Collective Entity Alignment for Knowledge Fusion of Power Grid Dispatching Knowledge Graphs

Knowledge graphs(KGs)have been widely accepted as powerful tools for modeling the complex relationships between concepts and developing knowledge-based services.In recent years,researchers in the field of power systems have explored KGs to develop intelligent dispatching systems for increasingly large power grids.With multiple power grid dispatching knowledge graphs(PDKGs)constructed by different agencies,the knowledge fusion of different PDKGs is useful for providing more accurate decision supports.To achieve this,entity alignment that aims at connecting different KGs by identifying equivalent entities is a critical step.Existing entity alignment methods cannot integrate useful structural,attribute,and relational information while calculating entities’similarities and are prone to making many-to-one alignments,thus can hardly achieve the best performance.To address these issues,this paper proposes a collective entity alignment model that integrates three kinds of available information and makes collective counterpart assignments.This model proposes a novel knowledge graph attention network(KGAT)to learn the embeddings of entities and relations explicitly and calculates entities’similarities by adaptively incorporating the structural,attribute,and relational similarities.Then,we formulate the counterpart assignment task as an integer programming(IP)problem to obtain one-to-one alignments.We not only conduct experiments on a pair of PDKGs but also evaluate o ur model on three commonly used cross-lingual KGs.Experimental comparisons indicate that our model outperforms other methods and provides an effective tool for the knowledge fusion of PDKGs.

Novel Affine Power Flow Method for Improving Accuracy of Interval Power Flow Data in Cyber Physical Systems of Active Distribution Networks

A large number of load power and power output of distributed generation in an active distribution network(ADN)are uncertain,which causes the classical affine power flow method to encounter problems of interval expansion and low efficiency when applied to an AND.This then leads to errors of interval power flow data sources in the cyber physical system(CPS)of an ADN.In order to improve the accuracy of interval power flow data in the CPS of an ADN,an affine power flow method of an ADN for restraining interval expansion is proposed.Aiming at the expansion of interval results caused by the approximation error of non-affine operations in an affine power flow method,the approximation method of the new noise source coefficient is improved,and it is proved that the improved method is superior to the classical method in restraining interval expansion.To overcome the decrease of computational efficiency caused by new noise sources,a novel merging method of new noise sources in an iterative process is designed.Simulation tests are conducted on an IEEE 33-bus,PG&E 69-bus and an actual 1180-bus system,which proves the validity of the proposed affine power flow method and its advantages in terms of computational efficiency and restraining interval expansion.

Multi-objective Coordination Control of Distributed Power Flow Controller

In this paper,distributed power flow controller(DPFC)constraints are analyzed.The energy balance relationship between fundamental wave and third harmonic in series and shunt-side converter is deduced.A proportional integral(PI)controller of the DPFC is constructed.The PI controller uses the voltage amplitude and phase angle injected into the system in the series side,along with the modulation ratio of the three-phase converter on the shunt side as the control variables.A multiobjective coordinated control equation is proposed,which factors the constraints of the energy balance between series and shunt side,device capacity limit,safe operation limit,fundamental component,as well as third harmonic component of the injection voltage at the series side.The equation minimizes the variance between the actual value of the control target and its given value to ensure that the DC capacitor voltage,both in the series and shunt side,is stable at target value.Simulations are conducted to verify correctness and effectiveness of the proposed control method.

Estimating life-cycle energy payback ratio of overhead transmission line toward low carbon development

The energy conservation plays an important role for low carbon development.In order to evaluate the energy conservation in the full life-cycle,a scheme to estimate the energy consumption,or alternatively the energy pay,in constructing an overhead transmission line is proposed in this paper.The analysis of a typical projection is given for demonstration.With new additional overhead transmission lines,the energy consumption,known as the power loss in power network,is expected to be decline,which is defined in this paper as the energy payback.In order to estimate this kind of contribution,the scheme that consisted of load forecast,production simulation for generating systems,load flow simulation and power loss calculation has been proposed.Case studies,based on the IEEE 24-bus test system,are given to demonstrate the efficacy of the schemes.Moreover,several presumptive scenarios are deployed and analysed with the presented schemes for comparison.

Renewable Scenario Generation Using Controllable Generative Adversarial Networks with Transparent Latent Space

With the growing penetration of renewable energysources in power systems, it becomes increasingly important tocharacterize their inherent variability and uncertainty. Scenariogeneration is a key approach to provide a series of possible powerscenarios in the future for the system planner and operator tomake decisions. In this paper, a data-driven method is presentedfor renewable scenario generation using stable and controllablegenerative adversarial networks with transparent latent space(ctrl-GANs). The machine learning based algorithm can capturethe nonlinear and dynamic renewable patterns without the needfor modeling assumptions and complicated sampling techniques.The orthogonal regularization and spectral normalization areadopted to improve the training stabilization of the GAN model.To control the generation process, a relationship is built betweenfeatures of the generated scenarios and latent vectors on themanifold. Moreover, several new metrics for GANs are used toevaluate the quality of the scenarios. The proposed approachis applied to generate realistic time series data of wind andphotovoltaic power. The results demonstrate that our methodhas a better performance on numerical stabilization and is ableto control the generation process with latent space.