly. These corrective measures included: (a) the effectiveness of output, (b) the number of outputs, (c) the type of features (static versus dynamic), (d) the number of features, (e) system partitioning and (f) the ratio of training samples to features. The final results obtained using the large scale systems of BC Hydro and Hydro Quebec demonstrates a good potential for neural network in dynamic security assessment contingency screening and ranking.