Electricity price optimization method considering efficiency improvement of time-sharing and active power distribution network

Abstract

The invention discloses an electricity price optimization method considering the efficiency improvement of a time-sharing and active power distribution network, and the method comprises the steps: building an electricity price optimization model considering the efficiency improvement of the time-sharing and active power distribution network, solving the electricity price optimization model through the cooperation of a QPSO algorithm, a simulated annealing algorithm and a group leapfrog algorithm, and obtaining an optimal electricity price optimization strategy. According to the method, the electricity price optimization model is solved by fusing the quantum behavior particle swarm optimization (QPSO) algorithm, the simulated annealing algorithm and the group frog leaping algorithm (SFLA) for cooperative work, a multi-dimensional optimization strategy is formed, and an efficient and accurate solution is provided for electricity price optimization and electricity consumption prediction. Efficient utilization of energy and economic benefits can be achieved, and meanwhile theoretical and method support is provided for sustainable development of an electric power system.

Description

Technical Field

[0001] The present invention belongs to the technical field of power distribution networks, and in particular relates to an electricity price optimization method considering time-sharing and active power distribution network efficiency improvement. Background Art

[0002] With the continuous development of the global economy and the accelerated urbanization process, the rapid growth of electricity demand has become a major challenge facing energy management around the world. Traditional power systems have many problems such as low energy efficiency, unstable grid operation, and large fluctuations in electricity prices. These problems not only hinder the effective use of energy, but also restrict the sustainable development of the economy. In order to meet such challenges, relevant research is increasingly focused on how to improve energy allocation and cost management by optimizing electricity price strategies and improving the accuracy of electricity consumption forecasts. Particle swarm optimization (PSO), as a global optimization algorithm that simulates the foraging behavior of bird flocks, has shown great potential in power system optimization problems.

[0003] In the current field of power system optimization, although the particle swarm optimization algorithm (PSO) has attracted widespread attention due to its potential in solving complex power system optimization problems, there are still some technical problems that need to be solved. When dealing with power price optimization problems, the traditional PSO algorithm may fall into the local optimal solution and lacks sufficient exploration of the problem space, which leads to a decrease in search efficiency. The algorithm's inertia weight and learning factor are fixed and cannot adapt to the dynamically changing power market environment, which limits its global search capability and the convergence speed of the algorithm. Summary of the invention

[0004] The purpose of the present invention is to solve the shortcomings of the above-mentioned background technology and provide an electricity price optimization method taking into account time-sharing and active distribution network efficiency improvement to achieve more efficient, flexible and accurate power system optimization.

[0005] The technical solution adopted by the present invention is: an electricity price optimization method considering time-sharing and active distribution network efficiency improvement, establishing an electricity price optimization model considering time-sharing and active distribution network efficiency improvement, using QPSO algorithm, simulated annealing algorithm and group frog leaping algorithm to work together to solve the electricity price optimization model, and obtain the optimal electricity price optimization strategy. The solution process is as follows:

[0006] Using the electricity price setting scheme as a particle, set the initialization parameters of the electricity price optimization model, including setting the number of particles, the maximum number of iterations, the inertia weight, and the learning factor;

[0007] Obtain electricity price data and perform preprocessing and feature screening;

[0008] Initialize the position and velocity of the particles through the QPSO algorithm based on the initialization parameters and the screened features, and optimize and update the particle velocity and position until the maximum number of iterations is reached;

[0009] During the optimization process, the quantum behavior mechanism is introduced through the quantum potential well model to increase the randomness and diversity of the particle search trajectory. The inertia weight and learning factor are dynamically adjusted according to the changes in electricity prices and distribution network efficiency. The simulated annealing algorithm is used for local search in each sub-population, and the group frog leaping algorithm is used to enhance the local search capability of the QPSO algorithm.

[0010] The optimal solution in the optimization process is taken as the optimal electricity price optimization strategy.

[0011] Furthermore, an electricity price optimization model is constructed with the optimization of economic cost, user cost, system stability and environmental cost as the objective function and the supply and demand balance and cost-effectiveness of the electricity market as constraints.

