Methods for implementing edge solid-state drive devices, edge data systems, and computers

Abstract

The various aspects include edge solid-state drive devices, edge data systems, and computer-implemented methods. The edge SSD device includes non-volatile memory circuitry. The edge SSD device includes one or more memory controllers for operating the non-volatile memory circuitry. The edge SSD device includes a wireless transceiver. The edge SSD device includes a data processor configured to aggregate data received from a remote sensor device using the wireless transceiver into aggregated data. The data processor can process and / or filter the aggregated data into processed and / or filtered data, and can cause the aggregated data to be stored in the volatile memory circuitry by one or more memory controllers. The data processor can cause the processed and / or filtered data to be transmitted using the wireless transceiver.

Description

[0001] This application claims the benefit of U.S. Provisional Application No. 63 / 039,980, filed on June 16, 2020, which is incorporated herein by reference. Technical Field

[0002] This disclosure relates to storage systems and networking systems, and more specifically, to edge solid-state drive (SSD) devices and edge data processing and / or filtering systems, including peer-to-peer (P2P) sensor networks. Background Technology

[0003] SSDs are commonly installed in computers and mobile devices. In large installations, SSDs are used in rack-mount systems. The Internet of Things (IoT) is constantly evolving. Tens of billions of devices are now interconnected via IoT. This growth in interconnected devices shows no signs of slowing down. Collecting and processing the data generated by these devices is a challenge. While some SSDs are configured to store data collected from IoT, SSDs only have the single function of storing information. Furthermore, various limitations such as cost, power, latency, bandwidth, and the total amount of information involved hinder the growth of SSDs and impede many additional benefits that could potentially be realized from the expansion of the Internet. Summary of the Invention

[0004] Various disclosed embodiments include an edge SSD device. The edge SSD device may include one or more non-volatile memory circuits. The edge SSD device may include one or more memory controllers configured to operate the one or more non-volatile memory circuits. The edge SSD device may include one or more wireless transceivers. The edge SSD device may include a data processor configured to aggregate data received from a first remote sensor device and a second remote sensor device into aggregated data using the one or more wireless transceivers. In some embodiments, the data processor may also be configured to process or filter the aggregated data such that the aggregated data is stored by the one or more memory controllers in the one or more non-volatile memory circuits, and that the processed or filtered data is transmitted using the one or more wireless transceivers.

[0005] Some embodiments may include an edge data system. The edge data system may include a first remote sensor device configured to collect a first type of data. The edge data system may include a second remote sensor device configured to collect a second type of data different from the first type. The edge data system may include an edge SSD device. The edge SSD device may include one or more non-volatile memory circuits. The edge SSD device may include one or more memory controllers configured to operate the one or more non-volatile memory circuits. The edge SSD device may include one or more wireless transceivers. The edge SSD device may include a data processor configured to receive first type data from the first remote sensor device using the one or more wireless transceivers, and to receive second type data from the second remote sensor device using the one or more wireless transceivers. In some embodiments, the data processor may also be configured to aggregate the first type of data and the second type of data, process or filter the aggregated data, store the aggregated data by the one or more memory controllers in the one or more non-volatile memory circuits, and transmit the processed or filtered data using the one or more wireless transceivers.

[0006] Some embodiments may include a computer-implemented method for collecting, processing, and / or filtering edge data. The method may include: controlling one or more non-volatile memory circuits of an edge solid-state drive (SSD) device by one or more memory controllers. The method may include: receiving data from a first remote sensor device and a second remote sensor device by one or more wireless transceivers of the edge SSD device. The method may include: aggregating data from the first and second remote sensor devices into aggregated data by the edge SSD device. The method may include: storing the aggregated data into the one or more non-volatile memory circuits by the one or more memory controllers. The method may include: processing or filtering the aggregated data by the edge SSD device. The method may include: transmitting the processed or filtered data by the edge SSD device. Attached Figure Description

[0007] The foregoing and additional features and advantages of this disclosure will become clearer from the following detailed description with reference to the accompanying drawings, in which:

[0008] Figure 1 A block diagram of an edge SSD device according to some embodiments is shown.

[0009] Figure 2 The illustration includes, according to some embodiments Figure 1 Block diagram of an edge data system consisting of an edge SSD device and a remote sensor device configured in a P2P network.

[0010] Figure 3 The illustration includes, according to some embodiments Figure 1 A block diagram of an edge SSD device and another edge data system with remote sensor devices having different P2P configurations.

[0011] Figure 4 The illustration includes, according to some embodiments Figure 1 A block diagram of an edge SSD device and various remote sensor devices, as well as another edge data system containing associated sensor data.

[0012] Figure 5 This is a flowchart illustrating techniques for collecting, processing, and / or filtering edge data by using an edge SSD device to detect anomalous data, according to some embodiments.

[0013] Figure 6 This is a flowchart illustrating techniques for collecting, processing, and / or filtering edge data by performing statistical analysis using an edge SSD device, according to some embodiments.

[0014] Figure 7 This is a flowchart illustrating techniques for collecting, processing, and / or filtering edge data using an edge SSD device, according to some embodiments.

[0015] Figure 8 This is a flowchart illustrating another technique for collecting, processing, and / or filtering edge data by using an edge SSD device to detect anomalous data, according to some embodiments.

[0016] Figure 9 This is a flowchart illustrating another technique for collecting, processing, and / or filtering edge data by performing statistical analysis using an edge SSD device, according to some embodiments. Detailed Implementation

[0017] Reference will now be made in detail to the embodiments disclosed herein, examples of which are illustrated in the accompanying drawings. In the following detailed description, numerous specific details are set forth to enable a thorough understanding of the inventive concept. However, it should be understood that those skilled in the art can practice the inventive concept without these specific details. In other instances, known methods, processes, components, circuits, and networks have not been described in detail to avoid unnecessarily obscuring aspects of the embodiments.

