PEM water electrolysis hydrogen production multi-tank series-parallel optimization method

Abstract

The invention relates to a PEM water electrolysis hydrogen production multi-tank series-parallel optimization method, which comprises the following steps: S1, obtaining photovoltaic power generation data, and carrying out data preprocessing; s2, dividing the photovoltaic power generation daytime data into a sunny day and a non-sunny day according to a weather mode by adopting a K-means clustering algorithm, and calculating the average power of different weathers; s3, constructing a scheduling strategy; s4, performing global search and optimization by adopting an improved particle swarm optimization (PSO) algorithm to find an optimal PEM scheduling strategy; s5, recording the operation time and the state switching frequency of each PEM electrolytic cell, and evaluating the generated PEM scheduling strategy; according to the method, the influence of weather on photovoltaic power generation is combined with PEM electrolytic cell distribution and scheduling through a K-means clustering algorithm, an optimal coupling control strategy, multi-target optimization and operation time management are designed, the switching frequency of the PEM electrolytic cells is remarkably reduced, equipment abrasion and maintenance cost are reduced, and the efficiency of PEM water electrolysis hydrogen production is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of renewable energy power generation for hydrogen production, and particularly to an optimization method for multi-tank hybrid connection in PEM water electrolysis for hydrogen production. Background Art

[0002] With the continuous growth of global energy demand and the phenomenon that fossil energy exacerbates environmental pollution, the development and utilization of renewable energy have gradually become an important issue. Compared with traditional fossil fuels, renewable energy is more environmentally friendly, does not produce greenhouse gas emissions, and helps to mitigate climate change; for example, solar energy has become the fastest-growing renewable energy. Renewable energy replaces the power generation method of traditional fossil fuels by building corresponding power stations, such as photovoltaic power stations, wind power stations, hydropower stations, etc., so as to achieve wide application and sustainable development.

[0003] However, the intermittency and instability of renewable energy have become the biggest reasons restricting the wide application of renewable energy; photovoltaic power generation has intermittency and volatility. How to efficiently utilize photovoltaic power for hydrogen production has become a current research hotspot; as a way of energy conversion, PEM water electrolysis technology can convert renewable energy into hydrogen energy to achieve energy storage and conversion. In addition, PEM water electrolysis technology has the advantages of high efficiency, environmental protection, and easy regulation, and has broad application prospects in the field of energy storage and conversion. The development of PEM water electrolysis technology helps to promote the optimization and upgrading of the energy structure, reduce the dependence on fossil fuels, and achieve sustainable development;

[0004] The effective scheduling optimization of PEM water electrolysis for hydrogen production is combined with photovoltaic power generation, converting the energy lost due to curtailment of light into hydrogen energy for storage. The goals of optimized scheduling usually include maximizing hydrogen production, increasing power absorption rate, and reducing the number of starts and stops of equipment, so as to extend the service life of PEM electrolyzers and reduce maintenance costs; currently, the technologies for optimized scheduling of PEM electrolyzers mainly focus on the following aspects:

[0005] (1) Rule-based scheduling strategies usually adopt preset start-stop rules, that is, simply set thresholds artificially without considering the variability of data, and determine the start and stop of PEM electrolyzers according to whether the real-time power or predicted power of photovoltaic power generation reaches or exceeds the preset threshold;

[0006] (2) Optimization scheduling based on prediction uses the predicted data of photovoltaic power generation power, and adopts optimization algorithms (such as linear programming, dynamic programming, etc.) to formulate the scheduling plan of PEM electrolyzers. By predicting future photovoltaic power generation and demand, the hydrogen production plan is optimized to achieve maximum production or minimum cost;

[0007] (3) Scheduling strategies based on optimization algorithms use various optimization algorithms to optimize the start-stop strategies of PEM electrolyzers, obtaining multi-objective optimization results. For example, the particle swarm optimization algorithm (PSO) is used to find the combination of the maximum power point of photovoltaic power generation and the number of PEMs, maximizing hydrogen production while minimizing the number of switches.

