A communication network scheduling system and method for power systems

Abstract

The application provides a communication network scheduling system and method for a power system, relates to the technical field of communication networks, and realizes real-time monitoring and collection of power data and traffic performance data of the power system, and divides the collected data into normal, abnormal and fault states; different allocation strategies are adopted for the data of each state according to the data of different states, a plurality of allocation strategies are generated in one scheduling, the strategies are optimized through an annealing algorithm, and a scheduling strategy with the minimum task execution time is output; and the bandwidth and buffer allocation for the task are adjusted according to the scheduling strategy; the application effectively improves the stability of the power system and ensures that the most required scheduling strategy can be found.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of communication network, in particular to a communication network scheduling system and method for power system. BACKGROUND

[0002] In modern power systems, the scheduling of communication networks is crucial for ensuring the stability and efficiency of power supply. Traditional power system communication network scheduling methods often lack comprehensive analysis of real-time power data and communication performance data, resulting in inefficient and inflexible allocation of communication resources when faults occur in the power system, thereby affecting the overall operational efficiency and safety of the power system. Furthermore, existing scheduling strategy optimization methods typically rely on fixed rules or simple algorithms, making it difficult to adapt to the complex and variable working environment of power systems, resulting in insufficient real-time and accuracy of scheduling strategies.

[0003] In the prior art, a power communication scheduling method is disclosed in CN113890780A, which constructs a communication network within a region based on a communication bus protocol. It determines whether the communication service involves the transmission of priority data, and sets a pre-reading threshold based on the computing power level of the communication system to determine which communication services need to be prioritized. When the progress of a communication service is not less than its pre-reading threshold, the service is added to the priority communication service group. The expected transmission quality is determined by the transmission delay and packet loss rate of the service, and all communication services in the priority communication service group are sorted according to the expected transmission quality, and the communication service with the smallest expected transmission quality is selected to start pre-reading.

[0004] The main problem of the above-mentioned scheme is that setting the pre-reading threshold based on the computing power level requires accurate assessment of the computing resources of the entire regional system, otherwise it may cause the pre-reading operation to be overloaded, affecting the overall performance. The calculation of expected transmission quality relies on real-time delay and packet loss rate, which are selected based on actual network conditions and service requirements, and are dynamically changing in actual situations. The above-mentioned scheme lacks real-time adjustment capability for network dynamic changes and is difficult to cope with emergencies.

[0005] The above information disclosed in the background section is only intended to enhance the understanding of the background of the present disclosure, and therefore it can include information that does not constitute the prior art known to those of ordinary skill in the art. SUMMARY

[0006] The present application aims to provide a communication network scheduling system and method for power system to solve the problems raised in the background.

[0007] To achieve the above-mentioned purpose, the present application provides the following technical scheme:

[0008] A communication network scheduling system for a power system, comprising specifically:

[0009] An information collection module for monitoring power data and communication performance data of each terminal of the power system in an equal time period in real time, performing normalization processing on the collected power data and communication performance data respectively, and generating a first data set, wherein the power data includes current, voltage and power, and the communication performance data includes delay time, packet loss rate and throughput data volume;

[0010] An information classification module for collecting power data and communication performance data of the power system, obtaining normal threshold and fault threshold of the power system data, comparing the first data set with the normal threshold and the fault threshold, and dividing all data into three states of normal, abnormal and fault to generate a second data set, a third data set and a fourth data set respectively;

[0011] A strategy calculation module for receiving the second data set, the third data set and the fourth data set transmitted by the information classification module, allocating communication resources according to the resource amount required for just completing a task for the second data set, reducing communication resource allocation for the corresponding task according to the fluctuation of data for the third data set, and stopping allocation of communication resources for the fourth data set, generating a scheduling strategy after all communication data in the power system is allocated according to a strategy, and integrating all scheduling strategies to generate a strategy set;

[0012] A strategy optimization module for receiving the strategy set, taking minimization of task execution time as an optimization objective, generating a target function, randomly selecting a scheduling strategy from the strategy set as an initial solution, setting an initial temperature of an annealing algorithm, and generating a cooling function, performing neighborhood search on the initial solution at the initial annealing temperature, randomly selecting a new scheduling strategy from all neighboring scheduling strategies as a new solution, determining whether to accept the new solution according to the Metropolis criterion, and gradually reducing the annealing temperature according to the cooling function until the annealing termination condition is reached, and outputting the scheduling strategy at this time;

[0013] A scheduling feedback module for receiving the scheduling strategy output by the strategy optimization module, and adjusting the allocated bandwidth and buffer size according to the data type and the scheduling strategy.