[0018] It will be understood that although the terms first, second, etc., may be used herein to describe various elements, these elements should not be limited by these terms. These terms are used only to distinguish one element from another. For example, without departing from the scope of the inventive concept, a first sensor may be referred to as a second sensor, and similarly, a second sensor may be referred to as a first sensor.

[0019] The terminology used in the description of the inventive concept herein is for the purpose of describing particular embodiments only and is not intended to limit the inventive concept. As used in the description of the inventive concept and the appended claims, the singular form is intended to include the plural form as well, unless the context clearly indicates otherwise. It will also be understood that the term “and / or (and / or)” as used herein indicates or covers any and all possible combinations of one or more of the associated listed items. It will also be understood that the term “comprising” as used in this specification indicates the presence of the stated features, integrals, steps, operations, elements, and / or components, but does not exclude the presence or addition of one or more other features, integrals, steps, operations, elements, components, and / or groups thereof. Components and features in the drawings are not necessarily drawn to scale.

[0020] Collecting and processing the massive amounts of data generated by sensors at the edge of networks (such as the internet or local area networks) is a challenge. Transmitting such large volumes of data is often impossible due to network bandwidth limitations, cost barriers, power consumption, transmission latency, and other factors. However, the Internet of Things (IoT) continues to expand as the total number of devices and sensors connected to the internet and other networks grows. This expansion threatens the ability to collect, process, and transmit the generated data.

[0021] The embodiments disclosed herein include edge SSD devices and edge data systems including P2P sensor networks. Edge SSD devices can communicate via wireless networks and can aggregate data from multiple sources, including remote sensors and other data sources. Edge SSD devices can be used in conjunction with various applications, such as edge computing, IoT, home automation, 4G and / or 5G networks, and in data centers.

[0022] The edge data system disclosed herein may include one or more edge SSD devices and remote IoT sensors to collect, store, and disseminate data from the network edge while reducing cost, power consumption, latency, and bandwidth. The one or more edge SSD devices may utilize one or more short- to mid-range wireless transceivers (such as Wi-Fi transceivers or Bluetooth transceivers). One or more edge SSD devices can use one or more remote wireless transceivers (such as cellular transceivers) to communicate with sensors near the network edge. Alternatively, one or more edge SSD devices can use wired connections (such as Ethernet connections) to communicate with the wider Internet.

[0023] Figure 1 A block diagram of an edge SSD device 105 according to some embodiments is shown. Figure 2 The illustration includes, according to some embodiments Figure 1 Block diagram of edge SSD device 105 and edge data system 200 with remote sensor devices (e.g., 205a to 205n) configured in P2P network. Figure 3 The illustration includes, according to some embodiments Figure 1 A block diagram of an edge SSD device 105 and another edge data system 300 with remote sensor devices (e.g., 205a to 205n) having different P2P configurations. Now refer to... Figure 1 , Figure 2 and Figure 3 .

[0024] Edge SSD device 105 may be a standalone device with wireless network capabilities. In some embodiments, edge SSD device 105 may be deployed as a standalone device at the network edge. In some embodiments, edge SSD device 105 may be connected to host 250 via a standard connector (such as PCIe or U.2). Edge SSD device 105 may include SSD 110, which includes one or more non-volatile memory circuits (e.g., 115) and one or more memory controllers 120. The one or more memory controllers 120 may operate one or more non-volatile memory circuits (e.g., 115). For example, the one or more non-volatile memory circuits (e.g., 115) may be NAND memory circuits. It will be understood that other suitable types of non-volatile memory circuits may be included in SSD 110.

[0025] Edge SSD device 105 may include one or more wireless transceivers (e.g., 190, 195, 198). Edge SSD device 105 may also include a data processor 125 for aggregating data 220 received from remote sensor devices (e.g., 205a to 205n) using one or more wireless transceivers (e.g., 190, 195, 198) into aggregated data 225. In some embodiments, data processor 125 includes a microprocessor. In some embodiments, data processor 125 includes field-programmable gate array (FPGA) logic. In some embodiments, data processor 125 includes application-specific integrated circuit (ASIC). In some embodiments, data processor 125 includes a coprocessor. In some embodiments, data processor 125 includes a complex programmable logic device (CPLD). It will be understood that edge SSD device 105 may include any suitable means to facilitate data processing. Data processor 125 may process and / or filter aggregated data 225 into processed and / or filtered data 230, and may store aggregated data 225 into one or more non-volatile memory circuits (e.g., 115) via one or more memory controllers 120. Therefore, aggregated data 225 can be stored on SSD 110. Data processor 125 can add together the values ​​from the stored aggregated data 225. Data processor 125 can multiply together the values ​​from the stored aggregated data 225. Data processor 125 can transform the values ​​from the stored aggregated data 225. As further described below, data processor 125 can cause processed and / or filtered data 230 to be transmitted using one or more wireless transceivers (e.g., 190, 195, 198). Therefore, purpose-specific information can be provided outside the network edge while reducing bandwidth load on networks and remote servers in the cloud. Purpose-specific information may include, for example, anomalous data, error data, data summaries, triggering events associated with the data, threshold levels associated with the data, data ranges, summed values, etc. Additionally, processed and / or filtered data 230 can be stored and stored on SSD 110. One or more transceivers (e.g., 190, 195, 198) may include a first transceiver (e.g., 190) for communicating with remote sensor devices (e.g., 205a to 205n) and a second transceiver (e.g., 195, 198) configured to communicate with the Internet.