[0012] Furthermore, the objective function is

[0013] min J=a·C economic +b·C user +c·C stability +d·C environment

[0014] Among them, C cconomic is the economic cost, C user is the user cost, C stability is the system stability, C cnvironment is the environmental cost, a, b, c, and d are the weight coefficients of economic cost, user cost, system stability, and environmental cost, respectively.

[0015] Furthermore, the constraint condition is

[0016] Supply ≥ Demand;

[0017] P min ≤P(n)≤P max ;

[0018] |P(n)-P historical (n)|≤ε;

[0019] Among them, Supply is supply, Demand is demand, P(n) is the electricity price at time (or moment) n, P historical (n) is the historical electricity price for the same period, ε is the allowable deviation, P min , P max are the maximum and minimum values ​​of the calibrated electricity price respectively.

[0020] Furthermore, the preprocessing includes performing missing data, outlier detection and data normalization processing on the electricity price data.

[0021] Furthermore, the feature screening is to screen out the features with the greatest predictive power for electricity price forecasting from the preprocessed data, and the screened features include time characteristics, market conditions, historical electricity prices and environmental factors.

[0022] Furthermore, the QPSO algorithm creates multiple sub-populations for parallel optimization search during the optimization process, and updates the best solution found in the entire population and each sub-population; each sub-population independently explores different areas of the solution space, and works together by sharing information between groups to jointly approach the global optimal solution.

[0023] Furthermore, the particle velocity and position are updated by the following formula:

[0024]

[0025] in, is the velocity of particle i at iteration t+1, is the velocity of particle i at the tth iteration, w is the inertia weight, c1 and c2 are the first learning factor and the second learning factor, rand1 and rand2 are the first random number vector and the second random number vector uniformly distributed in the interval [0,1], respectively. is the optimal position of particle i, is the best position globally. is the position of particle i at iteration t, is the position of particle i at the t+1th iteration, is the position of particle i at iteration t.

[0026] Furthermore, the quantum potential well model is:

[0027]

[0028] in, is the potential energy of particle i at the t+1th iteration, D is the dimension of the problem, m j and ω j are the particle mass and angular frequency in dimension j, is the position coordinate of particle i in dimension j at the t+1th iteration, j is the number of dimensions of the exploration space, is the wave function of the position of particle i at the t+1th iteration, and σ is the standard deviation of the wave function.

[0029] Furthermore, the local search capability of the algorithm is enhanced by the group frog leaping algorithm through the following formula:

[0030]

[0031] Among them, x ij (t+1) is the position of particle i at the t+1th iteration in dimension j, X ij (t) is the position of particle i in the jth dimension at the tth iteration, α and β are the first tuning parameter and the second tuning parameter, T is the randomization step size, best ij is the local optimal solution of particle i in dimension j, is the global optimal solution of particle i in dimension j.

[0032] The beneficial effects of the present invention are:

[0033] The present invention proposes an innovative electricity price optimization method by comprehensively considering Time-of-Use (ToU) pricing and active distribution network efficiency improvement to optimize electricity costs and improve system response speed. By integrating the quantum-behaved particle swarm optimization algorithm (QPSO), simulated annealing algorithm and swarm frog leaping algorithm (SFLA), a multi-level and multi-dimensional optimization strategy is formed, which provides an efficient and accurate solution for electricity price optimization and electricity consumption forecasting, helps to achieve efficient utilization of energy and economic benefits, and provides theoretical and methodological support for the sustainable development of the power system.

[0034] The optimization method of the present invention integrates the multimodal simulated annealing algorithm (MMSA) as a local search algorithm. Through the multi-path parallel annealing process, it effectively avoids the local optimal solution and improves the quality of the local optimization results. The integration of SFLA combines the global search and local optimization strategies by simulating the jumping behavior of frog groups, thereby improving the search efficiency of the algorithm and the quality of the solution.