[0014] Further, the formula for normalizing the power data is:

[0015]

[0016] wherein E0 represents the result of normalizing the power data, E represents the value of a kind of power data currently collected, E max represents the historical maximum value of the kind of power data currently collected, and E minLmax represents a historical maximum value of a kind of current collected power data, and the kind of power data specifically includes current, voltage and power;

[0017] The formula for normalizing the communication performance data is:

[0018]

[0019] wherein L0 represents the result of normalizing the communication performance data, L represents a kind of current collected communication performance data, L max Lmax represents a historical maximum value of a kind of current collected communication performance data, and the kind of communication performance data specifically includes delay, packet loss rate and throughput. min Lmin represents a historical minimum value of a kind of current collected communication performance data, and the kind of communication performance data specifically includes delay, packet loss rate and throughput.

[0020] Further, the principle for dividing the data into three states of normal, abnormal and fault is:

[0021] The collected power data and communication performance data are analyzed to determine the normal fluctuation range of the power data and the communication performance data when the power system is normally operated;

[0022] The boundary point of the normal fluctuation range is set as the normal threshold;

[0023] The collected power data and communication performance data are analyzed to determine the fluctuation range of the power data and the communication performance data corresponding to the interrupted line when there is an interrupted line in the power system;

[0024] The boundary point of the data fluctuation range of the interrupted line is set as the fault threshold;

[0025] The principle for judging the current state of a real-time collected data is:

[0026] When S0≤S z , the state of the real-time data is normal;

[0027] When S z ≤S0<S g , the state of the real-time data is abnormal;

[0028] When S0≥S g , the state of the real-time data is fault;

[0029] wherein S0 represents the real-time collected power system data, S z represents the normal threshold of the corresponding data, and S g represents the fault threshold of the corresponding data;

[0030] All the real-time power data and real-time and communication performance data collected are judged, all normal state data are extracted to generate a second data set, all abnormal state data are extracted to generate a third data set, and all fault state data are extracted to generate a fourth data set.

[0031] Further, the principle for generating the one-time scheduling strategy is:

[0032] For the task corresponding to the normal state data, a bandwidth and a buffer size just enough to make the task execution complete are allocated;

[0033] For the task corresponding to the fault state data, no communication resource allocation is performed;

[0034] For the task corresponding to the abnormal state data, the task allocation strategy of the normal state data is taken as a benchmark, a weight factor is generated for each data in the third data set, and the formula is:

[0035]

[0036] D i =S ij -S z

[0037] D max =S g -S z

[0038]

[0039] wherein, V i represents the fluctuation rate of the i-th data, represents the historical average value of the i-th data, S ij represents the j-th collection result of the i-th data, j represents the collection number of the data, V max represents the maximum fluctuation rate, S z represents the normal threshold value of the data, D i represents the deviation degree of the i-th data relative to the normal state, D max represents the maximum deviation degree, S g represents the fault threshold value of the data, α represents the influence proportion of the fluctuation rate on the weight factor, β represents the influence proportion of the deviation degree on the weight factor, and α+β=1, W i represents the weight factor of the i-th data in the third data set, by adjusting the values of α and β, different weight factors can be generated, and different scheduling schemes are formed;

[0040] The formula for performing communication resource allocation according to the weight factor is:

[0041] P i= P base × (1 - W i )

[0042] wherein P i represents the amount of resources allocated to the i-th data pair, P base represents the amount of resources allocated in the normal state.

[0043] Further, the formula according to which the objective function is generated is:

[0044]

[0045] wherein T represents the time for executing a task, N represents the total number of tasks to be scheduled in the primary dispatch of the power system, T exec (i) represents the computation time of the i-th task, T wait (i) represents the waiting time of the i-th task, T comm (i) represents the communication delay of the i-th task.

[0046] Further, the formula according to which the cooling function is generated is:

[0047] t i+1 = γt i

[0048] wherein t i represents the annealing temperature of the i-th iteration, t i+1 represents the annealing temperature of the (i+1)-th iteration, and γ represents the temperature decay rate.

[0049] Further, the formula according to which it is determined whether to accept the new solution according to the Metropolis criterion is:

[0050]

[0051] wherein P represents the probability of accepting the new solution, F(i) represents the time for executing a task corresponding to the current scheduling strategy, F(i+1) represents the time for executing a task corresponding to the next scheduling strategy, i.e., the new solution, and t represents the annealing temperature. In the annealing process, the annealing temperature gradually decreases according to the cooling function, and at this time, the probability of taking the larger new solution also gradually decreases. When the annealing temperature is lowered to the lowest, the probability of taking the larger new solution is 0, and at this time, the annealing termination condition is reached.

