A cloud architecture-based communication signal intelligent scheduling system

Abstract

The application belongs to the technical field of communication scheduling, and specifically discloses a communication signal intelligent scheduling system based on a cloud architecture, which divides the traffic dense period and the sparse period of each communication base station by analyzing historical communication data, analyzes the dislocation to construct the traffic flow direction relationship between the base stations, evaluates the terminal access stability of the communication base station in the traffic dense period, screens out the access fluctuation base station, and then migrates the traffic of the access fluctuation base station in the traffic dense period to a suitable base station in advance according to the traffic flow direction relationship, so that the on-demand scheduling of the communication base station traffic is realized, over-scheduling can be avoided to the maximum extent, preventive scheduling can be performed before traffic scheduling, network fluctuation caused by temporary demand migration can be avoided, the migration effect is improved, the actual mobile path of the user can be better matched by using the traffic flow direction relationship for migration, the continuity and stability of the connection are maintained, resource waste is reduced, and efficient transmission is ensured.

Description

Technical Field

[0001] This invention belongs to the field of communication scheduling technology, and specifically discloses a cloud-based intelligent communication signal scheduling system. Background Technology

[0002] With the rapid development of society, people's demand for mobile communication is increasing day by day. Traditional fixed-line telephone systems are limited to specific locations and cannot meet users' needs for communication anytime and anywhere. Therefore, communication base stations have emerged, enabling users to maintain continuous communication connections in different locations through mobile devices (such as smartphones, tablets, etc.). Since the service area of ​​a single base station is limited, especially in vast areas, multiple base stations are usually deployed to form a dense network layout to ensure wide signal coverage and high-quality communication services, thus meeting users' communication needs.

[0003] In areas covered by multiple base stations, the communication needs of users in the service areas of each base station vary significantly. This difference leads to an imbalance in traffic load among different base stations, thus creating a need for traffic scheduling and resource optimization. However, existing traffic scheduling strategies are usually implemented when base stations are under high traffic conditions, failing to fully consider the periodic movement paths and traffic transfer patterns of users between different communication base stations. This reactive approach cannot predict and preventatively schedule traffic in advance. This not only easily leads to increased communication network fluctuations at the base stations where demand is migrating, affecting the effectiveness and stability of the migration, but may also migrate traffic to base stations that do not match the user's actual movement path, causing users to frequently switch base stations during movement, increasing the handover failure rate and drop call rate, and affecting communication continuity and user experience.

[0004] Furthermore, existing traffic scheduling strategies primarily rely on the traffic levels of communication base stations to make migration decisions, typically implementing traffic migration when a base station is experiencing high traffic. However, this approach overlooks the stability of terminal access, leading to unnecessary communication scheduling. Specifically, some base stations may be experiencing high traffic, but their communication terminal access performance is good and can effectively handle current user demands, thus not requiring traffic migration. Excessive traffic migration introduces additional signaling overhead and handover operations, increasing network load, impacting the original communication base station's operational performance, and wasting scheduling resources. Summary of the Invention

[0005] In view of the shortcomings of the prior art described above, the purpose of this invention is to provide a cloud-based intelligent scheduling system for communication signals to solve the problems existing in the prior art.

[0006] The objective of this invention can be achieved through the following technical solution: a cloud-based intelligent communication signal scheduling system, comprising: a communication traffic data retrieval module, used to count the number of communication base stations existing in the target area, and retrieve the communication logs of each communication base station within a specified historical period to extract communication traffic data.

[0007] The communication time period distribution segmentation module is used to perform communication time period distribution analysis on the communication logs retrieved by each communication base station, and to divide the traffic-intensive time period and traffic-sparse time period corresponding to different communication base stations based on the communication traffic data under each communication time period.

[0008] The communication base station traffic flow construction module is used to compare the peak traffic periods and sparse traffic periods of each communication base station, thereby identifying communication base station groups with misaligned traffic periods, and then constructing the traffic flow relationship of the communication base stations.

[0009] The terminal access stability analysis module is used to extract terminal access data from different communication base stations during periods of high traffic density, thereby analyzing the terminal access stability of the communication base stations during these periods.