[0026] Data processor 125 may include an anomaly data module 135, which can detect anomaly data 235 within aggregated data 225. Anomaly data 235 may include at least one of erroneous data (e.g., aggregated data 225 is determined to be part of an error based on predefined conditions) and data outside of a predefined set of parameters. For example, anomaly data 235 may include an image of a face or an image of a specific object. As a further example, anomaly data 235 may include specific data of interest (e.g., a specific frame of interest within a series of images, a specific temperature within a series of temperature readings, a specific type of movement of a detected object, etc.). Data processor 125 may cause anomaly data 235 to be transmitted using one or more wireless transceivers (e.g., 190, 195, 198). By transmitting anomaly data 235 instead of all aggregated data 225, edge SSD device 105 can reduce the burden on network devices and the network. For example, fewer network components may be required, power consumption may be reduced and saved, and transmission latency may be improved, etc.

[0027] Data processor 125 may include statistical analysis module 130, which can perform statistical analysis on aggregated data 225 and generate statistical summaries 240 of at least some of the aggregated data 225. Data processor 125 may enable the statistical summaries 240 to be transmitted using one or more wireless transceivers (e.g., 190, 195, 198). By transmitting statistical summaries 240 instead of all aggregated data 225, edge SSD device 105 can reduce the bandwidth and throughput burden on network devices and the network. For example, fewer network components may be required, power consumption may be reduced and saved, and transmission latency may be improved.

[0028] The data processor 125 may include a third-party instruction module 138, which may receive and include one or more instructions from a third party. The one or more instructions may relate to processing and / or filtering aggregated data 225, saving and providing aggregated data 225, saving and providing anomalous data 235 associated with aggregated data 225, saving and providing a statistical summary 240 associated with aggregated data 225, saving and providing an addition summary of aggregated data 225, saving and providing a multiplication summary of aggregated data 225, and / or performing other data transformations on aggregated data 225 that result in reduced data transmission.

[0029] One or more wireless transceivers (e.g., 190, 195, 198) may include one or more WiFi transceivers (e.g., 190). For example, one or more WiFi transceivers may include multi-band WiFi N×N Multiple-Input Multiple-Output (MIMO) transceivers. One or more wireless transceivers (e.g., 190, 195, 198) may include one or more cellular radio transceivers (e.g., 195 and 198). One or more cellular radio transceivers (e.g., 195 and 198) may include one or more 4G transceivers (e.g., 195). One or more cellular radio transceivers (e.g., 195 and 198) may include one or more 5G transceivers (e.g., 198). One or more wireless transceivers (e.g., 190, 195, 198) may include two or more WiFi transceivers (e.g., 190). One or more wireless transceivers (e.g., 190, 195, 198) may include two or more cellular radio transceivers (e.g., 195 and 198). Edge SSD device 105 can receive data 220 from remote sensor devices (e.g., 205a to 205n) using one or more WiFi transceivers (e.g., 190). Edge SSD device 105 can aggregate data from remote sensor devices (e.g., 205a to 205n) on WiFi connectivity limitations (e.g., up to 250 connections per WiFi transceiver on edge SSD device 105). Edge SSD device 105 can use one or more cellular transceivers (e.g., 195 and 198) to transmit processed and / or filtered data 230. Edge SSD device 105 can collect data 220, aggregate, process, and / or filter data 220, and incrementally transmit processed and / or filtered data 230. Therefore, fewer cellular transceivers may be required than WiFi transceivers.

[0030] Edge SSD device 105 may include a communication module 140. Communication module 140 may include one or more transceivers (e.g., 190, 195, 198). Communication module 140 may include a WiFi radio module 145 for controlling one or more WiFi transceivers (e.g., 190). Communication module 140 may include a cellular radio module 150 for controlling one or more cellular transceivers (e.g., 195 and 198). Communication module 140 may include an Ethernet module 155 having one or more Ethernet ports (e.g., 160). Communication module 140 may include a Wireless Long Term Evolution (LTE) module 165, which may operate in conjunction with cellular radio module 150 to control one or more cellular transceivers (e.g., 195 and 198). Wireless LTE module 165 may support cellular phone wireless standards (such as 4G and 5G). In some embodiments, wireless LTE module 165 may support cellular phone wireless standards from 1G to NG, where N is a positive integer greater than 1. Communication module 140 may include a Transmission Control Protocol (TCP) module 170. Communication module 140 may include a Remote Direct Memory Access (RDMA) module 175, which can, for example, transfer data between SSD 110 and data processor 125. Communication module 140 may include an Internet Protocol (IP) module 180. Edge SSD device 105 may include a System Management (SM) bus 112. SM bus 112 can communicatively connect one or more memory controllers 120, data processor 125, and communication module 140 together. In some embodiments, one or more WiFi radio transceivers (e.g., 190) can receive data 220 from remote sensor devices (e.g., 205a to 205n), and Ethernet module 155 can transmit processed and / or filtered data 230 through one or more Ethernet ports 160.

[0031] Edge SSD device 105 may include a standard power connector 185. For example, power connector 185 may be a U.2 power connector. As another example, power connector 185 may be a Power over Ethernet (PoE) connector. Using a PoE connector allows for a lower power consumption mode and reduces power consumption. Where edge SSD device 105 may consume 25 watts (W) or more of power at or near this level, power connector 185 may be a connector other than a PoE connector. It will be understood that any suitable power connector can be used. In a standalone configuration, edge SSD device 105 may receive 12 volts (V) direct current (DC) through the power pins of power connector 185. Because aggregated data 225 can be locally analyzed, processed, and / or filtered into filtered data 230, and edge SSD device 105 can send less data, edge SSD device 105 can consume less power and thus save power. In an alternative embodiment, edge SSD device 105 may be directly connected to host 250.