[0052] Further, the principle according to which the bandwidth and the buffer size are adjusted according to the data type and the scheduling strategy is:

[0053] For data in normal state, the computing resource is sufficient, the task computing time is mainly affected by the task complexity, and the bandwidth and buffer size do not need to be adjusted; in order to reduce the waiting time, the bandwidth and the buffer size are increased; in order to reduce the communication delay time, the bandwidth size is increased; in general, the bandwidth and the buffer size in normal state remain stable or slightly increase, and resources are reserved for possible abnormal conditions;

[0054] For data in abnormal state, in order to optimize the task computing time, reduce the bandwidth allocation of non-critical tasks, and ensure the computing resource of critical tasks; in order to reduce the waiting time, reduce the bandwidth of non-critical tasks, and increase the bandwidth and buffer size of critical tasks; in order to reduce the communication delay time, reduce the bandwidth of non-critical tasks, and increase the bandwidth of critical tasks; in general, the bandwidth resource allocation of non-critical tasks is reduced in abnormal state, the bandwidth and buffer resource of critical tasks are increased, and the execution time and stability of critical tasks are ensured in priority;

[0055] The critical task represents that the system operation is crucial, and the execution time is required, and if it fails or is delayed, it will have a significant impact on the main function or service of the system, and the specific tasks involved are: system monitoring, safety control, real-time data transmission and tasks that need to be scheduled in priority in the specific scheduling process;

[0056] The non-critical task represents that the system operation is not essential, and even if it fails or is delayed, it will not have a serious impact on the main function or service of the system, and the specific tasks involved are: data analysis, report generation, system maintenance and tasks that do not need to be scheduled in priority in the specific scheduling process;

[0057] For data in fault state, stop allocating bandwidth and buffer.

[0058] The application also provides a communication network scheduling method for a power system, which is realized by the above-mentioned communication network scheduling system for the power system, and the specific steps include:

[0059] Step 1: Real-time monitoring of the power data and communication performance data of each terminal of the power system in an equal time period, normalizing the collected power data and communication performance data respectively to generate a first data set, wherein the power data includes current, voltage and power, and the communication performance data includes delay time, packet loss rate and throughput data volume;

[0060] Step 2: Collecting the power data and communication performance data of the power system, obtaining the normal threshold and fault threshold of the power system data, comparing the first data set with the normal threshold and fault threshold, and dividing all data into three states of normal, abnormal and fault to generate a second data set, a third data set and a fourth data set respectively;

[0061] Step 3: receiving the second data set, the third data set and the fourth data set, the second data set allocating communication resources according to the amount of resources required to just complete the task, the third data set reducing the allocation of communication resources for the corresponding task according to the fluctuation of data, and the fourth data set stopping the allocation of communication resources, generating a scheduling strategy once according to a strategy for allocating all communication data in the power system, and integrating all scheduling strategies to generate a strategy set;

[0062] Step 4: receiving the strategy set, generating an objective function with the optimization goal of minimizing the task execution time, randomly selecting a scheduling strategy from the strategy set as an initial solution, setting an initial temperature of an annealing algorithm, and generating a cooling function, performing neighborhood search on the initial solution at the initial annealing temperature, randomly selecting a new scheduling strategy from all neighboring scheduling strategies as a new solution, determining whether to accept the new solution according to the Metropolis criterion, and gradually reducing the annealing temperature according to the cooling function until the annealing termination condition is reached, and outputting the scheduling strategy at this time;

[0063] Step 5: receiving the scheduling strategy output by the strategy optimization module, and adjusting the allocated bandwidth and buffer size according to the data type and the scheduling strategy.

[0064] Compared with the prior art, the beneficial effects of the present application are:

[0065] The present application adopts real-time information collection and classification mechanism, which can effectively monitor and analyze the power data and communication performance data of the power system, ensure the comprehensiveness and accuracy of the data basis of the scheduling decision, quickly identify the system condition by classifying the data into normal, abnormal and fault states, respond to different states of data with different strategies, reduce the complexity while ensuring the coverage of the strategy set, and find the scheduling strategy with the shortest task execution time in the strategy set through the annealing algorithm, adjust the bandwidth and buffer size of each task according to the scheduling strategy and the data state; The present application can effectively deal with abnormal and fault conditions that may occur at any time in the dynamic power system through real-time monitoring and dynamic adjustment, reduce the allocation of resources in abnormal state, avoid resource waste, and optimize the utilization rate of communication resources. BRIEF DESCRIPTION OF DRAWINGS

[0066] Figure 1 The figure is a system module schematic diagram of an embodiment of the present application;

[0067] Figure 2 The figure is a method flowchart schematic diagram of an embodiment of the present application. DETAILED DESCRIPTION

[0068] In order to make the purpose, technical scheme and advantages of the present application clearer, the present application is further described in detail below in combination with specific embodiments.

[0069] It should be noted that, unless otherwise defined, technical terms or scientific terms used in the present application shall have the usual meaning understood by a person with ordinary skill in the art to which the present application pertains. The terms "first", "second", and similar words used in the present application do not represent any order, number, or importance, but are only used to distinguish different components. The terms "include" or "contain" and similar words mean that the elements or objects before the word cover the elements or objects listed after the word and their equivalents, without excluding other elements or objects. The terms "connect" or "connected" and similar words are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. The terms "upper", "lower", "left", "right", and the like are only used to represent relative positional relationships, which can change accordingly when the absolute positions of the described objects change.