[0010] The traffic migration and scheduling module is used to filter out unstable base stations based on the terminal access stability of communication base stations during peak traffic periods, and to migrate and schedule the traffic of unstable base stations during peak traffic periods using the traffic flow relationship of communication base stations.

[0011] Compared with existing technologies, the beneficial effects of this invention are as follows: This invention analyzes historical communication data to divide the traffic-intensive and sparse periods of each communication base station, and performs misalignment analysis to construct the traffic flow relationship between base stations. At the same time, it evaluates the terminal access stability of communication base stations during the traffic-intensive period, screens out base stations with fluctuating access, and then migrates the traffic of the fluctuating base stations to suitable base stations in advance according to the traffic flow relationship. This realizes on-demand scheduling of communication base station traffic, which can minimize over-scheduling and perform preventive scheduling before traffic scheduling to avoid network fluctuations caused by temporary demand migration, thus improving the migration effect. Attached Figure Description

[0012] To more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0013] Figure 1 This is a schematic diagram showing the connections of the various modules in the system of the present invention.

[0014] Figure 2This is a diagram showing the traffic flow relationship between different communication base stations within the target area in this invention.

[0015] Attached image caption: Arrows indicate the direction from sparse to dense. Detailed Implementation

[0016] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0017] Reference Figure 1 As shown, this invention proposes a cloud-based intelligent communication signal scheduling system, including a communication traffic data retrieval module, a communication time period distribution module, a communication base station traffic flow direction construction module, a terminal access stability analysis module, and a traffic migration scheduling module. The communication traffic data retrieval module is connected to the communication time period distribution module, which is connected to both the communication base station traffic flow direction construction module and the terminal access stability analysis module. Both the communication base station traffic flow direction construction module and the terminal access stability analysis module are connected to the traffic migration scheduling module.

[0018] It should be noted that this invention integrates the aforementioned modules into a cloud architecture. This is because the cloud architecture provides powerful computing resources and distributed storage. Specifically, firstly, the amount of communication log data generated by communication base stations is enormous. Traditional local servers or small data centers struggle to handle such massive data processing demands. The cloud architecture provides on-demand computing resources, dynamically expanding or shrinking computing power according to actual needs. This ensures sufficient resources to process large-scale data during peak periods and reduces resource consumption and costs during off-peak periods. Furthermore, the cloud architecture provides real-time stream processing services capable of receiving, processing, and analyzing communication data in real time, ensuring timely scheduling decisions. Secondly, communication log data is not only voluminous but also diverse, including base station communication logs and user communication terminal connection records. Traditional centralized storage systems struggle to efficiently manage and query this data. The cloud architecture provides a distributed file system, distributing data across multiple nodes to ensure data security and high availability. Additionally, the cloud architecture provides automatic backup functionality to ensure that communication logs are not lost due to hardware failures or human error, guaranteeing system reliability.

[0019] The communication traffic data retrieval module is used to count the number of communication base stations in the target area and retrieve the communication logs of each communication base station within a specified historical period to extract communication traffic data.

[0020] As an explanation of the above scheme, the specified historical period should not be too long or too short. If the specified historical period is too long (such as one year), the amount of communication log data retrieved will be too large. This not only increases the pressure on data storage and transmission, but also makes data processing and analysis complex and time-consuming. If the specified historical period is too short (such as a few hours or a day), the data sample size may not be sufficient to reflect the true traffic patterns, and short-term data may have large random fluctuations, making it difficult to extract stable information from it. In the example of this explanation, the specified historical period can be within 6 months from now, which can ensure the timeliness of communication log retrieval.

[0021] As further explanation of the above scheme, the communication log of the communication base station is automatically generated during the base station's operation. It records the communication activities and network status between the base station and user equipment. Whenever a user device (such as a mobile phone, tablet, etc.) communicates with the base station, the base station records the relevant communication activities. Generally, the communication log includes the start and end times of the communication activity, the communication terminal ID, the type of communication activity (such as voice call, data transmission, SMS, etc.), the user equipment's IP address, and the number of data packets transmitted.

[0022] It should be noted that the communication traffic data mentioned above can refer to the number of data packets transmitted.

