Search

CN-122022883-A - Dual-dimension electric power spot market quotation system and method based on tide and competition

CN122022883ACN 122022883 ACN122022883 ACN 122022883ACN-122022883-A

Abstract

The invention discloses a power flow and competition-based two-dimensional power spot market quotation system, which comprises a data input module, an intelligent decision unit, a market clearing simulation unit and a quotation output module, wherein the data input module is used for receiving, analyzing, verifying and formatting data required by quotation optimization from heterogeneous data sources, the intelligent decision unit is used for receiving the data from the data input module or the simulation result of the market clearing simulation unit to generate an adjusted quotation curve, the market clearing simulation unit is used for simulating the clearing process of a real power market, and the quotation output module is used for converting the final optimized quotation curve calculated by the intelligent decision unit from the internal data structure of the system into a standard format which accords with the technical specifications of a power market operator and outputting the final optimized quotation curve to a market trading platform. The invention can improve the defects of the prior art and increase the accuracy of quotation.

Inventors

  • HUANG YU
  • XU BO

Assignees

  • 华北电力大学（保定）

Dates

Publication Date
20260512
Application Date
20260115

Claims (6)

  1. 1. A power spot market quotation system based on tide and competition is characterized by comprising, The data input module is used for receiving, analyzing, verifying and formatting data required by quotation optimization from heterogeneous data sources; The intelligent decision unit is used for receiving the data from the data input module or the simulation result of the market clearing simulation unit and generating an adjusted quotation curve; The market clearing simulation unit is used for simulating the clearing process of the real electric power market; And the quotation output module is used for converting the final optimized quotation curve calculated by the intelligent decision unit from the internal data structure of the system into a standard format conforming to the technical specifications of the electric power market operators and outputting the final optimized quotation curve to the market trading platform.
  2. 2. The power flow and competition based two-dimensional power spot market quotation system of claim 1, wherein the data input module processes data types comprising, The static data of the power grid comprises a network topological structure of a node connection relation, reactance and thermal stability limits of a line, and minimum technical output of a generator set, maximum technical output, climbing rate, landslide rate and cost curves of the generator set; market dynamics data including a system load prediction curve for a future 24 hours, a renewable energy output prediction curve, and a demand for auxiliary services; competitor data including real-time market published adversary offers, historical offer databases, adversary intelligence obtained through third party subscriptions.
  3. 3. The power flow and competition based two-dimensional power spot market quotation system according to claim 1, wherein the target function of the market clearing simulation unit is that Wherein t is a period set, i is a conventional genset set, Is the conventional unit i outputting force The quotation cost VOLL is the power supply loss value, Is the amount of load reduction of node i during period t, Is that the j output of the gas unit is The power generation cost at the time; the constraints are as follows, Node power balancing constraints-ensuring that the power injection of each node at each instant is equal to the power outflow, , Wherein, the Is a set of generators connected to node k, And Respectively the charge and discharge power of the energy storage unit, Is the wind power output of the node k, Is the load demand of node k, Is the flow of lines from node k to node j, the constrained dual variable The node marginal electricity price of the node k in the period t is obtained; The power transmission line tide constraint, based on tide model, limiting the power transmission on the line not to exceed the physical limit, , , Wherein, the Is the susceptance of the line ij, Is the voltage phase angle of node i, Is the upper limit of the transmission capacity of the line ij, and when the line power flow reaches the upper limit, the constraint becomes a tight constraint, and the blocking is generated and the LMP of the related node is directly affected; The unit operation constraint comprises the upper and lower limits of the output force of the generator unit The system comprises an energy storage unit, a climbing rate constraint, a landslide rate constraint, a charge state updating constraint of the energy storage unit, a charge and discharge power limit and a mutual exclusion constraint.
  4. 4. A method of bidding based on a trend and competition two-dimensional electric power spot market bidding system as claimed in any one of claims 1-3, characterized by the steps of: The data input module acquires power grid static data, market dynamic data and competitor data, and generates a conservative initial segmentation quotation strategy for the target generator set after acquisition is completed; The intelligent decision unit generates an adjusted quotation curve according to the data of the data input module; the market clearing simulation unit executes a primary market clearing simulation operation according to the quotation curve; The intelligent decision unit analyzes the simulation result, the expected profit obtained by the machine-selected target unit in the round of simulation and the blocking index of the key power transmission line connected with the node where the target unit is located are defined as follows Where L is the set of critical lines, Is the actual power flow of the line i, Is its upper transmission limit; The intelligent decision unit generates a quotation curve according to the analysis result of the simulation result, and when the expected profit of the quotation curve is compared with the expected profit of the last iteration, the expected profit increment is greater than or equal to a preset threshold value, or the iteration number reaches a preset upper limit, the latest quotation curve is sent to the quotation output module; The quotation output module converts the final optimized quotation curve from the system internal data structure into a standard format conforming to the technical specifications of the electric power market operators and outputs the final optimized quotation curve to the market trading platform.
  5. 5. The bidding method based on the trend and competition two-dimensional power spot market bidding system of claim 4, wherein: the intelligent decision unit generating the offer curve comprises the steps of, Neural network encoder processes input time series of historical market data For each time step t, a hidden state is generated Aggregation of hidden states Representing encoded information from the entire input sequence; using a feed forward neural network for each hidden state Calculating an alignment score The alignment score quantifies the correlation of the information of the time step t with the current prediction task, Wherein 、 And Is a learnable weight parameter; Normalizing score to attention weight using softmax function , , Is a value between 0 and 1, and ; The context vector c is a weighted average of the encoder hidden states, ; Inputting the context vector c into a neural network decoder to generate a quotation curve; with initial quotation curve, initial temperature T, cooling rate and maximum number of iterations Starting iterative calculation of new quotation curve, and according to step length in kth iteration The offer curves are updated and the offer curves are updated, , As the temperature at the kth iteration, The adjustment amount is preset; Calculating a new profit from the new quotation curve, receiving the new quotation curve if the new profit is greater than the profit at the previous iteration, otherwise receiving the new quotation curve according to the probability p, , Profit difference for two adjacent iterative processes; After each iteration, the temperature is reduced according to the cooling plan, , When the temperature is Down to a preset threshold or iterate to a maximum number of iterations And outputting the current quotation curve as a final optimized quotation curve.
  6. 6. The method for quoting a two-dimensional power spot market quotation system based on trend and competition according to claim 5, wherein the preset adjustment amount is For the dynamic adjustment, the calculation method is that, , Wherein, the For a preset adjustment of the kth iteration, For a preset adjustment of the k +1 iteration, In order to be a step size, As the weight of the material to be weighed, And U is a preset adjustment quantity reference function, wherein the gradient is the gradient in the direction of the fastest change rate of the current quotation and the initial quotation after the kth iteration.