[0070] Embodiment:

[0071] Please refer to Figure 1 The present application provides a technical solution:

[0072] A communication network scheduling system for a power system, specifically comprising:

[0073] An information collection module for real-time monitoring of power data and communication performance data of each terminal of the power system in an equal time period, normalizing the collected power data and communication performance data respectively to generate a first data set, the power data including current, voltage, and power, and the communication performance data including delay time, packet loss rate, and throughput data volume;

[0074] In this embodiment, the formula for normalizing the power data is:

[0075]

[0076] Wherein, E0 represents the result of normalizing the power data, E represents the value of the current collected power data, E max represents the historical maximum value of the current collected power data, and E min represents the historical minimum value of the current collected power data, and the types of power data specifically include current, voltage, and power;

[0077] The formula for normalizing the communication performance data is:

[0078]

[0079] Wherein, L0 represents the result of normalizing the communication performance data, L represents the current collected communication performance data, L maxL represents the historical maximum value of the current collected communication performance data category min L represents the historical minimum value of the current collected communication performance data category.

[0080] An information classification module is configured to collect power data and communication performance data of the power system, obtain normal threshold values and fault threshold values of the power system data, compare the first data set with the normal threshold values and the fault threshold values, divide all the data into three states of normal, abnormal and fault, and generate a second data set, a third data set and a fourth data set respectively.

[0081] In this embodiment, the principle for dividing the data into three states of normal, abnormal and fault is as follows:

[0082] The collected power data and communication performance data are analyzed to determine the normal fluctuation range of the power data and the communication performance data when the power system is normally operated.

[0083] The boundary points of the normal fluctuation range are set as the normal threshold values.

[0084] The collected power data and communication performance data are analyzed to determine the fluctuation range of the power data and the communication performance data corresponding to the interrupted line when there is an interrupted line in the power system.

[0085] The boundary points of the data fluctuation range of the interrupted line are set as the fault threshold values.

[0086] The principle for judging the current state of a real-time collected data is as follows:

[0087] When S0≤S z , the real-time data state is normal.

[0088] When S z ≤S0<S g , the real-time data state is abnormal.

[0089] When S0≥S g , the real-time data state is fault.

[0090] Wherein, S0 represents the real-time collected power system data, S z represents the normal threshold value of the corresponding data, and S g represents the fault threshold value of the corresponding data.

[0091] All the real-time collected power data and real-time and communication performance data are judged, all the normal state data are extracted to generate the second data set, all the abnormal state data are extracted to generate the third data set, and all the fault state data are extracted to generate the fourth data set.

[0092] The policy calculation module is configured to receive the second data set, the third data set and the fourth data set transmitted by the information classification module, the second data set allocates the communication resources according to the amount of resources required to just complete the task, the third data set reduces the allocation of the communication resources for the corresponding task according to the fluctuation of the data, and the fourth data set stops allocating the communication resources, and a scheduling policy is generated after all the communication data in the power system is allocated according to a strategy, and all the scheduling policies are integrated to generate a policy set;

[0093] In this embodiment, the principle for generating the one-time scheduling policy is as follows:

[0094] For the task corresponding to the normal state data, the bandwidth and the buffer size that can just enable the task to be executed and completed are allocated;

[0095] For the task corresponding to the fault state data, no communication resource is allocated;

[0096] For the task corresponding to the abnormal state data, the task allocation strategy of the normal state data is taken as a reference, and a weight factor is generated for each data in the third data set, and the formula is as follows:

[0097]

[0098] D i =S ij -S z

[0099] D max =S g -S z

[0100]

[0101] wherein, V i represents the fluctuation rate of the i-th data, represents the historical average value of the i-th data, S ij represents the j-th collection result of the i-th data, j represents the collection number of the data, V max represents the maximum fluctuation rate, S z represents the normal threshold value of the data, D i represents the deviation degree of the i-th data relative to the normal state, D max represents the maximum deviation degree, S g represents the fault threshold value of the data, a represents the influence proportion of the fluctuation rate on the weight factor, b represents the influence proportion of the deviation degree on the weight factor, and a+b=1, W i represents the weight factor of the i-th data in the third data set, and different weight factors and different scheduling schemes can be generated by adjusting the values of a and b;

[0102] Weight factor W i represents the i th data in the third data set, the proportion of the allocated communication resources reduced relative to the data in the normal state in the first data set, reflecting the deviation of the data in the second data set from the data in the normal state, the deviation is measured by the volatility and the deviation degree, the volatility of the data is reflected by the standard deviation of the second data set, and the deviation is reflected by the deviation of the real-time data in the second data set from the data threshold, and the weight factor is proportional to the volatility and the deviation degree of the second data set; the values of α and β are adjusted, a plurality of weight factors are generated for one data, and then the allocation strategy is affected, and the allocation strategy is generated;

[0103] The formula for allocating communication resources according to the weight factor is:

[0104] P i =P base ×(1-W i )

[0105] Wherein, P i represents the amount of resources allocated to the task corresponding to the i th data, and P base represents the amount of resources allocated in the normal state;

[0106] P i reflects the actual amount of resources that should be allocated for the data in the i th second data set under the influence of the weight factor, which is generated by subtracting the reduced part affected by the weight factor from the amount of resources allocated in the normal state, and the actual amount of resources allocated is proportional to the amount of resources allocated in the normal state and inversely proportional to the weight factor.