[0023] The communication time period distribution segmentation module is used to perform communication time period distribution analysis on the communication logs retrieved by each communication base station, and to divide the traffic-intensive and traffic-sparse periods of different communication base stations based on the communication traffic data under each communication time period.

[0024] In the preferred implementation of the above scheme, the communication time period distribution analysis of the communication logs retrieved by each communication base station is performed as follows: the start time and end time of communication are extracted from the communication logs retrieved by each communication base station, thereby forming the communication time interval corresponding to each communication log.

[0025] Each retrieved communication log is arranged chronologically. Then, based on the arrangement, the corresponding communication time intervals of each log are extracted and their intersection is calculated to determine the overlap between each log's communication time interval and other logs. The specific formula for calculating the overlap is as follows: In the formula Indicates the degree of overlap. , These represent the communication time intervals of the two communication logs, and are compared with the set overlap threshold. For example, the overlap threshold is 0.7. This allows communication logs with an overlap of 0.7 to be selected and used to form several communication log sets with similar time intervals with other communication logs.

[0026] In the example above, assuming that the communication logs retrieved by a certain communication base station are A, B, C, D, E, F, G, H, and I, and the overlap between A and B, A and C, B and C, D and E, F and G, G and I, and H and I reaches the overlap threshold, then A, B and C, D and E, F and G, G and I, and H and I constitute a communication log set with similar time intervals.

[0027] The communication time intervals of each communication log in each similar time interval communication log set are combined to obtain the corresponding communication time segment for each similar time interval communication log set.

[0028] The communication time segments corresponding to the communication log sets of similar time intervals are clustered to obtain several classification clusters.

[0029] It should be added that clustering the communication time segments corresponding to the communication log sets of similar time intervals is based on the consideration that the communication time segments corresponding to adjacent similar time interval communication log sets may be quite close. The goal of clustering is to group these close time segments into a larger communication period. In the supplementary example, the communication time segments corresponding to A, B and C, D and E, F and G, G and I, and H and I are 8:00-8:40, 8:50-9:30, 10:00-10:40, 14:00-15:00, and 16:00-17:40, respectively. At this time, the end time of communication in 8:00-8:40 is quite close to the start time of communication in 8:50-9:30. Therefore, 8:00-8:40 and 8:50-9:30 can be grouped into a large communication period, such as 8:00-9:30.

[0030] In the example above, the resulting clusters are: Cluster 1: 8:00–9:30, Cluster 2: 10:00–10:40, Cluster 3: 14:00–15:00, and Cluster 4: 16:00–17:40. Cluster analysis ultimately formed several clusters, each representing a relatively large communication period. These clusters simplify the management of communication logs.

[0031] The communication time segments existing in each category are combined to obtain the communication time period corresponding to each category, which is then used as the communication time period distribution of the communication base station.

[0032] This invention obtains the communication time period distribution by using a clustering algorithm on the retrieved communication logs according to the communication time segment, instead of using a fixed division of a day as the communication time period distribution. This is because traditional fixed time segmentation is based on manually set time intervals, which may not accurately reflect the user's actual communication behavior. However, the clustering algorithm can automatically generate more reasonable communication time periods based on the communication time segment of the communication log. In addition, traditional fixed time segmentation is usually based on hours or half hours, which may cause short-term peaks and troughs to be smoothed when analyzing communication traffic, making it difficult to accurately identify them. The clustering algorithm can capture more granular communication patterns.

[0033] In a further optimized implementation of the above scheme, the traffic-intensive periods and traffic-sparse periods of different communication base stations are divided based on the communication traffic data under each communication period as follows: The communication logs retrieved by each communication base station are classified according to the communication period distribution of each communication base station to form the communication log set of each communication base station in each communication period.

[0034] The average communication traffic of each communication base station in each communication period is obtained by accumulating and averaging the communication traffic data of each communication log in the communication log set of the same communication base station in the same communication period.

[0035] The standard deviation of communication traffic data for each communication log in the communication log set of the same communication base station during the same communication period is calculated. The standard deviation and average communication traffic are used to calculate the coefficient of variation of communication traffic for each communication base station in each communication period. The coefficient of variation is a statistic that measures the relative dispersion of data. It represents the ratio of the standard deviation to the average value and reflects the fluctuation of communication traffic of the same communication base station during the same communication period.

