Artificial Intelligence Techniques in Power Systems

2: Technology and Science Laboratories, National Grid Company plc, Leatherhead, UK
3: School of Electronic and Electrical Engineering, University of Bath, Bath, UK
Research in artificial intelligence has developed many techniques and methodologies that can be adapted or used directly to solve complex power system problems.
Inspec keywords: artificial intelligence; power engineering computing; power systems
Other keywords: artificial intelligence techniques; reference text; researchers; power systems engineers; comprehensive text
Subjects: Expert systems and other AI software and techniques; Power systems; Power engineering computing; Artificial intelligence (theory)
- Book DOI: 10.1049/PBPO022E
- Chapter DOI: 10.1049/PBPO022E
- ISBN: 9780852968970
- e-ISBN: 9781849191722
- Page count: 320
- Format: PDF
-
Front Matter
- + Show details - Hide details
-
p.
(1)
-
1 Artificial intelligence techniques in power systems
- + Show details - Hide details
-
p.
1
–18
(18)
Since the early to mid 1980s much of the effort in power systems analysis has turned away from the methodology of formal mathematical modelling which came from the fields of operations research, control theory and numerical analysis to the less rigorous techniques of artificial intelligence (AI). Today the main AI techniques found in power systems applications are those utilising the logic and knowledge representations of expert systems, fuzzy systems, artificial neural networks (ANN) and, more recently, evolutionary computing. These techniques will be outlined in this chapter and the power system applications indicated.
-
2 Advanced knowledge engineering techniques with applications to electric power systems
- + Show details - Hide details
-
p.
19
–44
(26)
This chapter starts with a brief overview of the state-of-the-art of expert system applications to electric power systems. Several knowledge engineering techniques that were motivated by power system applications are reviewed: (1) identification of relations among rules or chains of rules, (2) estimation of the worst case processing time of rule-based systems, and (3) the equivalence class method for validation and verification of rule-based systems. The first issue, relation checking, is considered the most practical among the three and, therefore, the subject is discussed extensively in this chapter. A general relation checking algorithm developed at the University of Washington is described. A representation of rule based systems in the attribute space is proposed. This representation is used to define several relations among rules. The relations defined are cause-effect, mutual exclusion, redundancy, conflict, subsumption and implication. A relation between a rule and a chain of rules is either complete, i.e. the relation holds for all instantiations of the rules, or partial, i.e. the relation holds only for some instantiations of the rules. An algorithm to detect relations between a new rule (to be added to the rule base) and rules in the rule base is developed. Example applications of this algorithm to rule-based systems are provided.
-
3 Object-oriented design and implementation of power system analysis software
- + Show details - Hide details
-
p.
45
–67
(23)
From the preliminary results, the SIMIAN architecture appears to be a workable and efficient system for power system modelling. Future work will investigate the effects of a scaling in the size of the network. The IEEE 30-Bus network is unrealistically small compared to typical distribution planning studies of 5000 nodes. The dynamic behaviour capability of the SIMIAN system was found to allow easy extension, whilst maintaining the object-oriented nature of the architecture. Integration of a GUI (graphical user interface) for browsing model parameters and topological representation of a network were both implemented using the dynamic function, and state machine functionality. The use of a common mechanism not only simplified the design but also enabled the resultant GUI classes to be constructed in a highly generic manner and as completely independent application objects. In porting the 'applications' to disparate hardware platforms, such as PCs, this latter ability requires that only this one portion need be ported - the object server application may remain on a workstation. In addition, the automatic updating of information between applications and the OODBMS was completed seamlessly through the event handling system. From this experience, it appears that more complex applications, for instance SCADA could be 'bolted-on' in a comparable manner.
-
4 Fuzzy logic and hybrid systems
- + Show details - Hide details
-
p.
68
–86
(19)
In this chapter, fundamentals of fuzzy logic and an overview of its applications in power systems are presented first. Then hybrid techniques are discussed in detail.
-
5 Alarm analysis
- + Show details - Hide details
-
p.
87
–108
(22)
In this chapter a real-time alarm handling and fault analysis (AHFA) expert system is described , this being seen as more than simply an alarm processor. AHFA is able to perform its diagnoses directly in real-time without recourse either to situation specific heuristics or to model-based 'generate and test'. The key is a novel form of abstraction, also described in this chapter. Also described here is an adaptive form of AHFA based on a learning classifier system (LCS), and this uses a fault simulator to direct the entire fault diagnosis. Unlike a conventional expert system, rules are not programmed into the LCS, although that is quite possible. On the contrary, the LCS is trained by example. The diagnostics are then adapted through genetic algorithms (GAs), which directly operate on the rule strings.This chapter is intended to give an overview of the problem area of alarm analysis for power system transmission, along with a couple of approaches to help tackle the problems using computer-based technology.
-
6 Artificial intelligence techniques for voltage control
- + Show details - Hide details
-
p.
109
–122
(14)
In the light of the review presented in this chapter, the following future requirements for reactive power control may be concluded: 1) Despite remarkable advances in mathematical optimisation technology, conventional methods have yet to achieve fast and reliable real-time reactive power control; considerable efforts are required to avoid mathematical traps such as ill-conditioning and convergence difficulties; 2) The experience of prototype expert systems applied to voltage control demonstrates that: (i) knowledge-based systems can enhance the capabilities of a power system in handling reactive power control; (ii) knowledge-based development methodologies are relevant to reactive power control; (iii)the application of hybrid systems is a novel development which represents a future trend in research; (iv)the application of fuzzy systems theory to voltage control requires further development, for example of techniques for rule sequencing and conflict resolution, before it can be considered for practical applications.