[0107] The strategy optimization module is used for receiving a strategy set, taking minimizing the task execution time as an optimization target, generating a target function, randomly selecting a scheduling strategy from the strategy set as an initial solution, setting an initial temperature of an annealing algorithm, and generating a cooling function. At the initial annealing temperature, the initial solution is searched in the neighborhood, a new scheduling strategy is randomly selected from all neighboring scheduling strategies as a new solution, whether the new solution is accepted is determined according to the Metropolis criterion, and the annealing temperature is gradually reduced according to the cooling function, until the annealing termination condition is reached, and the scheduling strategy at this time is output.

[0108] In this embodiment, the formula for generating the target function is:

[0109]

[0110] Wherein, T represents the execution time of a task, N represents the total number of tasks to be scheduled, T exec (i) represents the calculation time of the i th task, and T wait(i) represents the waiting time of the i-th task, T comm (i) represents the communication delay of the i-th task;

[0111] The task execution time T reflects a task that needs to allocate resources, and is the sum of all times of allocating resources, scheduling resources, data transmission, task waiting and execution calculation, and the task execution time will also increase as these times grow;

[0112] Wherein, T exec (i) represents the execution calculation time, which is the time actually needed by the task to execute on the calculation resource, including all calculation steps of data processing and algorithm execution in the task; T wait (i) represents the time spent by the task in waiting for resource allocation and completion of other tasks, including the time of allocating resources, scheduling resources and task waiting, which can be obtained by the difference between the calculation task arrival time and the task execution start time; T comm (i) represents the communication delay time, reflecting the data transmission time, which is determined by the size of data, network bandwidth and network congestion degree; different scheduling strategies will generate different task execution times, and the annealing algorithm is used to find the shortest task execution time in all scheduling strategies;

[0113] In this embodiment, the formula for generating the cooling function is:

[0114] t i+1 = γt i

[0115] Wherein, t i represents the annealing temperature of the i-th iteration, t i+1 represents the annealing temperature of the (i+1)-th iteration, and γ represents the temperature decay rate, which is a constant less than 1 determined according to the actual situation, and can be taken as 0.98. The cooling function reflects the change rate of the annealing temperature with the increase of the iteration number, and the lower the temperature decay rate, the faster the change rate of the annealing temperature.

[0116] In this embodiment, the formula for determining whether to accept the new solution according to the Metropolis criterion is:

[0117]

[0118] Wherein, P represents the probability of accepting the new solution, T(i) represents the task execution time corresponding to the current scheduling strategy, T(i+1) represents the scheduling data corresponding to the next scheduling strategy, i.e. the new solution, and t represents the annealing temperature. In the annealing process, the annealing temperature gradually decreases with the cooling function, and the probability of taking the larger new solution also gradually decreases at this time. When the annealing temperature decreases to the lowest, the probability of taking the larger new solution is 0, and the annealing termination condition is reached at this time.

[0119] The calculation method of the probability of accepting the new solution adopts the Metropolis criterion in the simulated annealing algorithm, which is used to determine whether to accept a new solution, i.e., a new scheduling strategy. The simulated annealing algorithm is an optimization algorithm that searches the solution space to find a global optimal solution or an approximate optimal solution by simulating the process of solid annealing and gradually reducing the "temperature" according to a cooling function.

[0120] If the task execution time T(i+1) of the new solution is less than the scheduling data T(i) of the current solution, i.e., the new solution is better, the probability of accepting the new solution is 1, which means that if the new solution is better than the current solution, the new solution is always accepted; if the scheduling data T(i+1) of the new solution is greater than or equal to the task execution time T(i) of the current solution, i.e., the new solution is not better than the current solution, the probability of accepting the new solution is

[0121] Here, t represents the annealing temperature, which is a control parameter that determines the "randomness" of the algorithm in the search process. When t is large, even if the new solution is not better than the current solution, there is a high probability of accepting the new solution, which avoids the algorithm from falling into a local optimal solution. As t decreases, the probability of accepting a poor solution also decreases, and the algorithm gradually tends to accept a better solution. As the annealing process proceeds, the temperature t gradually decreases according to the predetermined cooling function, resulting in a decreasing probability of accepting a poor solution, until the temperature is reduced to the lowest, and the algorithm no longer accepts any solution worse than the current solution. At this time, the termination condition of the annealing algorithm is reached, and an approximate optimal solution is obtained.