[0035] The innovative multi-algorithm fusion strategy of the present invention not only significantly optimizes energy cost management and reduces electricity price fluctuations, but also improves system response speed, providing theoretical and methodological support for the sustainable development of the power system. It is expected to be widely used in the power market and promote the modernization and intelligence of energy management. BRIEF DESCRIPTION OF THE DRAWINGS

[0036] Figure 1 It is a flow chart of the present invention. DETAILED DESCRIPTION

[0037] The specific embodiments of the present invention are further described below in conjunction with the accompanying drawings. It should be noted that the description of these embodiments is used to help understand the present invention, but does not constitute a limitation of the present invention. In addition, the technical features involved in the various embodiments of the present invention described below can be combined with each other as long as they do not conflict with each other.

[0038] like Figure 1 As shown, the present invention provides an electricity price optimization method considering time-sharing and active distribution network efficiency improvement, aiming to optimize electricity costs and improve system response speed by comprehensively considering time-of-use (ToU) pricing and active distribution network efficiency improvement, including the following steps:

[0039] Step S1: Establish an electricity price optimization model considering time-sharing and active distribution network efficiency improvement.

[0040] An electricity price optimization model is constructed with the optimization of economic cost, user cost, system stability and environmental cost as the objective function and the supply and demand balance and cost-effectiveness of the electricity market as constraints.

[0041] The objective function is

[0042] min J=a·C economic +b·C user +c·C stabiliry +d·C environment

[0043] Among them, C economic is the economic cost, reflecting the balance between electricity supply and demand;

[0044] C user The user cost is considered, taking into account the user's sensitivity and satisfaction with electricity prices; C stability To ensure system stability and reliability of power supply; C cnvironmcnt is the environmental cost, including the impact of power generation on the environment and government subsidies; a, b, c, d are the weight coefficients of economic cost, user cost, system stability, and environmental cost, respectively, which are used to adjust the importance of different cost factors.

[0045] The constraints include but are not limited to

[0046] Supply and demand balance constraint: ensure that in any given time period, the power supply meets the demand: Supply ≥ Demand;

[0047] Electricity price range constraints: Electricity prices must be within a reasonable market range: P min ≤P(n)≤P max ;

[0048] Historical electricity price correlation constraint: The electricity price should maintain a certain correlation with the historical electricity price of the same period: |P(n)-P historical (n)|≤ε;

[0049] Environmental constraints: Consider the impact of environmental factors such as temperature and humidity on electricity prices;

[0050] Market conditions constraints: electricity prices should reflect current market conditions, such as load demand and supply capacity;

[0051] Time characteristic constraints: Electricity prices should take into account time characteristics, such as the difference between weekdays and holidays;

[0052] Transmission line loss constraint: The electricity price should take into account the energy loss during the transmission process P(n)≥P loss (n), where P loss (n) is the transmission line loss adjusted electricity price at time n.

[0053] Step S2: The QPSO algorithm, simulated annealing algorithm and group frog leaping algorithm are used to work together to solve the electricity price optimization model and obtain the optimal electricity price optimization strategy. The solution process is as follows:

[0054] Step 1: Initialize model parameters and evaluate

[0055] The first step in electricity price optimization is initialization, which involves setting a starting electricity price for each user or load point in the system. The goal of this step is to establish a benchmark so that subsequent steps can be improved on this basis. A series of key parameters are determined, including the number of particles, the number of iterations, the inertia weight, the learning factor, etc. The electricity price setting scheme is used as a particle, and its position is composed of the electricity value during peak, flat and valley periods. The speed value is randomly generated to simulate the movement of particles in the solution space. The electricity price array of each particle in the particle swarm is adjusted to ensure that the constraints of the electricity price optimization model are met, including but not limited to the supply and demand balance and cost-effectiveness analysis of the electricity market. These parameters will define the core framework of the model search strategy. Specifically, setting the initial value of the inertia weight determines the search speed of the particles at the beginning of the algorithm, which helps the particles move quickly in the global search space, while the learning factor determines the extent to which the particles update their positions based on individual experience and group experience.