[0032] Remote sensor devices (e.g., 205a to 205n) may include a wind speed sensor 205a, an accelerometer 205b, a camera 205c, etc. The camera 205c may be, for example, a visible light camera, an infrared camera, a still image camera, or a video camera. Remote sensor devices (e.g., 205a to 205n) may also include a temperature sensor 205d, a motion sensor 205e, a humidity sensor 205f, a water sensor 205g, or other types of sensors 205n. Each of the remote sensor devices (e.g., 205a to 205n) may each include a P2P module (or P2P logic module) (e.g., 210a to 210n). Each of the remote sensor devices (e.g., 205a to 205n) may each include a wireless transceiver (e.g., 215a to 215n). For example, the wireless transceiver (e.g., 215a to 215n) may include a WiFi transceiver. The P2P module may include logic for receiving and forwarding data packets 220 between remote sensor devices or between a specific remote sensor device and the edge SSD device 105. Depending on the distance between a specific remote sensor device (e.g., 205e) and the edge SSD device 105, the remote sensor device (e.g., 205e) may forward data packets 220 via adjacent remote sensor devices (e.g., 205d) or forward data packets 220 directly to the edge SSD device 105. Any particular data packet 220 may make multiple P2P hops through multiple remote sensor devices (e.g., 205a to 205n) before reaching the edge SSD device 105. Figure 3As shown, based on the fact that a specific remote sensor device (e.g., 205e) is located relatively close to the edge SSD device 105, the specific remote sensor device (e.g., 205e) can directly send data 220 to the edge SSD device 105. Figure 2 As shown, based on the fact that a specific remote sensor device (e.g., 205e) is located relatively far from the edge SSD device 105, the specific remote sensor device (e.g., 205e) may alternatively send data 220 to a nearby remote sensor device (e.g., 205d). The P2P module (e.g., 210e) of the specific remote sensor device (e.g., 205e) can determine whether to send data to a nearby remote sensor device (e.g., 205d) or directly to the edge SSD device 105 based on the distance between the specific remote sensor device (e.g., 205e) and the edge SSD device 105. Therefore, each of the remote sensor devices (e.g., 205a to 205n) can each send data directly to the edge SSD device 105, or additionally determine a routing path through other remote sensor devices to communicate with the edge SSD device 105.

[0033] Figure 4 The illustrations show the respective components according to some embodiments. Figure 1 A block diagram of an edge data system 400 comprising an edge SSD device 105, various remote sensor devices (e.g., 205a to 205n), and associated sensor data (e.g., 405a to 405n). The edge SSD device 105 may receive sensor data (e.g., 405a to 405n) directly from each of the remote sensor devices (e.g., 205a to 205n) or via a P2P network. For example, the edge SSD device 105 may receive sensor data (e.g., 405a to 405n) at a rate between 1 gigabits per second (Gb / s) and 10 Gb / s. For example, the edge SSD device 105 may transmit processed and / or filtered data 230 to a cloud 415 at a rate of 1 Gb / s or less. Figure 1 The data processor 125 can enable ( Figure 2 The abnormal data 235 is generated by using one or more wireless transceivers (e.g., Figure 1 (190, 195, 198) were sent to cloud 415. Figure 1 The data processor 125 can enable ( Figure 2 )Statistical summary 240 using one or more wireless transceivers (e.g., Figure 1 190, 195, and 198 were sent to cloud 415.

[0034] Edge SSD device 105 can be used in conjunction with various applications, such as edge computing, IoT, home automation, networking, and in data centers. For example, remote sensors (e.g., 205a to 205n) can be located in a data center, and edge SSD device 105 can aggregate sensor data from various points within or near the data center. As another example, a distributed file system can receive processed and / or filtered data 230 from edge SSD device 105 and can accelerate computing power based on the processed and / or filtered data 230 provided by edge SSD device 105. As yet another example, a distributed network can achieve accelerated hardware consensus based on the processed and / or filtered data 230 provided by edge SSD device 105.

[0035] Additionally, telecommunications applications can rely on the edge SSD device 105 for edge caching of local devices (such as connected sensor nodes). Instead of remote sensors, local data consumers can receive and use processed and / or filtered data 230 provided by the edge SSD device 105. Accelerated processing can be achieved based on the processed and / or filtered data 230 provided by the edge SSD device 105. For example, applications can more easily find and discover data to serve video streaming applications. Edge databases can receive and use the processed and / or filtered data 230 provided by the edge SSD device 105. Self-describing documents and data formats can receive and use the processed and / or filtered data 230 provided by the edge SSD device 105.

[0036] Furthermore, industrial automation applications, including data control systems (such as Supervisory Control and Data Acquisition (SCADA)), can receive and use processed and / or filtered data 230 provided by the edge SSD device 105. For industrial automation applications, decisions can be made closer to the network edge based on the processed and / or filtered data 230 provided by the edge SSD device 105. Additionally, data for industrial automation applications can be stored on the edge SSD device 105, and only important results are filtered into the hierarchical structure of network nodes.

[0037] Figure 5 This illustrates the detection of anomalous data (e.g., using an edge SSD device 105) according to some embodiments. Figure 2 Flowchart 500 (235) describes a technique for collecting and filtering edge data. Now refer to... Figures 1 to 5 .

[0038] In 505, remote sensor devices (e.g., Figure 2(205a to 205n) can collect data and wirelessly transmit data. At 510, the edge SSD device 105 can receive sensor data 220. At 515, the edge SSD device 105 can determine the IP type of the sensor data 220. Based on the IP type of the sensor data 220 being type 0, the process can proceed to 520a, then to 525a, wherein IP type 0 data can be processed by the edge SSD device 105. Based on the IP type of the sensor data 220 being type 1, the process can proceed to 520b, then to 525b, wherein IP type 1 data can be processed by the edge SSD device 105. Based on the IP type of the sensor data 220 being type 2, the process can proceed to 520c, then to 525c, wherein IP type 2 data can be processed by the edge SSD device 105.