[0122] The scheduling feedback module is configured to receive the scheduling strategy output by the strategy optimization module and adjust the allocated bandwidth and buffer size according to the data type and the scheduling strategy.

[0123] In this embodiment, the principle for adjusting the allocated bandwidth and buffer size according to the data type and the scheduling strategy is as follows:

[0124] For normal state data, the computing resources are sufficient, and the task computation time is mainly affected by the task complexity, so it is not necessary to adjust the bandwidth and buffer size. To reduce the waiting time, the bandwidth and buffer size are increased. To reduce the communication delay time, the bandwidth size is increased. Overall, the bandwidth and buffer size of the normal state remain stable or slightly increase, and resources are reserved for possible abnormal situations.

[0125] For the data of abnormal state, the calculation time of optimization task is calculated, the bandwidth allocation of non-critical task is reduced, and the calculation resource of critical task is ensured; in order to reduce the waiting time, reduce the bandwidth of non-critical task, increase the bandwidth and buffer size of critical task; in order to reduce the communication delay time, reduce the bandwidth of non-critical task, increase the bandwidth of critical task; in general, the bandwidth resource allocation of non-critical task is reduced under abnormal state, the bandwidth and buffer resource of critical task are increased, and the execution time and stability of critical task are ensured in priority;

[0126] The critical task represents that the operation of the system is very important, and the execution time is required, and if it fails or is delayed, it will have a significant impact on the main function or service of the system, and the critical task needs more calculation resource, bandwidth and buffer, and the tasks involved include: system monitoring, safety control, real-time data transmission and tasks that need to be scheduled in priority in the specific scheduling process;

[0127] The non-critical task represents that the operation of the system is not necessary, and even if it fails or is delayed, it will not have a serious impact on the main function or service of the system, and the demand for resources is relatively small, and the resource allocation can be reduced when the resource is tight, and the tasks involved include: data analysis, report generation, system maintenance and tasks that do not need to be scheduled in priority in the specific scheduling process;

[0128] For the data of fault state, stop allocating bandwidth and buffer.

[0129] Please refer to Figure 2 The application also provides a communication network scheduling method for a power system, which is executed by the above-mentioned communication network scheduling method for a power system, and the specific steps include:

[0130] Step 1: Real-time monitoring of power data and communication performance data of each terminal of the power system in an equal time period, normalizing the collected power data and communication performance data respectively to generate a first data set, the power data includes current, voltage and power, and the communication performance data includes delay time, packet loss rate and throughput data volume;

[0131] Step 2: Collecting power data and communication performance data of the power system, obtaining normal threshold and fault threshold of the power system data, comparing the first data set with the normal threshold and the fault threshold, dividing all data into three states of normal, abnormal and fault, and generating second data set, third data set and fourth data set respectively;

[0132] Step 3: receiving the second data set, the third data set and the fourth data set, the second data set allocating the communication resources according to the amount of resources required to just complete the task, the third data set reducing the communication resource allocation for the corresponding task according to the fluctuation of the data, and the fourth data set stopping the allocation of the communication resources, generating a scheduling strategy once according to a strategy for allocating all the communication data in the power system, and integrating all the scheduling strategies to generate a strategy set;

[0133] Step 4: receiving the strategy set, generating an objective function with the optimization goal of minimizing the task execution time, randomly selecting a scheduling strategy from the strategy set as an initial solution, setting an initial temperature of a simulated annealing algorithm, and generating a cooling function, performing neighborhood search on the initial solution at the initial simulated annealing temperature, randomly selecting a new scheduling strategy from all the neighboring scheduling strategies as a new solution, determining whether to accept the new solution according to the Metropolis criterion, and gradually reducing the simulated annealing temperature according to the cooling function until the simulated annealing termination condition is reached, and outputting the scheduling strategy at this time;

[0134] Step 5: receiving the scheduling strategy output by the strategy optimization module, and adjusting the allocated bandwidth and buffer size according to the data type and the scheduling strategy.

[0135] The above formulas are all dimensionless values calculated, the formulas are obtained by collecting a large amount of data to simulate a formula of the most recent real situation, and the preset parameters in the formulas are set by a person skilled in the art according to the actual situation.

[0136] The above embodiments can be realized wholly or partially by software, hardware, firmware or any other combination. When realized by software, the above embodiments can be realized wholly or partially in the form of a computer program product. Those skilled in the art can realize that the units and algorithm steps of the examples described in combination with the embodiments disclosed herein can be realized by electronic hardware or a combination of computer software and electronic hardware. Whether the functions are realized by hardware or software methods depends on the specific application and design constraints of the technical solutions.

[0137] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, which can be located in one place or distributed on multiple network units. Part or all of the units can be selected to achieve the purpose of the embodiments according to actual needs.