[0056] Step 2: Data preprocessing and feature selection

[0057] After determining the model initialization parameters, load the historical electricity price data from the database, and perform necessary cleaning and preprocessing steps to form a data set. Preprocessing includes processing missing data, outlier detection, and data normalization to ensure data quality and algorithm performance. By removing outliers and standardizing data, training can be performed on a uniform scale to avoid deviations caused by scale differences. The core implementation of this process is simply to remove missing values, eliminate abnormal prices, and implement more complex outlier detection.

[0058] Based on the preprocessed data, the features with the greatest predictive power for the target variable, i.e. electricity price forecast, are selected from the preprocessed data. This may include time characteristics, market conditions, historical electricity prices, and environmental factors. Effective feature selection can reduce the complexity of the model while improving the model's prediction accuracy and operating efficiency. These selected features are used in the following model construction.

[0059] Time characteristics include year, month, day, hour, day of the week, and whether it is a holiday. This information can reflect the long-term trend and seasonality of electricity prices, and the difference between working days and rest days. Market conditions focus on current load demand, load in the previous hour, year-on-year and month-on-month load change rates, power supply capacity, and time period electricity. These indicators are directly related to the supply and demand situation of the electricity market. Historical electricity price data, such as historical electricity prices for the same period, electricity prices in the previous hour, daily average electricity prices, monthly average electricity prices, and annual average electricity prices, provide the model with a reference for past electricity price changes. Environmental factors include temperature, humidity, wind speed, weather conditions, electricity subsidies, power generation capacity, and transmission line losses. These factors may affect electricity demand and supply due to changes in the external environment, and thus affect electricity prices. By integrating these multi-dimensional features, it is possible to more accurately predict electricity price trends and provide strong decision-making support for market participants.

[0060] Step 3: Solving the model

[0061] Initialize the position and velocity of the particles through the QPSO algorithm based on the initialization parameters and the screened features, and optimize and update the particle velocity and position until the maximum number of iterations is reached;

[0062] During the optimization process, the quantum behavior mechanism is introduced through the quantum potential well model to increase the randomness and diversity of the particle search trajectory and improve the global search capability; the inertia weight and learning factor are dynamically adjusted according to the changes in electricity prices and distribution network efficiency to balance the adaptability and convergence speed of the algorithm; the simulated annealing algorithm is used in each sub-population for local search to effectively avoid local optimal solutions and improve local optimization results; at the same time, the local search capability of the algorithm is enhanced through the group frog leaping algorithm;

[0063] The optimal solution in the optimization process is taken as the optimal electricity price optimization strategy.

[0064] The quantum-behaved particle swarm optimization (QPSO) algorithm is an improved algorithm based on PSO. It treats each particle as a quantum particle, whose state is described by a wave function containing position and momentum. The key calculation process of the QPSO algorithm includes the initialization of particle position and velocity, particle velocity update based on inertia weight and learning factor, position update, application of quantum potential well QPW model and wave function update, which work together to improve the performance of the algorithm.

[0065] In QPSO, a 'particle' refers to a candidate solution in the search space. Each particle represents a possible electricity price setting scheme. These particles are not directly equivalent to a single feature, but rather use a combination of multiple selected features to construct their position and velocity. The "position" of a particle in the algorithm represents a complete solution, i.e., a set of electricity price settings, while their "velocity" represents the speed and direction of movement in the solution space, thereby affecting the update and optimization path of the solution. The behavior of particles in QPSO is affected by quantum probability distribution and quantum potential wells, making the search behavior of particles more random and comprehensive than traditional particle swarm optimization, enhancing the ability to explore the solution space.

[0066] Therefore, the position update of each particle is actually based on the result of comprehensive consideration of all relevant features, trying to find a solution that can optimize the electricity price. A particle is not just a representative of a single data point, but a complex that considers multiple factors in the electricity price optimization decision-making process. It updates its own position by following the individual and global optimal solutions, thereby gradually finding the optimal electricity price strategy in the iterative process.

[0067] In general, the position of a particle is a multidimensional vector, and each dimension corresponds to a key power parameter or decision variable. For example, the electricity price vector: including the value of electricity during peak hours, normal hours, and valley hours, directly affects the user's electricity consumption behavior; load forecast correction factor: based on historical data and current grid status, fine-tuning the load forecast to adapt to real-time changes; energy storage scheduling plan: including the charging and discharging time and amount of the energy storage system to balance the supply and demand of the grid; demand-side management strategy: such as price incentives, direct load control, etc., to guide users to use electricity reasonably.