Description

Dual-dimension electric power spot market quotation system and method based on tide and competition Technical Field The invention relates to the technical field of competitive price trading of an electric power market, in particular to a system and a method for quoting a double-dimension electric power spot market based on tide and competition. Background In the context of power market reform, the current market now becomes the core platform for resource allocation. The power generation enterprises serve as independent market subjects, and the profit mode of the power generation enterprises is changed from traditional planned power generation to gain benefits through market bidding. In this mode, the power generation business needs to submit a segmented price quotation curve consisting of a plurality of capacity-price pairs for each period of 24 hours in the future. And the market operation mechanism performs unified optimization and clearing by using a complex market clearing model and taking the minimum social electricity purchasing cost as a target, and finally determines the winning bid output of each unit and the LMP of each node. Therefore, the quotation strategy which can accurately respond to market signals, fully utilize physical constraint and effectively cope with competition is the core competitiveness of power generation enterprises for survival and development in the market. The prior art has several technical drawbacks in terms of power spot market quotation strategies. Firstly, the existing quotation method cannot effectively couple physical power flow constraint of a power grid with a market economic competition model, so that the existing quotation method cannot accurately respond to local market price signals generated by physical conditions such as line blockage, and the like, so that not only is calculation accuracy insufficient, but also great potential economic benefits are missed. Secondly, in the prior art, when facing the market environment with uncertain quotation information of competitors, a systematic framework capable of adaptively switching decision logic according to information transparency is lacking, so that the robustness of the generated quotation strategy is poor, and the dynamic variability of the real market is difficult to adapt. In addition, most of the existing methods adopt a static or single-time optimized open-loop decision mode, and lack of a closed-loop iteration mechanism capable of feeding back, learning and correcting according to market clearing results, so that the optimization depth is insufficient, and the optimal solution cannot be continuously approximated. Disclosure of Invention The invention aims to solve the technical problem of providing a system and a method for quoting a power spot market based on trend and competition, which can solve the defects of the prior art and improve the accuracy of quotation. In order to solve the technical problems, the technical scheme adopted by the invention is as follows. A power spot market quotation system based on tide and competition comprises, The data input module is used for receiving, analyzing, verifying and formatting data required by quotation optimization from heterogeneous data sources; The intelligent decision unit is used for receiving the data from the data input module or the simulation result of the market clearing simulation unit and generating an adjusted quotation curve; The market clearing simulation unit is used for simulating the clearing process of the real electric power market; And the quotation output module is used for converting the final optimized quotation curve calculated by the intelligent decision unit from the internal data structure of the system into a standard format conforming to the technical specifications of the electric power market operators and outputting the final optimized quotation curve to the market trading platform. Preferably, the data input module processes data types including, The static data of the power grid comprises a network topological structure of a node connection relation, reactance and thermal stability limits of a line, and minimum technical output of a generator set, maximum technical output, climbing rate, landslide rate and cost curves of the generator set; market dynamics data including a system load prediction curve for a future 24 hours, a renewable energy output prediction curve, and a demand for auxiliary services; competitor data including real-time market published adversary offers, historical offer databases, adversary intelligence obtained through third party subscriptions. Preferably, the objective function of the market clearing simulation unit is thatWherein t is a period set, i is a conventional genset set,Is the conventional unit i outputting forceThe quotation cost VOLL is the power supply loss value,Is the amount of load reduction of node i during period t,Is that the j output of the gas unit isThe power generation cost at the