Correlation knowledge extraction based on data mining for distribution network planning

Traditional distribution network planning relies on the professional knowledge of planners,especially when analyzing the correlations between the problems existing in the network and the crucial influencing factors.The inherent laws reflected by the historical data of the distribution network are ignored,which affects the objectivity of the planning scheme.In this study,to improve the efficiency and accuracy of distribution network planning,the characteristics of distribution network data were extracted using a data-mining technique,and correlation knowledge of existing problems in the network was obtained.A data-mining model based on correlation rules was established.The inputs of the model were the electrical characteristic indices screened using the gray correlation method.The Apriori algorithm was used to extract correlation knowledge from the operational data of the distribution network and obtain strong correlation rules.Degree of promotion and chi-square tests were used to verify the rationality of the strong correlation rules of the model output.In this study,the correlation relationship between heavy load or overload problems of distribution network feeders in different regions and related characteristic indices was determined,and the confidence of the correlation rules was obtained.These results can provide an effective basis for the formulation of a distribution network planning scheme.

Distribution network planning based on shortest path

In order to form an algorithm for distribution network routing,an automatic routing method of distribution network planning was proposed based on the shortest path.The problem of automatic routing was divided into two steps in the method:the first step was that the shortest paths along streets between substation and load points were found by the basic ant colony algorithm to form a preliminary radial distribution network,and the second step was that the result of the shortest path was used to initialize pheromone concentration and pheromone updating rules to generate globally optimal distribution network.Cases studies show that the proposed method is effective and can meet the planning requirements.It is verified that the proposed method has better solution and utility than planning method based on the ant colony algorithm.

Models and Methods for Urban Power Distribution Network Planning

The models, methods and their application experiences of a practical GIS(geographic information system)-based computer decision-making support system of urban power distribution network planning with seven subsystems,termed CNP,are described.In each subsystem there is at least one or one set of practical mathematical methobs.Some new models and mathematical methods have been introduced.In the development of CNP the idea of cognitive system engineering has been insisted on,which claims that human and computer intelligence should be combined together to solve the complex engineering problems cooperatively.Practical applications have shown that not only the optimal plan can be automatically reached with many complicated factors considered, but also the computation,analysis and graphic drawing burden can be released considerably.

Distribution Network Equipment Location and Capacity Planning Method Considering Energy Internet Attribute from the Perspective of Life Cycle Cost

For facing the challenges brought by large-scale renewable energy having access to the system and considering the key technologies of energy Internet,it is very necessary to put forward the location method of distribution network equipment and capacity from the perspective of life cycle cost.Compared with the traditional energy network,the equipment capacity problem of energy interconnected distribution network which involves in electricity network,thermal energy network and natural gas network is comprehensively considered in this paper.On this basis,firstly,the operation architecture of energy interconnected distribution network is designed.Secondly,taking the grid connection location and configuration capacity of key equipment in the system as the control variables and the operation cost of system comprehensive planning in the whole life cycle as the goal,the equipment location and capacity optimization model of energy interconnected distribution network is established.Finally,an IEEE 33 bus energy mutual distribution grid system is taken for example analysis,and the improved chaotic particle swarmoptimization algorithm is used to solve it.The simulation results show that the method proposed in this paper is suitable for the equipment location and capacity planning of energy interconnected distribution network,and it can effectively improve the social and economic benefits of system operation.

Distribution Network Expansion Planning Based on Multi-objective PSO Algorithm

This paper presents a novel approach for electrical distribution network expansion planning using multi-objective particle swarm optimization (PSO). The optimization objectives are: investment and operation cost, energy losses cost, and power congestion cost. A two-phase multi-objective PSO algorithm is employed to solve this optimization problem, which can accelerate the convergence and guarantee the diversity of Pareto-optimal front set as well. The feasibility and effectiveness of both the proposed multi-objective planning approach and the improved multi-objective PSO have been verified by the 18-node typical system.

Integrated Planning of an Active Distribution Network and DG Integration in Clusters Considering a Novel Formulation for Reliability Assessment

The concept of DG clusters is introduced with highly penetrated integration of distributed generation(DG)into active distribution networks(ADNs).DG clusters are referred to as parts of an ADN,including DGs,distribution lines and loads.The formation of DG clusters helps to optimally dispatch DG outputs within ADNs.In this regard,an integrated planning strategy of ADNs and DGs in cluster(IPNDGC)is proposed.In order to guarantee that the planning strategy meets the reliability requirements,a reliability assessment is considered in the proposed model.However,reliability assessment is generally accomplished according to a fixed network topology and known DG allocation,which makes it difficult to integrate reliability into planning models.To deal with this difficulty,a novel formulation method for reliability assessment is proposed considering the network topology uncertainties and isolated operating probabilities of DG clusters.The reliability index(RI)represented by expected customer interruption cost(ECOST)is employed in the proposed planning model.The planning model is formulated as a mixed integer second order conic programming planning model.An actual distribution system is employed to illustrate the accuracy and efficiency of the proposed planning model.

Reliability assessment in active distribution networks with detailed effects of PV systems

With the increased integration of photovoltaic(PV)power generation into active distribution networks,the operational challenges and their complexities are increased.Such networks need detailed characterization PV systems under multiple operating conditions to understand true impacts.This paper presents a new mathematical model for a PV system to capture detailed effects of PV systems.The proposed model incorporates state transitions of components in a PV system and captures effects of insolation variations.The paper performs a reliability assessment incorporating PV systems at resource locations.The results suggest that the reliability performance of an active distribution network at stressed operating conditions might be influenced by the high penetration of PV system.Reliability performance of distribution networks that are high penetrated with PV systems can be affected by cloudy effects resulting from insolation variations.The proposed model can be used to quantify the level of reduction in reliability,resulting with cloudy effects.

An Optimal Expansion Planning of Electric Distribution Network Incorporating Health Index and Non-network Solutions

The health status of distribution equipment and networks is not considered directly in existing distribution network planning methods.In order to effectively consider the health status and deal with the risk associated with load and renewable generation uncertainties,this paper presents a new optimal expansion planning approach for distribution network(EPADN)incorporating equipment’s health index(HI)and non-network solutions(NNSs).HI and relevant risk are used to help develop the optimal equipment replacement strategy and temporary NNSs are considered as promising options for handling the uncertainties of load growth,reliability requirements of power supply and output of distributed energy resources(DERs)at a lower cost than network alternatives.An EPADN model using network solutions(NSs)and NNSs is proposed.The planning objectives of the proposed model are safety,reliability,economy,and‘greenness’that are also the meaning of distribution network HI.A method integrating an improved niche genetic algorithm(INGA)and a spanning tree algorithm(STA)is fitted to solve the model presented here for real sized networks with a manageable computational cost.Simulation results of an actual 22-node distribution network in China,illustrate the effectiveness of the proposed approach.

An Efficient Substation Placement and Sizing Strategy Based on GIS Using Semi-supervised Learning

As load and renewable penetration continues to grow,optimal placement and sizing of substations is becoming increasingly important in distribution system planning.This paper presents an improved methodology to solve the substation siting and sizing problem based on geographic information and supervised learning.The proposed approach can optimize the locations,capacities,and power supply ranges of substations with minimum investment and annual operation costs.Capital cost of land adds complexity and difficulty to the substation placement problem,especially for highly developed urban areas.This paper presents a theoretical framework to determine the optimal location of substations considering the cost of land.The state-of-the-art parallel computing techniques are employed so that co-optimization for substations of multiple voltage levels can be directly conducted in a computational efficient way.Case studies are presented to demonstrate the effectiveness of the proposed approach.