[0036] The coefficient of variation of communication traffic for each communication base station in each communication period is adjusted relative to the average communication traffic using the following expression. Obtain the effective average communication traffic of each communication base station in each communication period. In the formula , This represents the average communication traffic and the coefficient of variation of communication traffic for each communication base station during each communication period. Represents the natural constant.

[0037] It is important to understand that when using the communication log sets of each communication base station to divide the traffic-intensive and traffic-sparse periods, the division is not simply based on the average communication traffic of each communication base station in each communication period. Instead, it incorporates adjustments based on communication traffic fluctuations. This is because when communication traffic fluctuations are large, the representativeness of the average communication traffic weakens. Therefore, the communication traffic fluctuations are applied to the average communication traffic for adjustment. Specifically, when communication traffic fluctuations are small, the effective average communication traffic is close to the average communication traffic. When communication traffic fluctuations are large, the effective average communication traffic is penalized by the communication traffic fluctuations, resulting in a lower effective average communication traffic compared to the average communication traffic. This adjustment can reduce the impact of communication traffic fluctuations on the effective average communication traffic, ensuring that the effective average communication traffic more accurately reflects the actual communication traffic situation.

[0038] The effective average communication traffic of the same communication base station in each communication period is compared, and the communication periods with the highest and lowest effective average communication traffic are selected as the traffic-intensive and traffic-sparse periods of the communication base station.

[0039] In the innovative implementation of the above scheme, when determining the traffic-intensive and traffic-sparse periods of each communication base station in each communication period, we can not only make a simple selection based on the maximum and minimum effective average communication traffic, but we can also consider multiple high-traffic and low-traffic periods to more comprehensively reflect the peak and trough distribution of communication traffic. For example, the first 10% of the effective average communication traffic is selected as the traffic-intensive period, and the last 10% is selected as the traffic-sparse period.

[0040] The communication base station traffic flow direction identification module is used to compare the traffic-intensive periods and traffic-sparse periods of each communication base station, thereby identifying communication base station groups with misaligned traffic periods, and then constructing the traffic flow direction relationship of the communication base stations.

[0041] Specifically, the identification of communication base station groups with traffic time period misalignment is carried out as follows: the traffic-intensive time periods of each communication base station are matched with the traffic-sparse time periods of other communication base stations. If the traffic-intensive time period of a certain communication base station is successfully matched with the traffic-sparse time period of a certain communication base station, then the communication base station group consisting of these two communication base stations is identified as having traffic time period misalignment.

[0042] The above-mentioned successful mismatch refers to calculating the mismatch degree between the traffic-intensive periods of each communication base station and the traffic-sparse periods of other communication base stations by intersecting the traffic-intensive periods of each communication base station and the traffic-sparse periods of other communication base stations. The mismatch degree is calculated by taking the intersection of the traffic-intensive period and the traffic-sparse period, dividing by the union, and taking the percentage. This percentage is then compared with a preset matching degree threshold, which is exemplarily set at 80%. If the matching degree threshold is reached, the mismatch is considered successful.

[0043] For each communication base station group with misaligned traffic periods, the misaligned periods and traffic flow directions are marked, and a traffic flow relationship diagram between different communication base stations in the target area is constructed based on this. (See [reference]). Figure 2 As shown.

[0044] In the example above, the peak traffic period for base station 1 is from 08:00 to 10:00, while the sparse traffic period for base station 2 is the same time period. This indicates that during the period from 08:00 to 10:00, a large number of users switched from base station 1 to base station 2, indicating that traffic flowed from base station 1 to base station 2.

[0045] The terminal access stability analysis module is used to extract terminal access data from different communication base stations during periods of high traffic density, thereby analyzing the terminal access stability of the communication base stations during periods of high traffic density.

[0046] It is important to know that during peak traffic periods, user communication terminals may experience unstable access when connecting to communication base stations. This is because when a large number of users connect to the same base station simultaneously, the base station's processing capacity may reach its limit, making it unable to respond to new users' access requests in a timely manner. In addition, as the number of users increases, the signal strength in the base station's service area may decrease, and the signal quality may deteriorate, leading to access failure or unstable connection.