[0008] Although the existing technologies have made certain progress in the scheduling optimization of PEM electrolyzers, there are still defects and deficiencies. The existing scheduling optimization methods focus on maximizing hydrogen production or minimizing the number of switches, and cannot set other objectives and optimize them. The prediction-based optimization methods rely too much on the accuracy of the prediction model. Once the prediction error is large, the effect of the scheduling strategy will be affected. At the same time, there is a lack of scheduling strategies for optimizing the number of switches, resulting in difficulty in achieving a balance between high switching frequency and high hydrogen production in the system. Summary of the Invention

[0009] In view of this, the present invention provides a multi-tank hybrid connection optimization method for PEM water electrolysis hydrogen production, which combines the influence of weather on photovoltaic power generation with the distribution scheduling of PEM electrolyzers, designs an optimal coupling control strategy, and improves the efficiency of PEM water electrolysis hydrogen production.

[0010] To achieve the above object, a multi-tank hybrid connection optimization method for PEM water electrolysis hydrogen production is characterized by including the following steps:

[0011] S1. Obtain the data of photovoltaic power generation, separate the data into daytime data and nighttime data, and perform data preprocessing.

[0012] S2. Use the K-means clustering algorithm to divide the daytime data of photovoltaic power generation into sunny days and non-sunny days according to weather patterns, and calculate the average power of different weathers.

[0013] S3. Construct a scheduling strategy.

[0014] S301. Set the parameters of the PEM electrolyzer, including the rated power of each PEM electrolyzer and the total number of PEM electrolyzers in the system.

[0015] S302. Calculate the power threshold and the number of enabled PEM electrolyzers.

[0016] According to the average photovoltaic power of each weather pattern combined with the safety factor, calculate the power threshold applicable to each weather pattern and the number of PEM electrolyzers that can be enabled.

[0017] S4. Use the improved particle swarm optimization (PSO) algorithm for global search and optimization to find the optimal PEM scheduling strategy.

[0018] S401. Set up a multi-objective optimization function, where the multi-objectives include maximizing hydrogen production, improving power absorption rate, and minimizing the number of switching operations.

[0019] S402. Initialize the parameters of the particle swarm optimization algorithm, including the number of initialized particles, the number of iterations, and the inertia weight, introduce mutation operations, dynamically adjust parameters, and add a local search mechanism.

[0020] S403. Iteratively update the velocity and position of the particles to find the optimal PEM electrolyzer scheduling strategy, including the start-stop threshold and the standby duration of the PEM electrolyzer.

[0021] S5. Record the operating time and the number of state switches of each PEM electrolyzer, and evaluate the generated PEM scheduling strategy.

[0022] Evaluate the generated PEM scheduling strategy by calculating the hydrogen production and the power absorption rate.

[0023] Preferably, the data preprocessing includes extracting temperature, humidity, and light radiation characteristics from the obtained daytime photovoltaic power generation data and performing normalization processing.

[0024] Preferably, the multi-objective optimization function is the weighted sum of hydrogen production, the number of switching operations, and the power absorption rate, and the weights of hydrogen production, the number of switching operations, and the power absorption rate are preset according to requirements.

[0025] Preferably, the local search mechanism is to perform a small-range search and adjustment near the generated PEM electrolyzer scheduling strategy to obtain the optimal PEM electrolyzer scheduling strategy.

[0026] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0027] 1. The present invention applies the K-means clustering algorithm to the weather pattern recognition of photovoltaic power generation data, simplifies the complex meteorological data into two categories of typical sunny days and non-sunny days, and dynamically adjusts the start and stop of the PEM electrolyzer through the average power and characteristics of different clusters, improving the adaptability and optimization ability of the system to different weather conditions.

[0028] 2. The present invention designs a multi-objective optimization function that comprehensively considers hydrogen production, power absorption rate, and the number of switching operations, dynamically adjusts parameters such as the number of particles, the number of iterations, the inertia weight, and the acceleration coefficient, and uses a method enhanced by local search to perform a detailed search near the global optimal solution, and can find a better local solution, further improving the overall optimization effect.

