In order to improve the science of grid equipment overhaul and decommissioning decisions, a collaborative optimization method of equipment overhaul/decommissioning strategy considering system effectiveness and risk is proposed. The interaction effect between overhaul and decommissioning is analysed from the perspective of system effectiveness, and 2 attributes of integrated cost input and system reliability improvement are proposed, and then a prospect model with cost/benefit attributes is established based on the prospect theory. Then, with the maximum integrated prospect value as the optimization objective, a collaborative optimization model of overhaul/decommissioning strategy is established with the system risk level as the constraint. Finally, the effectiveness of the proposed method is verified by taking the transformer equipment of an urban area distribution network as an example.
Accurate short-term load forecasting can alleviate the contradiction between power supply and demand,coor-dinate load management and ensure power system security.Short-term power load had strong nonlinearity and time de-pendence,and was related to many external factors such as climate change and real-time electricity price,which made it difficult to accurately predict short-term power load.Therefore,we proposed a short-term power load forecasting method based on TPA(temporal pattern attention)mechanism of CNN(convolutional neural network)-BiGRU(bidi-rectional gated recurrent unit).Among them,the convolutional neural network was used to mine the nonlinear spatial relation between different input variables and the current load,bidirectional gated recurrent unit was used to capture long-term dependencies from time series,and temporal pattern attention mechanism was introduced to assign feature weights,thus highlighting important information and achieving short-term load prediction.Taking the Australian public load data set as an example to verify the effect of the proposed method,the prediction accuracy reached 97.651％,and comparing with the CNN-LSTM and RNN prediction models,the accuracy was increased by 0.531％and 5.992％re-spectively.The experimental results show that the proposed TPA-CNN-BiGRU prediction method has higher prediction accuracy and universality.
Captive heating plants are crowding the system baseload,and many captive heating plants in most provinces are not required to participate in peaking regulation.Therefore,in the 14th Five-Year Plan period,when the peaking capacity of the system is getting tighter,we studied the new challenges of captive heating plants under the carbon and renewable energy quotas.Firstly,we proposed a model to free up peaking space for captive heating plants in the north-ern winter heating period.Secondly,the contribution of the trading agents to the alliance was analyzed,and a multi-factor improved Shapley value profit distribution model was established.Then,the generalized analytic programming method and segmented linearization method were used to transform the nonlinear model into a mixed-integer linear mod-el,and the solver was used to solve the model.Finally,the correctness of the model was verified by simulation,and the impact of carbon trading price on the trading results was explored to alleviate the shortage of peaking in the power system during the transitional period of power reform and to provide benefits for captive heating plants.
The flexibility reformation of the heating unit is an effective measure to break the"heat-power constraints"and realize the capacity support of the coal-fired power unit for renewable energy power generation.The most common technical solution is the steam turbine low-pressure cylinder operates under zero output condition with HP-LP bypass steam extraction or electric boiler supplying heat.For a 350 MW supercritical heating unit,we adopted the iterative calculation method of variable working conditions to compute and compared the typical operating points thermal economy of the minimum power output,maximum heat supply and heat preservation and power regulation under the two schemes,as well as the adjustable range of electric output in thermal economy of the deep peak load section.The re-sults show that,due to the small cold source loss,the coal consumption of the electric boiler scheme is only slightly lar-ger than that of the HP-LP bypass steam extraction scheme under the same thermal and electric load conditions.While for the good reverse electric load regulation capability of electric boiler,the adjustable range of electric load is signifi-cantly larger than that of the HP-LP bypass steam extraction scheme.
In order to improve the flexibility of unit peak shaving and reduce carbon emissions,we built a optimal dis-tribution model of revenue and load of cogeneration unit,and obtained the distribution strategy,revenue and carbon e-mission characteristics of cogeneration unit.We selected four operation scenarios of two 350 MW units,used the evolu-tionary algorithm EA to optimize the thermoelectric load distribution with the goal of maximum overall income and mini-mum carbon emission of the units,and obtained the income and reasons of the four operation scenarios;We also de-fined the uneven distribution of thermoelectric load of two units,and investigated the influences of uneven distribution of thermoelectric load on the total income of units under four scenarios.It provides a reference for efficient and low-car-bon load optimal distribution and flexible operation of cogeneration units.