[0047] In the improved implementation of the above operations, the stability of terminal access of communication base stations during peak traffic periods is analyzed as follows: the terminal connection success rate, terminal access drop rate, and continuous connection duration are extracted from the terminal access data of each communication base station during peak traffic periods as terminal access indicators.

[0048] It's important to understand that terminal connection success rate refers to the ratio of the number of successfully completed access requests during peak traffic periods to the total number of access requests. Connection success rate is one of the most direct indicators, reflecting the base station's ability to process access requests. A low connection success rate indicates that the base station may not be able to respond to user access requests in a timely manner, resulting in users being unable to access the network normally.

[0049] Terminal access drop rate refers to the ratio of the number of unexpected connection interruptions between a communication terminal and the base station during periods of high traffic to the total number of connections. The connection drop rate is a key indicator for assessing connection stability; a high drop rate indicates instability in the communication base station.

[0050] Continuous connection duration refers to the length of time a terminal device maintains a stable connection with a base station. It reflects how long a user can maintain a stable connection after an initial access. A longer continuous connection duration means the communication base station can provide continuous service, allowing users to enjoy a stable communication experience for an extended period.

[0051] Terminal connection success rate, terminal access drop rate, and continuous connection duration are used as indicators of terminal access performance. These three indicators reflect various aspects of terminal access from different perspectives: connection success rate focuses on the initial stage of access, drop rate focuses on connection stability, and continuous connection duration focuses on connection persistence. Combining these three indicators allows for a comprehensive evaluation of the overall performance of terminal access.

[0052] Substitute the terminal access indicators of each communication base station during peak traffic periods into the analysis formula. Obtain the terminal access stability of each communication base station during peak traffic periods. , , , These represent the terminal connection success rate, terminal access drop rate, and continuous connection duration, respectively. Indicates the duration of periods with high traffic volume. , , These represent the weighting coefficients for terminal connection success rate, terminal access drop rate, and continuous connection duration, respectively. .

[0053] In the above calculation of terminal access stability, the weighting coefficients for terminal connection success rate, terminal access drop rate, and continuous connection duration can be exemplarily set to 0.5, 0.3, and 0.2, respectively. This weighting allocation is based on the following considerations: Terminal connection success rate: As a prerequisite for users to use communication services normally, the connection success rate is crucial. Any other performance indicator depends on a successful initial connection, therefore it should be given the highest weight.

[0054] Terminal access drop rate: Drop rate has a direct and significant impact on user experience and service quality. Frequent drops can lead to user operation interruptions, data loss, and may cause user dissatisfaction and complaints. Therefore, drop rate is of secondary importance and is given a higher weight.

[0055] Continuous connection duration: While continuous connection duration is an important indicator for evaluating the long-term stability and resource utilization of a system, it reflects a long-term performance characteristic rather than an immediate issue that directly impacts user experience. Therefore, it can be assigned a relatively low weight.

[0056] The traffic migration scheduling module is used to filter out unstable access base stations from the terminal access stability of communication base stations during peak traffic periods, and to migrate and schedule the traffic of unstable access base stations during peak traffic periods using the traffic flow relationship of communication base stations.

[0057] In the specific implementation of the above scheme, the following process is used to screen out the access fluctuation base stations: the terminal access stability of each communication base station during the period of high traffic is compared with the critical access stability set by the system. For example, the critical access stability is 0.6. If the terminal access stability of a certain communication base station during the period of high traffic is less than the critical access stability, then the communication base station is regarded as the access fluctuation base station.

[0058] It's important to note that after identifying the peak traffic periods for each communication base station, traffic during these periods isn't directly migrated. Instead, the stability of terminal access at each base station during peak traffic periods is first assessed to determine if it can meet communication demands. Traffic migration is only considered when a communication base station cannot meet communication demands during peak traffic periods. Specifically, by analyzing the stability of terminal access at communication base stations during peak traffic periods, it's possible to identify which base stations have unstable access or insufficient resources, thus selecting those requiring traffic migration. This method ensures the necessity and effectiveness of traffic migration, avoids unnecessary resource scheduling, and improves overall network performance and user service quality.

