<meter id="61161"></meter>
      <acronym id="61161"></acronym>
    <acronym id="61161"></acronym>

    1. <var id="61161"></var>
    2. <var id="61161"></var>

    3. <var id="61161"></var>

      <output id="61161"></output>


      How Edge Devices Enable Faster Insights From Video Analytics

      Never before have organizations relied so heavily on data. From basic problem solving to advanced safety precautions, this growing dependence has magnified both the complexity and importance of our IT architecture. Businesses today are, by necessity, becoming data-driven enterprises. In the video surveillance sector specifically, an unprecedented amount of data is being analyzed, and all signs point to continued growth in the coming years. One estimate (from IDC) forecasts that the amount of data generated around the globe destined to be used for analysis will increase 50-fold by 2025.

      Big Data Challenges

      The rise of big data applications and Internet of Things (IoT) technology means that organizations face unprecedented growth in the number of data touch points being utilized in a given application. Capturing input from a variety of end points, such as cameras and IoT sensors, increases the volume of data that must be stored, processed, managed, and protected. This combined with the advent of ultra-high definition cameras and artificial intelligence (AI) applications, means that surveillance systems are collecting more data and storing it for longer.

      Given the increasingly critical role video plays for security and operational purposes, deploying the most reliable storage solution is of paramount importance. Organizations cannot afford to lose data or video integrity, as the accuracy of AI systems rely heavily on this information. For AI applications, storing excess data for extended periods of time is required for systems to “learn” and improve their ability to perform predictive analysis. The more AI functionality that is built into deployments, the greater the storage infrastructure and capacity must be to optimize performance.

      Thus, any storage device used for these types of advanced applications must be as reliable as possible, ideally featuring redundant system components to maximize efficiency and minimize downtime. Unfortunately, relying solely on cloud data centers can cause problems for data-intensive applications. These solutions depend heavily upon Internet connection and the distance between cameras and their server, often causing latency issues, which can delay a transfer of real-time business critical information.

      When considering edge storage, drives deployed for big data applications must be capable of performing under extreme workload stress. A surveillance hard drive must be optimized for a 24×7 workload, without the luxury of occasional downtime, which can more than quadruple the annual number of hours a typical desktop drive must work. If an organization selects a drive for video applications that is not optimized for surveillance, the result can range from failures in video streaming quality and workload performance to subpar analytical capabilities.

      The need to keep hard drives going longer means that drives with health monitoring capabilities should be a priority, in order to maximize uptime and help prevent or recover from potential data loss related to disruptive incidents (such as power outages, vandalism, or natural disasters).

      Leveraging IT 4.0

      To manage the ever-growing complexity that characterizes today’s data-intensive applications and ensure businesses can successfully utilize all this data, a new infrastructure is emerging for business applications – an IT 4.0 data storage architecture that connects edge devices, IoT, the cloud, and enterprise data centers. The IT 4.0 approach effectively extends the power of the cloud to the edge of the data processing continuum, which helps mitigate latency issues because initial analysis takes place close to where the data was captured. This enables real-time decision-making that can power useful applications ranging from crime prevention to traffic management.

      By deploying edge computing devices powered by AI-optimized surveillance hard drives, several benefits can be achieved, such as reducing data access delays, avoiding bandwidth issues, and handling data compliance restrictions. The end result is a reduction in maintenance calls and an increase in overall customer satisfaction. That, in turn, can improve the bottom line. But the most important benefit is that edge devices powered by AI-enabled drives deliver faster insights, right on site, so that critical decision-making in real time becomes possible.

      One application made possible by data collected from AI-enabled security systems is efficient traffic flow management among connected vehicles. In this scenario, a smart camera can detect a car accident and immediately send an alert to command center personnel who can dispatch a traffic officer to the area to provide assistance. Another prime example is smart city traffic agencies utilizing cameras with object recognition to detect wrong-way drivers.

      The Takeaway

      Modern business applications should not rely on one technology, or take a “one size fits all” approach, but rather should address big data challenges by implementing an IT 4.0 data storage architecture, which leverages data from multiple end points, edge devices, data centers, and the cloud. Choosing an IT 4.0 approach is the optimal strategy to take full advantage of the potential that lies in big data applications, and large-capacity AI-enabled hard drives play an essential role in this solution.