[0029] 3. The present invention combines the K-means clustering algorithm and the particle swarm optimization algorithm (PSO), combines the influence of weather on photovoltaic power generation with the distribution and scheduling of hydrogen production by PEM electrolyzer hydrolysis, and designs an optimal coupling control strategy for PEM electrolyzer;

[0030] 4. Through multi-objective optimization and operation time management, the present invention significantly reduces the switching times of PEM electrolyzers, reduces equipment wear and maintenance costs, extends the service life of PEM electrolyzer equipment, and improves the efficiency and stability of the PEM electrolytic water hydrogen production system. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 is a flow chart of the present invention;

[0032] Figure 2 is a clustering analysis result diagram of the present invention;

[0033] Figure 3 is a comparison diagram of the start-stop switching times of two groups of PEM electrolyzers of the present invention. DETAILED DESCRIPTION OF THE INVENTION

[0034] To further elaborate on the technical means and effects adopted by the present invention to achieve the predetermined invention purpose, the following combines the drawings and preferred embodiments to detail the specific implementation manners, structures, features and their effects of the present invention as follows.

[0035] In order to optimize the scheduling strategy of PEM electrolyzers, increase hydrogen production, power absorption rate and reduce start-stop switching times, thereby improving the efficiency and stability of the PEM electrolytic water hydrogen production system, the present invention provides the following technical solutions:

[0036] A multi-tank parallel-series optimization method for PEM electrolytic water hydrogen production, comprising the following steps:

[0037] S1. Obtain the data of photovoltaic power generation, separate the data into daytime data and nighttime data, and perform data preprocessing. The data preprocessing includes extracting temperature, humidity and light radiation characteristics from the obtained daytime data of photovoltaic power generation, and performing normalization processing to eliminate the influence of different feature dimensions and ranges;

[0038] S2. Use the K-means clustering algorithm to divide the daytime data of photovoltaic power generation into sunny days and non-sunny days according to weather patterns. The number of categories can be adjusted according to needs, and calculate the average power of different weathers; dynamically adjust the start and stop of PEM electrolyzers through the average power and characteristics of different clusters, and improve the adaptability and optimization ability of the system to different weather conditions;

[0039] The data acquisition for preprocessing and the K-means clustering algorithm are as follows:

[0040]

[0041]

[0042] Group the PV data during the daytime through K - means clustering analysis. The principle is to divide the data into multiple groups according to the similarity of data characteristics, so that the data points within the same group are as similar as possible, while the differences between data points in different clusters are as large as possible, thereby achieving the identification and analysis of the PV power generation characteristics under different weather conditions: Extract meteorological variables (such as solar irradiance, temperature, humidity, etc.), and divide the data into day and night based on irradiance; Select multiple meteorological characteristics for normalization to eliminate the dimension difference, and then apply the K - means algorithm to divide the daytime data into two categories (sunny days and non - sunny days); Analyze the average value of meteorological characteristics for each category, and visualize the clustering results through a scatter plot.

[0043] S3. Construct a scheduling strategy;

[0044] S301. Set the PEM electrolyzer parameters, including the rated power of each PEM electrolyzer and the total number of PEM electrolyzers in the system (which can be set according to specific situations and modify the data in the code);

[0045] S302. Calculate the power threshold and the number of enabled PEM electrolyzers;

[0046] Calculate the power threshold applicable to each weather pattern and the number of PEM electrolyzers that can be enabled by combining the average PV power of each weather pattern with a safety factor, ensuring stable operation under different weather conditions;

[0047] The scheduling strategy algorithm is constructed as follows:

[0048]

[0049]

[0050] S4. Adopt an improved particle swarm optimization (PSO) algorithm for global search and optimization to find the optimal PEM scheduling strategy;

[0051] S401. Set a multi - objective optimization function as the weighted sum of hydrogen production, switching times, and power absorption rate. The multi - objectives include maximizing hydrogen production, improving power absorption rate, and minimizing switching times. The weights of hydrogen production, switching times, and power absorption rate in the multi - objective optimization function are preset according to requirements. The multi - objective optimization function is as follows:

[0052]

[0053] Among them, N is the hydrogen production, S is the number of switching times, PAR is the power absorption rate, representing the proportion of the power absorbed by the electrolyzer in the total photovoltaic power generation. The weights k1, k2, and k3 control the relative importance of these three factors respectively, and these weights are usually adjusted through experiments or requirements.