[0059] In a further concrete implementation, the traffic flow relationship of communication base stations is used to migrate and schedule the traffic of access fluctuating base stations during periods of high traffic as follows: locate the location of each communication base station in the target area, and thereby obtain the service area corresponding to each communication base station.

[0060] The service area mentioned above refers to the geographical range within which a communication base station can effectively provide communication services. Generally speaking, the greater the transmission power of a communication base station, the larger its service area. The specific service area can be obtained from the management center of the communication base station.

[0061] Based on the service area corresponding to the access fluctuation base station, communication base stations adjacent to the service area of ​​the access fluctuation base station are selected as candidate base stations.

[0062] It should be noted that "adjacent" also includes overlapping service areas.

[0063] It's important to explain that when migrating traffic to a fluctuating access base station, the proximity of the base station to be migrated to the fluctuating access base station must be considered. This is because the signal strength between adjacent base stations is usually similar, making handover easier for communication terminals and reducing the risk of handover failure. Conversely, migrating to a distant base station may cause a sudden drop in signal strength, increasing the likelihood of handover failure. Furthermore, migrating to a distant base station may involve cross-regional resource scheduling, increasing the complexity and cost of network management. Migrating between adjacent base stations is relatively simple, can resolve the issue locally, and minimizes the impact on the overall network.

[0064] It is important to emphasize that since a candidate base station is a communication base station with unstable access during periods of high traffic, the traffic flow relationship is from periods of high traffic to periods of low traffic. If a candidate base station has a traffic flow relationship with a candidate base station with a fluctuating access, it means that the candidate base station has low traffic during periods of high traffic. In this case, the candidate base station is recorded as the target base station, and the traffic of the candidate base station during periods of high traffic is then migrated to the target base station.

[0065] When implementing traffic migration, communication terminals currently connected to the fluctuating base station can be switched to the target base station in advance before the peak traffic period. This is done to avoid an excessively large communication traffic base during the peak traffic period, thereby reducing the instantaneous peak pressure of communication traffic and realizing preventive scheduling before the peak traffic period.

[0066] If there is no traffic flow relationship between the candidate base station and the access fluctuating base station, then obtain the effective average communication traffic of each candidate base station during the traffic-intensive period from the candidate base stations corresponding to the access fluctuating base station. At the same time, calculate the overlap of the service areas of each candidate base station and the access fluctuating base station. Specifically, the overlap is obtained by dividing the overlapping area of ​​the service areas by the service area of ​​the access fluctuating base station.

[0067] The migration value is evaluated by combining the effective average communication traffic of each candidate base station during peak traffic periods with the service area overlap. The specific migration value evaluation formula is as follows: In the formula Indicates migration value. This represents the effective average communication traffic of the candidate base station during peak traffic periods. This represents the cumulative effective average communication traffic of each candidate base station during peak traffic periods. This indicates the degree of overlap between the service areas of the candidate base station and the access fluctuating base station.

[0068] It should be noted that when there is no traffic flow relationship between the candidate base station and the access fluctuating base station, it means that the candidate base stations adjacent to the access fluctuating base station are all in the period of high traffic density. Even if all candidate base stations are in the period of high traffic density, their traffic is not exactly the same. At this time, you can choose to migrate to the candidate base station with less traffic and greater service area overlap. On the one hand, choosing the candidate base station with less traffic can ensure that the migrated base station has spare communication capacity to carry the migrated traffic. On the other hand, the candidate base station with greater service area overlap means that the user's communication terminal can complete the handover without interrupting the connection. This seamless handover can ensure that the user's communication experience is not affected and avoid dropped calls or data loss due to handover failure or delay.

[0069] Candidate base stations are sorted in descending order of migration value, and the sorting results are used as the traffic migration order for access fluctuating base stations during periods of high traffic.

[0070] It should be noted that because all candidate base stations operate during peak traffic periods, their spare communication capacity is limited, and a single candidate base station may not be able to meet all migration requirements. To address this, candidate base stations can be ranked in descending order of their migration value, and the priority of traffic migration can be determined based on this ranking. This way, if the initial migration still cannot meet the demand, the next high-value candidate base station can be selected for migration, ensuring a gradual migration process that ultimately satisfies the overall migration requirements.