[0138] The above is merely specific embodiments of the present application, but the protection scope of the present application is not limited thereto, and any person skilled in the art can easily think of changes or replacements within the technical range disclosed by the present application, which should be covered within the protection scope of the present application.

Claims

1. A communication network scheduling system for an electric power system, characterized by, Specifically, it includes: The information acquisition module is used to monitor power data and communication performance data of various terminals of the power system in real time over an equal period of time. The acquired power data and communication performance data are normalized to generate a first dataset. The power data includes current, voltage and power, and the communication performance data includes delay time, packet loss rate and throughput. The information classification module is used to collect power data and communication performance data of the power system, obtain the normal threshold and fault threshold of the power system data, compare the first dataset with the normal threshold and fault threshold, classify all data into three states: normal, abnormal and fault, and generate the second dataset, third dataset and fourth dataset respectively. The strategy calculation module is used to receive the second, third, and fourth datasets transmitted by the information classification module. The second dataset allocates communication resources according to the amount of resources required to complete the task. The third dataset reduces the allocation of communication resources for the corresponding task based on the data fluctuation. The fourth dataset stops allocating communication resources. After all communication data in the power system is allocated according to a strategy, a scheduling strategy is generated. All scheduling strategies are integrated to generate a strategy set. The strategy optimization module receives a set of strategies, generates an objective function with the goal of minimizing task execution time, randomly selects a scheduling strategy from the strategy set as the initial solution, sets an initial temperature for the annealing algorithm, generates a cooling function, performs a neighborhood search on the initial solution at the initial annealing temperature, randomly selects a new scheduling strategy as the new solution from all neighboring scheduling strategies, determines whether to accept the new solution according to the Metropolis criterion, and gradually reduces the annealing temperature according to the cooling function until the annealing termination condition is reached, and outputs the current scheduling strategy. The scheduling feedback module receives the scheduling policy output by the policy optimization module and adjusts the allocated bandwidth and buffer size according to the data type and scheduling policy.

2. The communication network scheduling system for power systems of claim 1, wherein: The formula used in the information acquisition module to normalize the power data is: Wherein, E0 represents the result of normalizing the power data, E represents the value of a kind of power data currently collected, E max represents the historical maximum value of the kind of power data currently collected, E min represents the historical minimum value of the kind of power data currently collected, and the kind of power data specifically includes current, voltage and power. The formula used to normalize communication performance data is: Wherein, L0 represents the result of normalizing the communication performance data, L represents a kind of communication performance data currently collected, L max represents the historical maximum of the kind of communication performance data currently collected, L min represents the historical minimum of the kind of communication performance data currently collected, and the kind of communication performance data specifically includes: delay, packet loss rate and throughput.

3. The communication network scheduling system for power systems of claim 1, wherein: The principle underlying the information classification module's division of data into three states—normal, abnormal, and fault—is as follows: Analyze the collected power and communication performance data to determine the normal fluctuation range of power and communication performance data when the power system is operating normally. Set the boundary points of the normal fluctuation range as the normal threshold; Analyze the collected power data and communication performance data to determine the fluctuation range of power data and communication performance data for the corresponding lines when there are interrupted lines in the power system; Set the boundary point of the data fluctuation range of the interrupted line as the fault threshold; The principle underlying the determination of the current state of real-time collected data is as follows: When S0≤S z , the real-time data state is normal; When S z ≤ S0 < S g , the real-time data state is abnormal; When S0≥ S g the real-time data state is fault; wherein S0represents real-time collected power system data, S z represents a normal threshold value of the corresponding data, S g represents a fault threshold value of the corresponding data; All collected real-time power data and real-time communication performance data are evaluated, and all normal state data are extracted to generate a second dataset, all abnormal state data are extracted to generate a third dataset, and all fault state data are extracted to generate a fourth dataset.

4. The communication network scheduling system for power systems of claim 1, wherein: The principle upon which the strategy calculation module generates a scheduling strategy is based is as follows: For tasks corresponding to normal state data, allocate bandwidth and buffer size that are just enough to complete the task execution; No communication resources are allocated to the tasks corresponding to the fault status data; For tasks corresponding to abnormal state data, based on the task allocation strategy for normal state data, weight factors are generated for each data point in the third dataset, using the following formula: D i = S ij - S z D max = S g - S z wherein, V i represents the fluctuation rate of the i-th data, represents the historical average value of the i-th data, S ij represents the j-th acquisition result of the i-th data, j represents the number of data acquisition, V max represents the maximum fluctuation rate, S z represents the normal threshold of the data, D i represents the deviation degree of the i-th data relative to the normal state, D max represents the maximum deviation degree, S g represents the fault threshold of the data, α represents the influence proportion of the fluctuation rate on the weight factor, β represents the influence proportion of the deviation degree on the weight factor, and α+β=1, W i represents the weight factor of the i-th data in the third data set, by adjusting the values of α and β, different weight factors can be generated, and different scheduling schemes are formed; The formula used for allocating communication resources based on weighting factors is as follows: P i = P base x (1 - W i ) wherein P i represents the amount of resources allocated to the i-th data pair, P base represents the amount of resources allocated in the normal state.