      安义| 范县| 遂平| 门源| 化州| 庆安| 石首| 江宁| 祥云| 郁南| 北仑| 平安| 闵行| 桂阳| 青龙山| 海盐| 广饶| 洛隆| 瑞昌| 西华| 清河| 武城| 佳县| 井陉| 东平| 佛坪| 东胜| 北辰| 沅陵| 北塔山| 兴文| 海北| 屏山| 塞罕坎| 墨玉| 鄞县| 博爱| 海门| 淳化| 子长| 曲江| 兴义| 杭锦后旗| 黔阳| 淮南| 平安| 桦川| 栾川| 衡水| 莫索湾| 方城| 辽阳| 寿光| 原阳| 曲靖| 桦南| 磐石| 康山| 邯郸| 洋县| 横县| 邗江| 五台山| 鹤山| 芒康| 饶河| 海兴| 莱州| 临沂| 天台| 丹徒| 平顶山| 太仓| 万荣| 多伦| 潞城| 抚远| 苏州| 景洪| 碌曲| 灯塔| 阿拉尔| 平塘| 固始| 宁波| 当阳| 融安| 宁城| 阿图什| 新源| 米林| 西平| 科尔沁左翼中旗| 万州龙宝| 大连| 枞阳| 泾源| 榆次| 犍为| 交城| 日喀则| 漯河| 新晃| 邵阳| 勃利| 南充| 斋堂| 围场| 淳化| 连州| 夏河| 曲阜| 荔浦| 益阳| 石台| 淇县| 罗江| 大柴旦| 邗江| 阳春| 普洱| 马站| 汶上| 砀山| 常山| 麻阳| 郸城| 二连浩特| 云梦| 海盐| 淮安| 莱西| 遵义县| 滦平| 金沙| 湟中| 古田| 岑溪| 新界| 吐鲁番| 辽阳县| 赤水| 长寿| 桂林农试站| 硕龙| 夏津| 徽县| 盐山| 六盘水| 龙胜| 平武| 太谷| 远安| 德钦| 繁昌| 准格尔旗| 龙川| 金坛| 兴义| 剑阁| 伊金霍洛旗| 腾冲| 中江| 渝北| 容城| 翼城| 广南| 万源| 布尔津| 黄冈| 嵩县| 徐家汇| 洛南| 广宁| 淖毛湖| 商南| 甘谷| 唐河| 夏邑| 武汉| 茫崖| 策勒| 介休| 密云上甸子| 淮北| 瑞金| 旌德| 邹平| 宾阳| 昌都| 四会| 突泉| 修武| 云县| 洛川| 柘城| 连江| 婺源| 平陆| 鹿邑| 莎车| 平鲁| 巴林右旗| 岳西| 岳西| 洛南| 都安| 锦屏| 河曲| 云浮| 永年| 屯溪| 青浦| 宜君| 漯河| 珙县| 阿荣旗| 峨眉山| 霍城| 刚察| 哈密| 和田| 青龙山| 帕里| 满都拉| 敖汉旗| 昌邑| 石柱| 扬中| 中环| 济宁| 仪陇| 新界| 黄陵| 乌什| 郏县| 赫章| 兴仁| 羊山| 百色| 新龙| 双江| 如皋| 吉木乃| 宝应| 容城| 云县| 策勒| 佛山| 武功| 凤台| 灯塔| 洛川| 西峡| 宜黄| 灵寿| 沁县| 莒南| 庆云| 宁津| 曲阳| 鞍山| 柞水| 宁安| 新邵| 梁山| 大庆| 安庆| 和林格尔| 邻水| 崂山| 常山| 东莞| 沁县| 海原| 余干| 马山| 建水| 呼兰| 景洪电站| 虎林| 延吉| 广安| 宣城| 平邑| 新平| 黄冈| 开县| 永修| 塔河| 甘德| 新都| 天池| 唐县| 五道梁| 鹤山| 汤原| 屯昌| 翁牛特旗| 广河| 莎车| 那仁宝力格| 囊谦| 宁城| 贵阳| 商水| 依安| 三门| 正兰旗| 广州| 淄川| 三门峡| 阜城| 洛阳| 普陀| 南海| 苍溪| 平台| 信都| 漾鼻| 临武| 通州| 青神| 淳安| 旬阳| 邱北| 绩溪| 奈曼旗| 广南| 庆阳| 福安| 凌源| 安丘| 枣阳| 湘阴| 巴塘| 海城| 泰来| 庆安| 川沙| 鹿寨| 隆回| 舒城| 渭源| 鸡西| 邵武| 唐山| 鹤山| 鄯善| 关岭| 河间| 海晏| 富源| 彰武| 高唐| 佛冈| 肇庆| 通化| 五指山| 旌德| 三水| 柘城| 丹阳| 南召| 昌乐| 镇沅| 郑州农试站| 民勤| 中心站| 通化| 英吉沙| 草河口| 巩义| 邱北| 七台河| 天山大西沟| 乡城| 东沙岛| 定襄| 定边| 拐子湖| 鄂托克旗| 尚义| 武定| 分宜| 得荣| 托托河| 方山| 锡林浩特| 崇明| 玛沁| 汝城| 新城子| 山丹| 宁南| 穆棱| 丹东| 岑溪| 绥阳| 兴国