-
7 AI for protection systems
- + Show details - Hide details
-
p.
123
–142
(20)
The reliable operation of large power systems with small stability margins is highly dependent on control systems and protection devices. Progress in the field of microprocessor systems and demanding requirements in respect of the performance of protective relays are the reasons for digital device applications to power system protection. The superiority of numeric protection over its analogue alternatives is attributed to such factors as accurate extraction of the fundamental voltage and current components through filtering, functional benefits resulting from multi-processor design and extensive self-monitoring, etc. However, all these reasons have not led to a major impact on speed, sensitivity and selectivity of primary protective relays, and the gains are only marginal; this is so because conventional digital relays still rely on deterministic signal models and a heuristic approach for decision making, so that only a fraction of the information contained within voltage and current signals as well as knowledge about the plant to be protected is used.
-
8 Artificial neural networks for static security assessment
- + Show details - Hide details
-
p.
143
–191
(49)
The chapter gives a short introduction to static security assessment. It discusses merits and pitfalls of different artificial intelligence approaches, and then focuses on the application of artificial neural networks (ANN) to static security assessment by studying the nature of different supervised and unsupervised neural nets. Finally two examples will illustrate in more detail the application of multi-layer perceptrons and Kohonen's self-organising map to power system static security assessment.
-
9 Knowledge based systems for condition monitoring
- + Show details - Hide details
-
p.
192
–219
(28)
In this chapter the structured development of KBS for decision support roles in power system operation, control and monitoring will be considered. Three techniques, 'classical' KBS, CBR and MBR will be considered as potential complementary routes towards the implementation of decision support system functionality. Case studies of the application of these techniques in practical power systems applications will be described. While the use of these techniques has proven successful in isolation, the potential exists to combine them together with appropriate analytical support within an integrated decision support system. The chapter concludes with a discussion of a potential implementational framework for such a system, and the scope it provides for more flexible and user responsive decision support.
-
10 Scheduling maintenance of electrical power transmission networks using genetic programming
- + Show details - Hide details
-
p.
220
–237
(18)
The National Grid Company plc is responsible for the maintenance of the high voltage electricity transmission network in England and Wales. It must plan maintenance so as to minimise costs taking into account: (i) location and size of demand, (ii) generator capacities and availabilities, (iii) electricity carrying capacity of the remainder of the network, i.e. that part not undergoing maintenance. Previous work showed the combination of a genetic algorithm using an order or permutation chromosome combined with hand coded 'greedy' optimisers can readily produce an optimal schedule for a four node test problem [10]. Following this the same GA has been used to find low cost schedules for the South Wales region of the UK high voltage power network. This chapter describes the evolution of the best known schedule for the base South Wales problem using genetic programming starting from the hand coded heuristics used with the GA.
-
11 Neuro-expert system applications in power systems
- + Show details - Hide details
-
p.
238
–258
(21)
In this chapter we outline a generic neuro-expert system (GENUES) architecture for hybrid reasoning. The architecture consists of five phases, namely, decomposition phase, control phase, decision phase, preprocessing phase, and postprocessing phase. The architecture is particularly applicable in time critical diagnostic/classification domains and data intensive domains in general. We describe the application of GENUES in a real time alarm processing system in a power system control centre.
-
12 Intelligent systems for demand forcasting
- + Show details - Hide details
-
p.
259
–279
(21)
Electricity demand forecasting within the National Grid Company (NGC) is carried out using various mathematical models. These models use comprehensive weather forecasts supplied by the UK Meteorological Office to provide short-term demand forecasts. These demand forecasts then become the vital input to schedule plant in merit order from 15 minutes to 36 hours ahead. Longer-term demand forecasts are also carried out for planning and business purposes up to five years ahead. The NGC is required to produce demand forecasts for operational, endurance and business planning in order to match generation output with demand. The National Grid system operates at 400,000 volts (400 kV) and 275,000 volts (275 kV) and enables the transmission of electrical energy across England and Wales to the customer. The flexibility of the National Grid system enables the daily and seasonal variations in customer demand for electricity and changing patterns of generation to be satisfied.
-
13 A practical application and implementation of adaptive techniques using neural networks into autoreclose protection and system control
- + Show details - Hide details
-
p.
280
–299
(20)
Reyrolle Protection have carried out research in conjunction with Bath University into applying adaptive techniques to autoreclose schemes and have produced an algorithm based on an artificial neural network which can recognise when it is 'safe to reclose' and when it is 'unsafe to reclose'. This algorithm is based on examination of the induced voltage on the faulted phase and by applying pattern recognition techniques determines when the secondary arc extinguishes. Significant operational advantages can now be realised using this technology resulting in changes to existing operational philosophy. Conventional autoreclose relays applied to the system have followed the philosophy of 'reclose to restore the system', but a progression from this philosophy to 'reclose only if safe to do so' can now be made using this adaptive approach. With this adaptive technique the main requirement remains to protect the investment i.e. the system, by reducing damaging shocks and voltage dips and maintaining continuity of supply.
-
Back Matter
- + Show details - Hide details
-
p.
300
(1)
Related content