[0068] The speed of particles in the QPSO algorithm is no longer just a simple linear increment of position update, but a dynamic adjustment mechanism that integrates the characteristics of quantum probability distribution. It reflects the trend and intensity of particles moving towards the global optimal solution in the solution space, while maintaining a certain degree of randomness, which helps to explore new areas of the solution space. In power optimization, changes in speed may represent dynamic adjustments to the adjustment range of electricity prices, the speed of load management strategy adjustment, etc.

[0069] Initialize the particle's position and velocity

[0070]

[0071] here, is the initial position of particle i. min and x max are the minimum and maximum boundaries of the search space respectively, and rand is a random number vector uniformly distributed in the interval [0,1].

[0072] Updates particle velocity.

[0073]

[0074] in, is the velocity of particle i at iteration t+1, is the velocity of particle i at iteration t, w is the inertia weight, c1 and c2 are the first learning factor and the second learning factor, rand1 and rand2 are the first random number vector and the second random number vector uniformly distributed in the interval [0,1], respectively. is the optimal position of particle i, is the best position globally. is the position of particle i at iteration t.

[0075] Update the particle position.

[0076]

[0077] is the position of particle i at iteration t+1, is the position of particle i at iteration t, is the velocity of particle i at iteration t+1.

[0078] This step uses a multi-group strategy, where each group represents a set of potential electricity price plans. By updating the particle position and adjusting the adaptive parameters, the algorithm can simulate the impact of electricity price adjustments on system performance. The QPSO algorithm balances the relationship between exploring new electricity price plans and further developing the current optimal solution by dynamically adjusting the inertia weight and learning factor.

[0079] As the optimization process deepens, the quantum behavior particle swarm optimization algorithm is introduced to enhance the global search capability. The core of QPSO lies in the concept of quantum potential well (QPW), which makes the movement of particles in the search space more random and diverse, thereby improving the global search capability of the algorithm. The quantum behavior mechanism of QPSO, especially the characteristics of quantum superposition and probability distribution, provides the algorithm with more powerful exploration capabilities in the global search process.

[0080] Update the wave function:

[0081]

[0082] σ is the standard deviation of the wave function, is the wave function of the position of particle i at iteration t+1, is the potential energy of particle i at iteration t+1.

[0083]

[0084] Where D is the dimension of the problem, m jand ω j are the particle mass and angular frequency in dimension j, is the position coordinate of particle i in dimension j at iteration t+1, and j is the number of dimensions of the exploration space.

[0085] The QPSO algorithm simulates the random behavior of quantum particles through the quantum potential well model, increasing the diversity of solutions in the search space. This quantum behavior mechanism not only improves the algorithm's ability to explore the global optimal solution, but also provides new perspectives and possibilities for electricity price optimization through the update of wave functions.

[0086] The adaptive adjustment of the learning factor is a manifestation of the algorithm's intelligence. It is dynamically adjusted according to changes in electricity prices and distribution network efficiency to balance the algorithm's adaptability and convergence speed. The introduction of multi-group strategies further enhances the algorithm's diversity and global search capabilities. Through information exchange between groups, the algorithm can simultaneously explore the solution space from multiple angles.

[0087] To further improve the efficiency and accuracy of the optimization process, the simulated annealing algorithm is integrated into the electricity price optimization. This step effectively avoids the algorithm from falling into the local optimal solution through multi-path parallel annealing technology. The local search results are enhanced. The simulated annealing process simulates the physical annealing process, and through the temperature control of random perturbations during the search process, global search at high temperature and local search at low temperature are achieved, ensuring the discovery of the global optimal solution.