[0071] This invention analyzes historical communication data to divide each communication base station into periods of high and low traffic, and performs misalignment analysis to construct the traffic flow relationship between base stations. Simultaneously, it assesses the terminal access stability of communication base stations during periods of high traffic, identifies base stations with fluctuating access, and then, based on the traffic flow relationship, preemptively migrates the traffic of these fluctuating base stations to suitable base stations during periods of high traffic. This achieves on-demand scheduling of communication base station traffic, minimizing over-scheduling and enabling preventative scheduling before traffic scheduling, avoiding network fluctuations caused by temporary migration needs, and improving migration efficiency.

[0072] The above content is merely an example and illustration of the concept of the present invention. Those skilled in the art can make various modifications or additions to the specific embodiments described, or use similar methods to replace them, as long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, and all such modifications and additions should fall within the protection scope of the present invention.

Claims

1. A cloud-based intelligent communication signal scheduling system, characterized in that... ,include: The communication traffic data retrieval module is used to count the number of communication base stations in the target area and retrieve the communication logs of each communication base station within a specified historical period to extract communication traffic data. The communication time period distribution segmentation module is used to perform communication time period distribution analysis on the communication logs retrieved by each communication base station, and to divide the traffic-intensive time period and traffic-sparse time period corresponding to different communication base stations based on the communication traffic data under each communication time period. The communication base station traffic flow construction module is used to compare the traffic-intensive and traffic-sparse periods of each communication base station, thereby identifying communication base station groups with misaligned traffic periods, and then constructing the traffic flow relationship of the communication base stations. The terminal access stability analysis module is used to extract terminal access data from different communication base stations during periods of high traffic density, thereby analyzing the terminal access stability of the communication base stations during periods of high traffic density. The traffic migration and scheduling module is used to filter out unstable base stations based on the terminal access stability of the communication base station during peak traffic periods, and to migrate and schedule the traffic of the unstable base stations during peak traffic periods using the traffic flow relationship of the communication base station. The process of dividing the traffic-intensive and traffic-sparse periods corresponding to different communication base stations based on communication traffic data under each communication period is as follows: The communication logs retrieved by each communication base station are categorized according to the communication time period distribution of each communication base station to form a communication log set for each communication base station in each communication time period. The average communication traffic of each communication base station in each communication period is obtained by accumulating and averaging the communication traffic data of each communication log in the communication log set of the same communication base station in the same communication period. The standard deviation of communication traffic data for each communication log in the same communication log set of the same communication base station during the same communication period is calculated, and the standard deviation and average communication traffic are used to calculate the coefficient of variation of communication traffic for each communication base station in each communication period. The coefficient of variation of communication traffic for each communication base station in each communication period is adjusted by the average communication traffic using the following expression. Obtain the effective average communication traffic of each communication base station in each communication period. In the formula , This represents the average communication traffic and the coefficient of variation of communication traffic for each communication base station in each communication period. Represents the natural constant; The effective average communication traffic of the same communication base station in each communication period is compared, and the communication periods with the highest and lowest effective average communication traffic are selected as the traffic-intensive and traffic-sparse periods of the communication base station. The analysis of terminal access stability of the communication base station during peak traffic periods is performed as follows: Terminal connection success rate, terminal access drop rate, and continuous connection duration are extracted from terminal access data of various communication base stations during peak traffic periods as terminal access indicators. Substitute the terminal access indicators of each communication base station during peak traffic periods into the analysis formula. Obtain the terminal access stability of each communication base station during peak traffic periods. , , , These represent the terminal connection success rate, terminal access drop rate, and continuous connection duration, respectively. Indicates the duration of periods with high traffic volume. , , These represent the weighting coefficients for terminal connection success rate, terminal access drop rate, and continuous connection duration, respectively. .