[0039] At 530, sensor data 220 can be stored, processed, and / or filtered by edge SSD device 105. At 535, edge SSD device 105 can determine whether sensor data 220 includes anomalous data 235. Based on the determination that sensor data 220 includes anomalous data 235, the process can proceed to 540, whereby anomalous data 235 can be sent to cloud 415. Based on the determination that sensor data 220 does not include anomalous data 235, the process can proceed to 545, whereby sensor data 220 can be refined. At 550, edge SSD device 105 can determine whether any further anomalies exist in the refined data. Based on the determination that further anomalies exist, the process can proceed to 540, whereby anomalous data 235 can be sent to cloud 415. Based on the determination that no further anomalies exist, the process can terminate.

[0040] Figure 6 This is a flowchart 600 illustrating a technique for collecting, processing, and / or filtering edge data by performing statistical analysis using an edge SSD device 105, according to some embodiments. Referring now... Figures 1 to 5 and Figure 6 .

[0041] In 605, remote sensor devices (e.g., Figure 2(205a to 205n) can collect data and wirelessly transmit data. At 610, the edge SSD device 105 can receive sensor data 220. At 615, the edge SSD device 105 can determine the IP type of the sensor data 220. Based on the IP type of the sensor data 220 being type 0, the process can proceed to 620a, and then to 625a, wherein the IP type 0 data can be processed by the edge SSD device 105. Based on the IP type of the sensor data 220 being type 1, the process can proceed to 620b, and then to 625b, wherein the IP type 1 data can be processed by the edge SSD device 105. Based on the IP type of the sensor data 220 being type 2, the process can proceed to 620c, and then to 625c, wherein the IP type 2 data can be processed by the edge SSD device 105.

[0042] At 630, sensor data 220 can be stored by edge SSD device 105. At 635, edge SSD device 105 can perform statistical analysis on sensor data 220. At 640, edge SSD device 105 can determine whether statistical summary 240 is complete. Based on the determination that statistical summary 240 is complete, the process can proceed to 645, where statistical summary 240 can be sent to cloud 415. Based on the determination that statistical summary 240 is not complete, the process can proceed to 650, where sensor data 220 can be refined. At 655, edge SSD device 105 can further perform statistical analysis on sensor data 220, after which the process can return to 640 to determine whether statistical summary 240 is complete. Based on the determination that statistical summary 240 is complete at 640, the process can proceed to 645, where statistical summary 240 can be sent to cloud 415.

[0043] Figure 7 This is a flowchart 700 illustrating techniques for collecting, processing, and / or filtering edge data using an edge SSD device, according to some embodiments. Referring now to… Figures 1 to 5 and Figure 7 .

[0044] At 705, edge SSD device 105 can receive data 220 from remote sensors (e.g., 205a to 205n) using one or more wireless transceivers (e.g., 190). At 710, edge SSD device 105 can aggregate the data 220 into aggregated data 225. At 715, edge SSD device 105 can store the aggregated data 225 into one or more non-volatile memory circuits (e.g., 115). At 720, edge SSD device 105 can process and / or filter the aggregated data 225 into processed and / or filtered data 230. At 725, edge SSD device 105 can transmit the processed and / or filtered data 230 using one or more wireless transceivers (e.g., 195, 198).

[0045] Figure 8 This is a flowchart 800 illustrating another technique for collecting, processing, and / or filtering edge data by using an edge SSD device to detect anomalous data, according to some embodiments. Referring now... Figures 1 to 5 and Figure 8 .

[0046] At 805, edge SSD device 105 can receive data 220 from remote sensors (e.g., 205a to 205n) using one or more wireless transceivers (e.g., 190). At 810, edge SSD device 105 can aggregate the data 220 into aggregated data 225. At 815, edge SSD device 105 can store the aggregated data 225 into one or more non-volatile memory circuits (e.g., 115). At 820, edge SSD device 105 can detect anomalous data 235 within the aggregated data 225 using an anomalous data module 135. At 825, edge SSD device 105 can transmit the anomalous data 235 using one or more wireless transceivers (e.g., 195, 198).

[0047] Figure 9 This is a flowchart 900 illustrating another technique for collecting, processing, and / or filtering edge data by performing statistical analysis using an edge SSD device, according to some embodiments. Referring now to… Figures 1 to 5 and Figure 9 .

[0048] At 905, edge SSD device 105 can receive data 220 from remote sensors (e.g., 205a to 205n) using one or more wireless transceivers (e.g., 190). At 910, edge SSD device 105 can aggregate the data 220 into aggregated data 225. At 915, edge SSD device 105 can store the aggregated data 225 into one or more non-volatile memory circuits (e.g., 115). At 920, edge SSD device 105 can perform statistical analysis on the aggregated data 225 using its statistical analysis module 130. At 925, edge SSD device 105 can generate a statistical summary 240 of the aggregated data 225. At 930, edge SSD device 105 can transmit the statistical summary 240 using one or more wireless transceivers (e.g., 195, 198).

[0049] The various operations described above can be performed by any suitable means capable of performing the operations (such as various hardware and / or software components, circuits and / or modules).

[0050] Some embodiments may include a standalone edge SSD device. The edge SSD device may include one or more non-volatile memory circuits. The edge SSD device may include one or more memory controllers configured to operate the one or more non-volatile memory circuits. The edge SSD device may include one or more wireless transceivers. The edge SSD device may include a data processor configured to aggregate data received from a first remote sensor device and a second remote sensor device using one or more wireless transceivers into aggregated data. In some embodiments, the data processor may also be configured to process and / or filter the aggregated data into processed and / or filtered data such that the aggregated data is stored by one or more memory controllers into one or more non-volatile memory circuits, and that the processed and / or filtered data is transmitted using one or more wireless transceivers.