[0088] In the next stage of electricity price optimization, the Shuffle Frog Leaping Algorithm is used to enhance local search. The Swarm Frog Leaping Algorithm (SFLA) is another algorithm based on swarm intelligence optimization. It combines global search and local optimization strategies by simulating the cooperative and competitive behavior of frog groups. Through the local search step, SFLA allows each frog to update its position according to its current position, the best frog position, and the global best position, and through the information exchange step, the frogs share position information to adjust their current and target positions. The design of this algorithm not only enhances the quality of the solution and the search efficiency, but also provides a novel solution to the optimization problem by simulating the biological behavior in nature.

[0089] Especially when the power generation efficiency of active distribution networks continues to improve, SFLA uses its efficient information exchange mechanism to quickly adjust and optimize the electricity price strategy, ensuring the simultaneous improvement of power generation efficiency and electricity price optimization. The key calculation process is as follows:

[0090] Local Search:

[0091]

[0092] Among them, xij (t+1) is the position of particle i at the t+1th iteration in dimension j, X ij (t) is the position of particle i in the jth dimension at the tth iteration, α and β are the first tuning parameter and the second tuning parameter, T is the randomization step size, best ij is the local optimal solution of particle i in dimension j, is the global optimal solution of particle i in dimension j.

[0093] Information Exchange

[0094]

[0095] N f is the number of frogs in the population, c k and w k represent the current position and target position of the kth frog respectively. ij (t)) is the fitness function of the i-th frog in the j-th dimension at time t. The purpose of the fitness function f is to quantify the frog's position X ij (t) “good” or “bad”.

[0096] In the above optimization process, the strategy of adaptively adjusting the inertia weight and learning factor is adopted to dynamically adjust these parameters according to the real-time changes in electricity prices and distribution network efficiency. This adaptive adjustment not only improves the adaptability of the algorithm and accelerates the convergence speed, but also enables particles to explore quickly in the early stage of the search through the adjustment of the adaptive inertia weight, and show stronger convergence characteristics in the later stage. In addition, the dynamic adjustment of the learning factor balances individual cognition and social cognition, optimizes the search path of particles, and improves the overall search efficiency.

[0097] In each round of iteration, the fitness of each particle in the particle swarm is evaluated, and the position and velocity of the particle are updated according to the evaluation results. At the same time, according to the characteristics of the current search stage, the algorithm parameters such as inertia weight and learning factor are dynamically adjusted to ensure that the algorithm can maintain efficient search capabilities at different stages.

[0098] During the iteration process, it is necessary to continuously check whether the algorithm meets the convergence conditions. Once convergence signs are detected, such as the quality of the solution does not improve much in consecutive iterations, or the preset number of iterations is reached, the global optimal solution is updated. This step ensures that the algorithm can stop in time after finding the optimal solution, avoiding unnecessary computational waste.

[0099] After the optimization process is completed, the optimal solution is analyzed in detail to evaluate whether it has achieved cost minimization and efficiency maximization while meeting the power system operation requirements. The analysis results will provide a scientific basis for price decisions in the power market, and the optimization results will be stored for future reference.

[0100] The above are only specific embodiments of the present invention, but the protection scope of the present invention is not limited thereto. Any changes or substitutions that can be easily thought of by a person skilled in the art within the technical scope disclosed by the present invention should be included in the protection scope of the present invention. The contents not described in detail in this specification belong to the prior art known to professional and technical personnel in the field.

Claims

1. A method for optimizing electricity prices considering time-sharing and active distribution network efficiency improvement, characterized in that: An electricity price optimization model considering time-sharing and active distribution network efficiency improvement is established. The QPSO algorithm, simulated annealing algorithm and swarm frog leaping algorithm are used to work together to solve the electricity price optimization model and obtain the optimal electricity price optimization strategy. The solution process is as follows: Using the electricity price setting scheme as a particle, set the initialization parameters of the electricity price optimization model, including setting the number of particles, the maximum number of iterations, the inertia weight, and the learning factor; Obtain electricity price data and perform preprocessing and feature screening; Initialize the position and velocity of the particles through the QPSO algorithm based on the initialization parameters and the screened features, and optimize and update the particle velocity and position until the maximum number of iterations is reached; During the optimization process, the quantum behavior mechanism is introduced through the quantum potential well model to increase the randomness and diversity of the particle search trajectory. The inertia weight and learning factor are dynamically adjusted according to the changes in electricity prices and distribution network efficiency. The simulated annealing algorithm is used for local search in each sub-population, and the group frog leaping algorithm is used to enhance the local search capability of the QPSO algorithm. The optimal solution in the optimization process is taken as the optimal electricity price optimization strategy.

