Aryaka Networks, Inc.

Cisco Technology, Inc.

Other

Alcatel

Gupta, Ajit

Bharadhwaj, Rajeev

Nagaraj, Ashwath

Ashwath Nagaraj

Ajit Gupta

Rajeev Bharadhwaj

Thomas Jeffrey Enderwick

Henry Kin-Chuen Kwok

Peter Y Yu

Shyamtanu Majumder

Ramakrishna Rao

Vivek Padmanabhan

Naveen Maveli

Samar Sharma

Rina Panigrahy

Justin Joseph

Johny Nainwani

Parth Arvindbhai Patel

Wheling Cheng

Charlie Ghahremani

Bangalore J Shanker

Yoichi Hariguchi

Richard Schunk

Vikas Garg

Desmond Young

Mano Murthy

Ben Tseng

Alex S Kaufman

Benjamin Tseng

Surya Prakash Jonnavithula

Jiing-Yang Twu

Suryaprakash Jonnavithula

Mehdi Farid

Subrat Mishra

A method implemented through a server of a cloud computing network including subscribers of application acceleration as a service provided therethrough includes sampling time series data associated with each network entity for each feature thereof into a smaller time interval as a first data series and a second data series including a maximum value and a minimum value respectively of the sampled time series data for the each feature within the smaller time interval, and generating a reference data band from predicted future data sets. The method also includes detecting, based on the reference data band, an anomaly in real-time data associated with the each network entity for the each feature thereof and determining an event associated with a pattern of change of the real-time data associated with the each network entity based on executing an optimization algorithm to determine a series of anomalies including the detected anomaly.

Efficient detection and prediction of data pattern changes in a cloud-based application acceleration as a service environment

A method of data bandwidth overhead reduction in a protocol based communication over a Wide Area Network (WAN) includes transmitting, through a sender device of a source location, data packets of a sequence to a receiver device of a destination location communicatively coupled to the sender device through the WAN and storing a copy of the transmitted data packets in the sender device for a first threshold duration of time. When the receiver device receives a non-consecutive data packet, the receiver device waits for a second threshold period of time before transmitting a NAK message to the sender device related to non-receipt of one or more out-of-order data packet(s). The sender device interprets the NAK message and retransmits the one or more out-of-order data packet(s) to the receiver device after which the one or more out-of-order data packets are removed.

Data bandwidth overhead reduction in a protocol based communication over a wide area network (WAN)

Disclosed are systems and methods to provide application acceleration as a service. In one embodiment, a system includes a head office to serve an enterprise application comprised of a collaborative document. The system also includes a branch office to request the collaborative document from the head office. The enterprise application may also include a computed document and/or a static document. In addition, the system also includes a set of Point of Presence (POP) locations between the head office and the branch office to communicate the collaborative document, the computed document and the static document on behalf of the head office from a closest POP location to the head office to a closest POP location to the branch office and then onward to the branch office.

Application acceleration as a service system and method

Disclosed are a method and/or a system for defining logical channels and channel policies in an application acceleration environment. In one aspect, a system includes a branch site including a branch client. A headquarters site includes a headquarters server, the branch site and the headquarters site are communicatively coupled over a logical link via a transmission media. A first point of presence (POP) is communicatively coupled with a branch customer premise equipment (CPE) located at the branch site over a first segment of the logical link. A second POP is communicatively coupled with the first POP over a second segment of the logical link. Each segment of the logical link is constructed from a physical link and contains two segment endpoints. The physical link carries a network traffic of the network connection between the two segment endpoints of an associated segment.

Method and system for defining logical channels and channel policies in an application acceleration environment

Disclosed is a method of incremental computation of billing percentile values in a cloud based application acceleration as a service environment. In one aspect, a method includes sampling a usage data of a network entity of an application acceleration as a service provider in intervals of five minutes using a processor and a memory. A 95percentile value is automatically calculated based on a next value in the billing cycle after the top 5% of samples in the billing cycle. The 95percentile value of each of a plurality of billable units for each of billing measurements for a large scale data associated with the network entity is incrementally computed by computing the 95percentile value upon a newest set of data arrived to the network entity in each five minute interval. A billing amount is determined based on an incremental computation.