[0051] In some embodiments, the data processor includes an anomalous data module configured to detect anomalous data within aggregated data. In some embodiments, anomalous data includes at least one of erroneous data and data outside a predefined set of parameters. In some embodiments, anomalous data includes at least one of images of faces and images of specific objects. In some embodiments, the data processor is configured to transmit anomalous data to a cloud (such as a data center) using one or more wireless transceivers. In some embodiments, the data processor includes a statistical analysis module configured to perform statistical analysis on the aggregated data and generate a statistical summary of at least some of the aggregated data. In some embodiments, the data processor is configured to transmit a statistical summary of at least some of the aggregated data to a cloud (such as a data center) using one or more wireless transceivers. In some embodiments, the one or more wireless transceivers include at least one of WiFi radio transceivers and cellular radio transceivers. In some embodiments, the one or more wireless transceivers include two or more WiFi radio transceivers and two or more cellular radio transceivers.

[0052] The edge SSD device may include a communication module. The communication module may include one or more transceivers, including at least one of a WiFi radio transceiver and a cellular radio transceiver; an Ethernet module including one or more Ethernet ports; at least one of a 4G module and a 5G module; a Transmission Control Protocol (TCP) module; a Remote Direct Memory Access (RDMA) module; and an Internet Protocol (IP) module. The edge SSD device may include a system management bus configured to communicatively connect one or more memory controllers, a data processor, and the communication module together.

[0053] In some embodiments, the WiFi transceiver is configured to receive data from a first remote sensor device and a second remote sensor device, and the cellular transceiver is configured to transmit processed and / or filtered data. In some embodiments, the WiFi transceiver is configured to receive data from a first remote sensor device and a second remote sensor device, and the Ethernet module is configured to transmit the processed and / or filtered data through one or more Ethernet ports.

[0054] Some embodiments may include an edge data system. The edge data system may include a first remote sensor device configured to collect a first type of data. The edge data system may include a second remote sensor device configured to collect a second type of data different from the first type. The edge data system may include an edge SSD device. The edge SSD device may include one or more non-volatile memory circuits. The edge SSD device may include one or more memory controllers configured to operate one or more non-volatile memory circuits. The edge SSD device may include one or more wireless transceivers. The edge SSD device may include a data processor configured to receive first type data from the first remote sensor device using one or more wireless transceivers, and to receive second type data from the second remote sensor device using one or more wireless transceivers. In some embodiments, the data processor may also be configured to: aggregate the first type of data and the second type of data; process and / or filter the aggregated data into processed and / or filtered data; store the aggregated data by one or more memory controllers into one or more non-volatile memory circuits; and transmit the processed and / or filtered data using one or more wireless transceivers.

[0055] In some embodiments, the first remote sensor device includes a P2P module configured to receive and transmit data packets from at least a second remote sensor device. In some embodiments, the second remote sensor device includes a P2P module configured to receive and transmit data packets from at least the first remote sensor device. In some embodiments, the first remote sensor device is configured to transmit data packets from both the first and second remote sensor devices to an edge SSD device. In some embodiments, the first remote sensor device includes at least one of a camera, an accelerometer, a wind speed sensor, a temperature sensor, and a motion sensor. In some embodiments, the second remote sensor device includes at least one of a humidity sensor, a water sensor, and other sensors.

[0056] In some embodiments, the data processor includes an anomalous data module configured to detect anomalous data within aggregated data. In some embodiments, anomalous data includes at least one of erroneous data and data outside of a predefined set of parameters. In some embodiments, the data processor is configured to transmit anomalous data to a cloud (such as a data center) using one or more wireless transceivers.

[0057] In some embodiments, the data processor includes a statistical analysis module configured to perform statistical analysis on the aggregated data and generate statistical summaries of at least some of the aggregated data. In some embodiments, the data processor is configured to transmit the statistical summaries of at least some of the aggregated data to a cloud (such as a data center) using one or more wireless transceivers.

[0058] Some embodiments may include a computer-implemented method for collecting, processing, and / or filtering edge data (hereinafter referred to as the "method"). The method may include one or more non-volatile memory circuits of an edge solid-state drive (SSD) device controlled by one or more memory controllers. The method may include receiving data from a first remote sensor device and a second remote sensor device by one or more wireless transceivers of the edge SSD device. The method may include aggregating data from the first and second remote sensor devices into aggregated data by the edge SSD device. The method may include storing the aggregated data into one or more non-volatile memory circuits by one or more memory controllers. The method may include processing and / or filtering the aggregated data into processed and / or filtered data by the edge SSD device. The method may include transmitting the processed and / or filtered data by the edge SSD device.

[0059] The method may include detecting anomalous data within aggregated data by an anomaly data module of the edge SSD device, wherein the anomalous data includes at least one of erroneous data and data outside of a predefined set of parameters. Transmission may include the edge SSD device sending the anomalous data to a cloud (such as a data center) using one or more wireless transceivers.

[0060] The method may include performing statistical analysis on aggregated data by a statistical analysis module of an edge SSD device. The method may include generating a statistical summary of at least some of the aggregated data by the statistical analysis module. Transmission may include transmitting the statistical analysis to a cloud (such as a data center) by the edge SSD device using one or more wireless transceivers. In some embodiments, processing may include summing a first value and a second value in the aggregated data by the edge SSD device to obtain a summed data. The method may include transmitting the summed data by the edge SSD device.