[0054]

[0055] Among them, N represents the number of electrolyzers, PEMstate(i) represents the state of the i-th electrolyzer (0 for off and 1 for on), P is the operating power of the electrolyzer, and Δt is the time step. is the coefficient of hydrogen production per megawatt per hour.

[0056]

[0057] Among them, PEMstate(i) represents the state of the i-th electrolyzer at the previous moment, and prestate(i) represents the state of the i-th electrolyzer at the next moment.

[0058]

[0059] Among them, CurP is the photovoltaic power generation at the current moment.

[0060] S402. Initialize the parameters of the particle swarm optimization algorithm, including the number of initial particles, the number of iterations, and the inertia weight. Introduce mutation operations, dynamically adjust parameters, and add a local search mechanism. The local search mechanism is to perform a small-range search and adjustment near the generated PEM electrolyzer scheduling strategy to obtain the optimal PEM electrolyzer scheduling strategy, realizing the global search and optimization of the improved particle swarm algorithm PSO;

[0061] S403. Update the velocity and position of the particles through iteration to find the optimal PEM electrolyzer scheduling strategy, including the start-stop threshold and the standby duration of the PEM electrolyzer, realizing the balanced optimization of multiple objectives;

[0062] The particle swarm optimization algorithm is as follows:

[0063]

[0064]

[0065]

[0066] The Particle Swarm Optimization (PSO) algorithm is used to optimize the scheduling strategy of PEM electrolyzers. The optimization objectives are the PEM startup threshold and standby time. The specific principle of the algorithm is to simulate the movement of multiple particles. Each particle (vector) is represented as a scheduling strategy, and the fitness function value (objective function value) is calculated during each iterative optimization process to evaluate the performance of each particle. In the example code, the fitness function includes the weighted sum of hydrogen production, switching times, and power absorption rate. The particles continuously update their positions and velocities in the search space based on their own experience and the guidance of the global best particle, and finally find the optimal scheduling strategy. In each iteration, the algorithm dynamically adjusts the velocity of the particles and further improves the accuracy of the global optimal solution through a local search strategy, and finally outputs the optimal scheduling parameters and the corresponding fitness values.

[0067] S5. Record the running time and start-stop switching times of each PEM electrolyzer, visually output the operating status of the PEM electrolyzer through visualization, and evaluate the generated PEM scheduling strategy by calculating hydrogen production and power absorption rate. The algorithm is as follows:

[0068]

[0069]

[0070]

[0071] S6. Analysis of operation results

[0072] The basic parameters are set as shown in Table 1:

[0073] Table 1

[0074]

[0075] As Figure 2 shown, the point sets of the two colors in the figure represent different categories after clustering. The K-means clustering obtains two clustering results as shown in Table 2-1 and Table 2-2;

[0076] Table 2-1

[0077]

[0078] Table 2-2

[0079]

[0080] The average values of Category 1 show relatively high irradiance, especially direct normal irradiance and global irradiance, which generally indicate a sunny day or a high-irradiance weather condition, with moderate air temperature and low relative humidity, suggesting it may be a dry and sunny day; the average values of Category 2 show relatively low irradiance, especially direct normal irradiance and global irradiance, which may indicate overcast, hazy or cloudy weather, with air temperature relatively close to that of Category 1 but high relative humidity, indicating that the air may be relatively humid.

[0081] The method provided by the present invention has a significant effect on distinguishing weather patterns; through K-means clustering analysis of daytime photovoltaic data, the weather patterns can be effectively divided into two categories, representing sunny weather and non-sunny weather respectively. The visualization results in the figure clearly show the distribution of these two clusters. Category 1 (sunny weather) has high irradiance and low humidity, while Category 2 (non-sunny weather) shows low irradiance and high humidity; this result verifies the effectiveness and accuracy of the proposed method in weather pattern recognition.

[0082] Specifically, in practical applications, the start-stop decision of PEM electrolyzers is mainly based on the power generation of photovoltaic panels at each moment. The electrolyzers need to obtain the power generation of photovoltaic panels at any time to start and stop, thus causing different switching times for different electrolyzers; in addition, there are also issues regarding energy efficiency and cost considerations. In some scheduling strategies, the start-stop status of each electrolyzer may be dynamically adjusted according to the efficiency of the electrolyzer or price fluctuations, which will also lead to uneven switching times.