5. The communication network scheduling system for power systems of claim 1, wherein: The formula used to generate the objective function in the strategy optimization module is: wherein T represents a primary task execution time, N represents a total number of tasks to be scheduled in the primary dispatch of the power system, T exec (i) represents a computation time of the i-th task, T wait (i) represents a waiting time of the i-th task, T comm (i) represents a communication delay of the i-th task.

6. The communication network scheduling system for power systems of claim 1, wherein: The formula used by the strategy optimization module to generate the cooling function is: t i+1 = γt i where t i represents the annealing temperature of the i-th iteration, t i+1 represents the annealing temperature of the (i+1)-th iteration, and γ represents the temperature decay rate.

7. A communication network dispatching system for a power system according to claim 1, characterized in that: In the strategy optimization module The formula used to determine whether to accept a new solution according to the Metropolis criterion is as follows: Where P represents the probability of accepting a new solution, F(i) represents the task execution time corresponding to the current scheduling policy, F(i+1) represents the scheduling data corresponding to the next scheduling policy, i.e., the new solution, and t represents the annealing temperature. During the annealing process, the annealing temperature gradually decreases with the cooling function. At this time, the probability of taking a larger new solution also gradually decreases. When the annealing temperature drops to the minimum, the probability of taking a larger new solution is 0, and the annealing termination condition is reached.

8. A communication network dispatching system for a power system according to claim 1, characterized in that: The principle underlying the scheduling feedback module's adjustment of allocated bandwidth and buffer size based on data type and scheduling strategy is as follows: For data under normal conditions, computing resources are sufficient, and task computation time is mainly affected by task complexity, so there is no need to adjust bandwidth and buffer size. To reduce waiting time, increase bandwidth and buffer size. To reduce communication latency, increase bandwidth size. Overall, bandwidth and buffer size under normal conditions remain stable or slightly increased to reserve resources for possible abnormal situations. For data in abnormal states, to optimize task computation time, reduce bandwidth allocation for non-critical tasks and ensure computational resources for critical tasks; to reduce waiting time, reduce bandwidth for non-critical tasks and increase bandwidth and buffer size for critical tasks; to reduce communication latency, reduce bandwidth for non-critical tasks and increase bandwidth for critical tasks; overall, in abnormal states, reduce bandwidth resource allocation for non-critical tasks and increase bandwidth and buffer resources for critical tasks, prioritizing the execution time and stability of critical tasks. The critical tasks mentioned refer to those that are essential to the operation of the system and have time requirements. Failure or delay will have a significant impact on the main functions or services of the system. The specific tasks involved include: system monitoring, security control, real-time data transmission, and tasks that need to be prioritized in the specific scheduling process. The non-critical tasks refer to tasks that are not essential to the operation of the system and will not have a serious impact on the main functions of the system even if they fail or are delayed. These tasks include data analysis, report generation, system maintenance, and tasks that do not need to be prioritized in the scheduling process. For data in a fault state, stop allocating bandwidth and buffers.

9. A communication network scheduling method for power systems, characterized in that: The method is performed by the communication network dispatching system for power systems according to any one of claims 1-8, comprising: Step 1: Monitor the power data and communication performance data of each terminal of the power system in real time over an equal period of time. Normalize the collected power data and communication performance data to generate the first dataset. The power data includes current, voltage and power, and the communication performance data includes latency, packet loss rate and throughput. Step 2: Collect power data and communication performance data of the power system, obtain the normal threshold and fault threshold of the power system data, compare the first dataset with the normal threshold and fault threshold, divide all data into three states: normal, abnormal and fault, and generate the second dataset, the third dataset and the fourth dataset respectively. Step 3: Receive the second dataset, the third dataset, and the fourth dataset. Allocate communication resources for the second dataset according to the amount of resources required to complete the task. Reduce the allocation of communication resources for the corresponding task based on the data fluctuations of the third dataset. Stop allocating communication resources for the fourth dataset. After all communication data in the power system is allocated according to a certain strategy, a scheduling strategy is generated. Integrate all scheduling strategies to generate a strategy set. Step 4: Receive the policy set, generate an objective function with the goal of minimizing task execution time, randomly select a scheduling policy from the policy set as the initial solution, set an initial temperature for the annealing algorithm, and generate a cooling function. At the initial annealing temperature, perform a neighborhood search on the initial solution, randomly select a new scheduling policy as the new solution from all adjacent scheduling policies, determine whether to accept the new solution according to the Metropolis criterion, and gradually reduce the annealing temperature according to the cooling function until the annealing termination condition is reached, and output the current scheduling policy. Step 5: Receive the scheduling policy output by the policy optimization module, and adjust the allocated bandwidth and buffer size according to the data type and scheduling policy.

Images