[0061] The blocks or steps of methods or algorithms and functions described in conjunction with the embodiments disclosed herein can be implemented directly in hardware, as software modules executed by a processor, or a combination of both. Modules can include hardware, software, firmware, or any combination thereof. If implemented in software, the functionality can be stored as one or more instructions or code on or transferred through a tangible, non-transitory computer-readable medium. Software modules can reside in random access memory (RAM), flash memory, read-only memory (ROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), registers, hard disks, removable disks, CD-ROMs, or any other form of storage medium known in the art.

[0062] The following discussion is intended to provide a brief general description of one or more suitable machines that can implement certain aspects of the inventive concept. Typically, one or more machines include a system bus, a processor, memory (e.g., RAM, ROM, or other state-saving media), storage devices, video interfaces, and input / output interface ports attached to the system bus. One or more machines can be controlled at least in part by input from conventional input devices (such as a keyboard, mouse, etc.) and by instructions received from another machine, interaction with a virtual reality (VR) environment, biofeedback, or other input signals. As used herein, the term "machine" is intended to broadly encompass a single machine, a virtual machine, or a system of communicatively connected machines, virtual machines, or devices operating together. Exemplary machines include computing devices (such as personal computers, workstations, servers, portable computers, handheld devices, telephones, tablets, etc.) and transportation devices (such as private or public transportation devices (e.g., cars, trains, taxis, etc.)).

[0063] One or more machines may include embedded controllers (such as programmable or non-programmable logic devices or arrays, application-specific integrated circuits (ASICs), embedded computers, cards, etc.). One or more machines may utilize one or more connections to one or more remote machines (such as via network interfaces, modems, or other communication connections). Machines may be interconnected via physical and / or logical networks (such as intranets, the Internet, local area networks, wide area networks, etc.). Those skilled in the art will understand that network communication can utilize a variety of wired and / or wireless short-range or long-range carriers and protocols, including radio frequency (RF), satellite, microwave, IEEE 545.11, Bluetooth, optical, infrared, cable, laser, etc.

[0064] Embodiments of this disclosure can be described by referring to or in conjunction with associated data, including functions, processes, data structures, applications, etc., which, when accessed by a machine, cause the machine to perform tasks or define abstract data types or underlying hardware environments. The associated data can be stored, for example, in volatile and / or non-volatile memory (e.g., RAM, ROM, etc.), or in other storage devices and their associated storage media (including hard disk drives, floppy disks, optical storage devices, magnetic tape, flash memory, memory sticks, digital video disks, bio-storage devices, etc.). The associated data can be transmitted over a transmission environment (including physical and / or logical networks) in the form of packets, serial data, parallel data, propagated signals, etc., and can be used in compressed or encrypted formats. The associated data can be used in a distributed environment and stored locally and / or remotely for machine access.

[0065] Having described and illustrated the principles of this disclosure with reference to the illustrated embodiments, it will be appreciated that the illustrated embodiments may be modified in arrangement and detail without departing from these principles, and may be combined in any desired manner. Furthermore, although the foregoing discussion focuses on particular embodiments, other configurations can be contemplated. Specifically, even though expressions such as "according to an embodiment of the inventive concept" are used herein, these phrases are intended to refer generally to the possibilities of the embodiments and not to limit the inventive concept to particular embodiment configurations. As used herein, these terms may refer to the same or different embodiments that can be combined into other embodiments.

[0066] Embodiments of this disclosure may include a non-transient machine-readable medium comprising instructions executable by one or more processors, including instructions for performing elements of the inventive concept as described herein.

[0067] The foregoing illustrative embodiments are not to be construed as limiting the inventive concept. Although some embodiments have been described, those skilled in the art will readily understand that many modifications can be made to these embodiments without substantially departing from the novel teachings and advantages of this disclosure. Therefore, all such modifications are intended to be included within the scope defined in the claims of this disclosure.

Claims

1. An edge solid-state driver device, comprising: One or more non-volatile memory circuits; One or more memory controllers are configured to operate the one or more non-volatile memory circuits; One or more wireless transceivers; as well as A data processor is configured to aggregate sensor data received from a first device and a second device using one or more wireless transceivers into aggregated data. The data processor is further configured to process the aggregated data into processed data, such that the aggregated data is stored by the one or more memory controllers in the one or more non-volatile memory circuits, and that the processed data is transmitted using the one or more wireless transceivers. The data processor is also configured as follows: Determine whether the sensor data includes anomalous data. Based on the determination that the sensor data includes anomalous data, the anomalous data is sent to the cloud. Based on the premise that the sensor data does not include abnormal data, the sensor data is refined. To determine if there are any further anomalies in the refined data, Based on the determination that further anomalies exist in the refined data, the anomaly data is sent to the cloud.

2. The edge solid-state driver device as claimed in claim 1, wherein, The data processor includes an anomaly data module configured to detect anomalous data within aggregated data.

3. The edge solid-state driver device as claimed in claim 2, wherein, Abnormal data includes at least one of the following: i) aggregated data is identified as part of an error based on predefined conditions, and ii) data with values ​​outside of a predefined set of parameters.

4. The edge solid-state driver device as claimed in claim 2, wherein, Abnormal data includes at least one of images of faces and images of specific objects.

5. The edge solid-state driver device as claimed in claim 2, wherein, The data processor is configured to transmit abnormal data to the data center using one or more wireless transceivers.

6. The edge solid-state driver device of claim 1, wherein, The data processor includes a statistical analysis module configured to perform statistical analysis on the aggregated data and generate statistical summaries of at least some of the aggregated data.

7. The edge solid-state driver device of claim 6, wherein, The data processor is configured to transmit a statistical summary of at least some of the aggregated data to the data center using the one or more wireless transceivers.

8. The edge solid-state driver device as claimed in claim 1, wherein, The data processor includes a third-party instruction module configured to receive one or more instructions from a third party. The one or more instructions involve at least one of the following: i) processing aggregated data, ii) saving and providing aggregated data, iii) providing anomalous data associated with aggregated data, iv) providing a statistical summary of aggregated data, and v) data transformation of aggregated data that results in reduced data transmission.