2. The intelligent communication signal scheduling system based on cloud architecture as described in claim 1, characterized in that: The specific process of performing communication time period distribution analysis on the communication logs retrieved from each communication base station is as follows: The start and end times of communication are extracted from the communication logs retrieved from each communication base station, thus forming the communication time interval corresponding to each communication log. Each retrieved communication log is arranged in chronological order. Then, the corresponding communication time intervals of the communication logs are extracted sequentially according to the arrangement results. The intersection calculation is performed to obtain the overlap degree of each communication log's communication time interval with other communication logs. This is compared with the set overlap degree threshold. In this way, communication logs with an overlap degree that reaches the overlap degree threshold are selected to form several similar time interval communication log sets with other communication logs. The communication time intervals of each communication log in each similar time interval communication log set are combined to obtain the communication time segment corresponding to each similar time interval communication log set. Cluster the communication time segments corresponding to the communication log sets of similar time intervals to obtain several classification clusters; The communication time segments existing in each category are combined to obtain the communication time period corresponding to each category, which is then used as the communication time period distribution of the communication base station.

3. The intelligent communication signal scheduling system based on cloud architecture as described in claim 1, characterized in that: The identification of communication base station groups with misaligned traffic periods is implemented as follows: The traffic-intensive periods of each communication base station are matched with the traffic-sparse periods of other communication base stations. If the traffic-intensive period of a certain communication base station is successfully matched with the traffic-sparse period of a certain communication base station, then the traffic period mismatch of the communication base station group consisting of these two communication base stations is identified.

4. The intelligent communication signal scheduling system based on cloud architecture as described in claim 3, characterized in that: The specific process for successfully identifying a mismatch is as follows: The mismatch degree between the traffic-intensive periods of each communication base station and the traffic-sparse periods of other communication base stations is calculated by intersecting the traffic-intensive periods of each communication base station and the traffic-sparse periods of other communication base stations. This mismatch degree is then compared with a preset matching degree threshold. If the matching degree threshold is reached, the mismatch is considered to be successfully identified.

5. The intelligent communication signal scheduling system based on cloud architecture as described in claim 1, characterized in that: The specific process for constructing the traffic flow relationship of the communication base station is as follows: For each communication base station group with misaligned traffic periods, mark the misaligned period and traffic flow direction, and construct a traffic flow relationship diagram between different communication base stations in the target area based on this.

6. The intelligent communication signal scheduling system based on cloud architecture as described in claim 1, characterized in that: The process for filtering out unstable access base stations is as follows: The terminal access stability of each communication base station during peak traffic periods is compared with the critical access stability set by the system. If the terminal access stability of a certain communication base station during peak traffic periods is less than the critical access stability, then the communication base station is designated as an access fluctuation base station.

7. The intelligent communication signal scheduling system based on cloud architecture as described in claim 5, characterized in that: The process of migrating and scheduling traffic to access fluctuating base stations during periods of high traffic density by utilizing the traffic flow relationship of communication base stations is as follows: Locate the location of each communication base station in the target area, and thereby obtain the service area corresponding to each communication base station; Based on the service area corresponding to the access fluctuation base station, communication base stations adjacent to the service area of ​​the access fluctuation base station are selected as candidate base stations. Identify whether the selected candidate base stations have a traffic flow relationship with the access fluctuating base station. If a candidate base station has a traffic flow relationship with the access fluctuating base station, then record the candidate base station as the target base station, and then migrate the traffic of the access fluctuating base station to the target base station during the period of high traffic.

8. The intelligent communication signal scheduling system based on cloud architecture as described in claim 7, characterized in that: The process of migrating and scheduling traffic to fluctuating base stations during periods of high traffic volume by utilizing the traffic flow relationship of communication base stations also includes the following steps: If there is no traffic flow relationship between the candidate base station and the access fluctuating base station, then obtain the effective average communication traffic of each candidate base station during the traffic-intensive period from the candidate base stations corresponding to the access fluctuating base station, and calculate the overlap between the service areas of each candidate base station and the access fluctuating base station. The migration value of each candidate base station is evaluated by combining the effective average communication traffic of each candidate base station during peak traffic periods with the degree of overlap. Candidate base stations are sorted in descending order of migration value, and the sorting results are used as the traffic migration order for access fluctuating base stations during periods of high traffic.

Images