2. The method for optimizing electricity prices considering time-sharing and active distribution network efficiency improvement according to claim 1, characterized in that: An electricity price optimization model is constructed with the optimization of economic cost, user cost, system stability and environmental cost as the objective function and the supply and demand balance and cost-effectiveness of the electricity market as constraints.

3. The method for optimizing electricity prices considering time-sharing and active distribution network efficiency improvement according to claim 2 is characterized in that: The objective function is min J=a·C economic +b·C user +c·C stabiliry +d·C environment Among them, C cconcmic is the economic cost, C user is the user cost, C stability is the system stability, C cnvironmcnt is the environmental cost, a, b, c, and d are the weight coefficients of economic cost, user cost, system stability, and environmental cost, respectively.

4. The method for optimizing electricity prices considering time-sharing and active distribution network efficiency improvement according to claim 2, characterized in that: The constraints are Supply ≥ Demand; P min ≤P(n)≤P max ; |P(n)-P historical (n)|≤ε; Among them, Supply is supply, Demand is demand, P(n) is the electricity price at time n, P historical (n) is the historical electricity price for the same period, ε is the allowable deviation, P min , P max are the maximum and minimum values ​​of the calibrated electricity price respectively.

5. The method for optimizing electricity prices considering time-sharing and active distribution network efficiency improvement according to claim 1, characterized in that: The preprocessing includes missing data, outlier detection and data normalization processing on the electricity price data.

6. The method for optimizing electricity prices considering time-sharing and active distribution network efficiency improvement according to claim 1, characterized in that: The feature screening is to screen out the features with the greatest predictive power for electricity price forecasting from the preprocessed data, and the screened features include time characteristics, market conditions, historical electricity prices and environmental factors.

7. The method for optimizing electricity prices considering time-sharing and active distribution network efficiency improvement according to claim 1, characterized in that: The QPSO algorithm creates multiple sub-populations to perform parallel optimization searches during the optimization process, and updates the best solution found in the entire population and each sub-population; each sub-population independently explores different areas of the solution space, and works together by sharing information between groups to jointly approach the global optimal solution.

8. The method for optimizing electricity prices considering time-sharing and active distribution network efficiency improvement according to claim 1, characterized in that: Update particle speed and position by the following formula: in, is the velocity of particle i at iteration t+1, is the velocity of particle i at the tth iteration, w is the inertia weight, c1 and c2 are the first learning factor and the second learning factor, rand1 and rand2 are the first random number vector and the second random number vector uniformly distributed in the interval [0, 1], respectively. is the optimal position of particle i, is the best position globally. is the position of particle i at iteration t, is the position of particle i at the t+1th iteration, is the position of particle i at iteration t.

9. The method for optimizing electricity prices considering time-sharing and active distribution network efficiency improvement according to claim 1, characterized in that: The quantum potential well model is: in, is the potential energy of particle i at the t+1th iteration, D is the dimension of the problem, m j and ω j are the particle mass and angular frequency in dimension j, is the position coordinate of particle i in dimension j at the t+1th iteration, j is the number of dimensions of the exploration space, is the wave function of the position of particle i at the t+1th iteration, and σ is the standard deviation of the wave function.

10. The method for optimizing electricity prices considering time-sharing and active distribution network efficiency improvement according to claim 1, characterized in that: The group frog leaping algorithm enhances the local search capability of the algorithm through the following formula: Among them, x ij (t+1) is the position of particle i at the t+1th iteration in dimension j, X ij (t) is the position of particle i in the jth dimension at the tth iteration, α and β are the first tuning parameter and the second tuning parameter, T is the randomization step size, best ij is the local optimal solution of particle i in dimension j, is the global optimal solution of particle i in dimension j.

Images