9. The edge solid-state driver device according to any one of claims 1 to 8, wherein, The one or more wireless transceivers include two or more WiFi radio transceivers and two or more cellular radio transceivers.

10. The edge solid-state driver device according to any one of claims 1 to 8, further comprising: The communication module includes: The one or more wireless transceivers include a first transceiver configured to communicate with a first device and a second device, and a second transceiver configured to communicate with the Internet. Ethernet module, including one or more Ethernet ports; Wireless Long Term Evolution Module; Transmission Control Protocol module; Remote direct memory access module; and Internet Protocol module; and A system management bus is configured to communicatively connect the one or more memory controllers, data processors, and communication modules together.

11. The edge solid-state driver device of claim 10, wherein, The first transceiver is configured to receive sensor data from the first device and the second device, and The second transceiver is configured to send the processed data.

12. The edge solid-state driver device of claim 10, wherein, The first transceiver is configured to receive sensor data from the first device and the second device, and The Ethernet module is configured to send the processed data through one or more Ethernet ports.

13. An edge data system, comprising: A first device is configured to collect sensor data of a first type; The second device is configured to collect sensor data of a second type that is different from the first type; as well as An edge solid-state driver device includes: One or more non-volatile memory circuits; One or more memory controllers are configured to operate the one or more non-volatile memory circuits; One or more wireless transceivers; and A data processor is configured to receive first-type sensor data from a first device using the one or more wireless transceivers, and to receive second-type sensor data from a second device using the one or more wireless transceivers. The data processor is further configured to aggregate first-type sensor data and second-type sensor data, process the aggregated data into processed data, store the aggregated data in the one or more memory controllers to the one or more non-volatile memory circuits, and transmit the processed data using the one or more wireless transceivers. The data processor is also configured as follows: Determine whether the sensor data includes anomalous data. Based on the determination that the sensor data includes anomalous data, the anomalous data is sent to the cloud. Based on the premise that the sensor data does not include abnormal data, the sensor data is refined. To determine if there are any further anomalies in the refined data, Based on the determination that further anomalies exist in the refined data, the anomaly data is sent to the cloud.

14. The edge data system of claim 13, wherein: The first device includes a point-to-point module configured to receive and transmit data packets from at least the second device; The second device includes a point-to-point module configured to receive and send data packets from at least the first device; The first device is configured to: i) send data packets directly to the edge solid-state drive device, and ii) determine a routing path through the second device to communicate with the edge solid-state drive device; as well as The second device is configured to: i) send data packets directly to the edge solid-state drive device, and ii) determine a routing path through the first device to communicate with the edge solid-state drive device.

15. The edge data system of claim 13, wherein: The first device includes at least one of a camera, an accelerometer, a wind speed sensor, a temperature sensor, and a motion sensor; and The second device includes at least one of a humidity sensor, a water sensor, and other sensors that are different from the humidity sensor and the water sensor.

16. The edge data system according to any one of claims 13 to 15, wherein: The data processor includes an anomaly data module configured to detect anomalous data within aggregated data; Abnormal data includes at least one of the following: erroneous data and data outside the predefined parameter set; and The data processor is configured to transmit abnormal data to the data center using one or more wireless transceivers.

17. The edge data system according to any one of claims 13 to 15, wherein: The data processor includes a statistical analysis module configured to perform statistical analysis on the aggregated data and generate statistical summaries of at least some of the aggregated data. and The data processor is configured to transmit a statistical summary of at least some of the aggregated data to the data center using the one or more wireless transceivers.

18. A computer-implemented method for collecting and processing edge data, the method comprising: One or more non-volatile memory circuits of an edge solid-state driver device are controlled by one or more memory controllers; One or more wireless transceivers of an edge solid-state driver device receive sensor data from a first device and a second device; Sensor data from the first and second devices are aggregated into aggregated data by an edge solid-state driver device; The aggregated data is stored in the one or more non-volatile memory circuits by the one or more memory controllers; The aggregated data is processed into processed data by an edge solid-state driver device; as well as Processed data is sent by the edge solid-state driver device. The method further includes: using an edge solid-state driver device to determine whether the sensor data includes anomalous data; based on determining that the sensor data includes anomalous data, sending the anomalous data to the cloud; based on determining that the sensor data does not include anomalous data, refining the sensor data; determining whether there are further anomalous data in the refined data; and based on determining that there are further anomalous data in the refined data, sending the anomalous data to the cloud.

19. The computer-implemented method as described in claim 18, wherein, The method further includes: Anomalies were detected within the aggregated data by the anomaly data module of the edge solid-state driver device. Abnormal data includes at least one of the following: erroneous data and data outside the predefined parameter set. The transmission includes: the edge solid-state drive device sending abnormal data to the data center using the one or more wireless transceivers.

20. The computer-implemented method as described in claim 18, wherein, The method further includes: The statistical analysis module of the edge solid-state driver device performs statistical analysis on the aggregated data; and The statistical analysis module generates statistical summaries of at least some of the aggregated data. The transmission includes: the edge solid-state drive device sending a statistical summary to the data center using the one or more wireless transceivers.

21. The computer-implemented method according to any one of claims 18 to 20, wherein, The method further includes at least one of the following steps: i) adding the first and second values ​​in the aggregated data to obtain summation data; ii) multiplying the first and second values ​​in the aggregated data to obtain multiplied data; and iii) transforming at least one of the first and second values ​​in the aggregated data into transformed data. The transmission includes transmitting at least one of the following by the edge solid-state driver device: i) summation data, ii) multiplication data, and iii) transformation data.

Images