Incremental computation of billing percentile values in a cloud based application acceleration as a service environment

A method, an apparatus and/or a system of data compression through redundancy removal in an application acceleration environment is disclosed. In one aspect, a method includes generating through a fingerprint module of a redundancy removal engine associated with a first network element a hash identifier of at least one portion of data of a contiguous data block stored in a bidirectional cache memory of the redundancy removal engine associated with a first network element. The size of contiguous data block is larger than the size of the at least one portion of data of the contiguous data block for which the hash identifier is generated. The method further includes compressing a data stream through a transmission compression module of the redundancy removal engine based on the at least one a hash identifier that is indexed.

Data compression through redundancy removal in an application acceleration environment

Disclosed are a system, a method and an apparatus of reduction of routing and service performance management in an application acceleration environment. In one embodiment, a system includes a branch site that includes a branch client. In addition, the system includes a headquarters site that includes a headquarters server. The headquarters site including a headquarters server includes the branch site. The headquarters site is communicatively coupled over a link via transmission media. The link is identified through a link identifier. The headquarters site including a headquarters server also includes the branch client and the headquarters server being communicatively coupled over a network connection via the transmission media. The network connection is identified through a connection identifier. The system also includes a first point of presence (POP) communicatively coupled with the branch site over a first segment of the link.

Routing and service performance management in an application acceleration environment

A method and system of a heterogeneous service provider model through pay-for-performance based transit settlements are disclosed. In one embodiment, a system includes a plurality of Point of Presence (POP) locations between a head office and a branch office in a heterogeneous computer network configured to communicate data through a pay-per-performance peering relationship between different entities of the heterogeneous computer network. In this embodiment, the system implements a debit-credit mechanism configured to handle payments as well as penalties associated with violation of a pair-wise mutual agreement between independent for-profit entities providing network services in a segment of the heterogeneous computer network.

Heterogeneous service provider model through pay-for-performance based transit settlements

Mechanisms for storing and searching a hierarchy of policies and associations thereof are disclosed which may be particularly useful for implementing security protocols, such as, but not limited to Internet Protocol security (IPsec). For example, a hierarchy of policies is stored in a search priority order in an associative memory, with each association of a particular policy stored higher in the search priority than its associated policy and after any other policy. Therefore, a lookup operation on the associative memory will identify a matching association, if one, else its matching policy. A match of a policy instead of an association may result in a corresponding association being added in the appropriate location. For IPsec implementations, the lookup word is typically derived from the packet, with this packet being typically processed based on the identified policy or association.

Storing and searching a hierarchy of policies and associations thereof of particular use with IP security policies and security associations

Processes are disclosed in which an index value is generated for locating a security association in a security association database, such as an inbound SAD associated with the IPsec set of protocols. The index value is specified for insertion into a Security Parameter Index (SPI) field of a packet header, such as an IPsec header. For packets that are to be secured according to the policies and protocols identified in the header and the security association and that are transmitted to a particular network device or host, the index value is inserted into the SPI field of the packets by a packet sender. The packet is then parsed by a packet receiver, the index value determined from the SPI and used to identify the security association in the SAD, based solely on the index value determined from the SPI. Hence, a simple and efficient mechanism is provided for fast inbound security association lookups.

Method and apparatus for indexing an inbound security association database

Error protection is provided for associative memory entries and lookup operations performed thereon. Protected associative memory entries are determined which include one or more protection bits. These protected entries are programmed into an associative memory, typically with each protected entry being programmed into two or more consecutive locations. Corresponding protected lookup words are generated and used to perform lookup operations in the associative memory. For binary content-addressable memories (CAMs) and ternary content-addressable memory (TCAMs), one or more error detection bits are used per entry to prevent or at least reduce the possibility of a lookup error. For example, a single parity bit or multiple error-correction code (ECC) bits may be used per entry. The use of the protection bits reduces the possibility of a false matching of a corrupted entry, and the duplicate entries reduce the possibility of not matching an entry that should be matched as all copies of the entry must be corrupt in order to not match one of the entries during a lookup operation.

Error protection for associative memory entries and lookup operations performed thereon

Growing community of inventors

Los Altos Hills, CA, United States of America

Ashwath Nagaraj