[0083] According to the actual photovoltaic power generation data, the start-up threshold of the electrolyzer is reasonably set. In sunny mode, two electrolyzers are required to complete the coupling. The result is that the total hydrogen production is 103955.00 kg, the switching times of PEM electrolyzer No. 1 is 7524 times, the switching times of PEM electrolyzer No. 2 is 2692 times, the total switching times is 10216 times, the total operating time of PEM electrolyzer No. 1 is 5299.50 hours, the total operating time of PEM electrolyzer No. 2 is 5096.50 hours, and the total power absorption under the scheduling optimization strategy is 13291.25 MW·h.

[0084] At a certain moment, due to an increase in hydrogen demand or a change in power demand, PEM electrolyzer No. 1 may be started, and its status changes from off (0) to on (1). If its working status does not change in subsequent time steps, its switching times will increase by 1. Assume that in the same time step, PEM electrolyzer No. 2 remains in the standby state (not started), or even if it is started, it continues to work in subsequent time steps without changing its status. In this case, the switching times of No. 2 remain unchanged.

[0085] As described above, it is only the preferred embodiment of the present invention, and there is no limitation to the present invention in any form. Although the present invention has been disclosed as above with the preferred embodiment, it is not intended to limit the present invention. Any person skilled in the art can make some changes or modifications to equivalent embodiments with equivalent changes within the scope of the technical solution of the present invention. However, as long as it does not depart from the content of the technical solution of the present invention, any brief modifications, equivalent changes and modifications made to the above embodiments according to the technical essence of the present invention still fall within the scope of the technical solution of the present invention.

Claims

1. A multi-tank hybrid optimization method for hydrogen production by PEM water electrolysis, characterized in that: The following steps are involved: S1. Acquire photovoltaic power generation data, separate the data into daytime data and nighttime data, and perform data preprocessing; S2, using K-means clustering algorithm to divide the photovoltaic power generation daytime data into sunny days and non-sunny days according to the weather pattern, and calculate the average power in different weather conditions; S3, build a scheduling strategy; S301, setting PEM electrolyzer parameters, including the rated power of each PEM electrolyzer and the total number of PEM electrolyzers in the system; S302, calculating the power threshold and the number of enabled PEM electrolyzers; Based on the average PV power in each weather mode and the safety factor, the power threshold applicable to each weather mode and the number of PEM electrolyzers that can be enabled are calculated; S4, using improved particle swarm optimization (PSO) algorithm to perform global search and optimization to find the optimal PEM scheduling strategy; S401, setting a multi-objective optimization function, where the multi-objectives include maximizing hydrogen production, improving power absorption rate, and minimizing the number of switching times; S402, initializing the parameters of the particle swarm optimization algorithm, including initializing the number of particles, the number of iterations, the inertia weight, introducing mutation operations, dynamically adjusting parameters, and adding a local search mechanism; S403, by iteratively updating the speed and position of the particles, finding the optimal PEM electrolyzer scheduling strategy, including the start-stop threshold and the PEM electrolyzer standby duration; S5, recording the operation time and state switching times of each PEM electrolyzer, and evaluating the generated PEM scheduling strategy; The generated PEM dispatch strategy is evaluated by calculating the hydrogen production and electricity absorption rate.

2. A multi-tank hybrid optimization method for producing hydrogen by PEM water electrolysis according to claim 1, characterized in that: Data preprocessing includes extracting temperature, humidity and light radiation characteristics from the acquired photovoltaic power generation daytime data and performing normalization processing.

3. A multi-tank hybrid optimization method for producing hydrogen by PEM water electrolysis according to claim 1, characterized in that: The multi-objective optimization function is a weighted sum of hydrogen production, switching times and power absorption rate, and the weights of hydrogen production, switching times and power absorption rate are preset according to demand.

4. A multi-tank hybrid optimization method for producing hydrogen by PEM water electrolysis according to claim 1, characterized in that: The local search mechanism is to search and adjust a small range near the generated PEM electrolyzer scheduling strategy to obtain the optimal PEM electrolyzer scheduling strategy.

Images